[["calgarske-listy_2003_unor_ocr.txt", "CALGARSK\u00c9 LISTY (97) VYD\u00c1V\u00c1 CZECH AND SLOVAK ASSOCIATION OF CANADA, Calgary Branch P.O. Box 355, Calgary, Alberta T2P 2H9 ii\u2019ini\u2019. czcanada.", [["CALGARSK\u00c9", "calgarsk\u00fd", "ADJ", [0, 9]], ["LISTY", "list", "NOUN", [10, 15]], ["(", "(", "PUNCT", [16, 17]], ["97", "97", "NUM", [17, 19]], [")", ")", "PUNCT", [19, 20]], ["VYD\u00c1V\u00c1", "vyd\u00e1vat", "VERB", [21, 27]], ["CZECH", "CZECH", "NOUN", [28, 33]], ["AND", "And", "X", [34, 37]], ["SLOVAK", "Slovak", "X", [38, 44]], ["ASSOCIATION", "Association", "X", [45, 56]], ["OF", "Of", "X", [57, 59]], ["CANADA", "Canada", "X", [60, 66]], [",", ",", "PUNCT", [66, 67]], ["Calgary", "Calgary", "PROPN", [68, 75]], ["Branch", "Branch", "X", [76, 82]], ["P", "P", "NOUN", [83, 84]], [".", ".", "PUNCT", [84, 85]], ["O", "O", "NOUN", [85, 86]], [".", ".", "PUNCT", [86, 87]], ["Box", "box", "NOUN", [88, 91]], ["355", "355", "NUM", [92, 95]], [",", ",", "PUNCT", [95, 96]], ["Calgary", "Calgary", "PROPN", [97, 104]], [",", ",", "PUNCT", [104, 105]], ["Alberta", "Albert", "PROPN", [106, 113]], ["T", "T", "NOUN", [114, 115]], ["2P", "2P", "NOUN", [115, 117]], ["2H", "2egawaat", "NOUN", [118, 120]], ["9", "9", "NUM", [120, 121]], ["ii", "ii", "NUM", [122, 124]], ["\u2019", "'", "PUNCT", [124, 125]], ["ini", "ini", "NOUN", [125, 128]], ["\u2019", "'", "PUNCT", [128, 129]], [".", ".", "PUNCT", [129, 130]], ["czcanada", "czcanada", "NOUN", [131, 139]], [".", ".", "PUNCT", [139, 140]]]], ["calgarske-listy_2003_unor_ocr.txt", "com \u00danor 2003.", [["com", "com", "NOUN", [0, 3]], ["\u00danor", "\u00fanor", "NOUN", [4, 8]], ["2003", "2003", "NUM", [9, 13]], [".", ".", "PUNCT", [13, 14]]]], ["calgarske-listy_2003_unor_ocr.txt", "LEVO\u010cA.", [["LEVO\u010cA", "Levo\u010d", "PROPN", [0, 6]], [".", ".", "PUNCT", [6, 7]]]], ["calgarske-listy_2003_unor_ocr.txt", "Radnica vystaven\u00e1 uprostred levo\u010dsk\u00e9ho n\u00e1mestia v polovici 15. storo\u010dia, s\u00fa\u010das\u0165 mestskej pamiatkovej rezerv\u00e1cie, ktor\u00e1 si zachovala svoj stredovek\u00fd vzh\u013ead.", [["Radnica", "Radnica", "PROPN", [0, 7]], ["vystaven\u00e1", "vystaven\u00fd", "ADJ", [8, 17]], ["uprostred", "uprostred", "NOUN", [18, 27]], ["levo\u010dsk\u00e9ho", "levo\u010dsk\u00fd", "ADJ", [28, 38]], ["n\u00e1mestia", "n\u00e1mestia", "NOUN", [39, 47]], ["v", "v", "ADP", [48, 49]], ["polovici", "polovice", "NOUN", [50, 58]], ["15", "15", "NUM", [59, 61]], [".", ".", "PUNCT", [61, 62]], ["storo\u010dia", "storo\u010dia", "PROPN", [63, 71]], [",", ",", "PUNCT", [71, 72]], ["s\u00fa\u010das\u0165", "s\u00fa\u010das\u0165", "NOUN", [73, 79]], ["mestskej", "mestskej", "X", [80, 88]], ["pamiatkovej", "pamiatkovej", "X", [89, 100]], ["rezerv\u00e1cie", "rezerv\u00e1cie", "NOUN", [101, 111]], [",", ",", "PUNCT", [111, 112]], ["ktor\u00e1", "ktor\u00fd", "ADJ", [113, 118]], ["si", "se", "PRON", [119, 121]], ["zachovala", "zachovat", "VERB", [122, 131]], ["svoj", "svoj", "NOUN", [132, 136]], ["stredovek\u00fd", "stredovek\u00fd", "ADJ", [137, 147]], ["vzh\u013ead", "vzh\u013eada", "NOUN", [148, 154]], [".", ".", "PUNCT", [154, 155]]]], ["calgarske-listy_2003_unor_ocr.txt", "V budove je umiestnen\u00e9 muzeum.", [["V", "v", "ADP", [0, 1]], ["budove", "budove", "NOUN", [2, 8]], ["je", "b\u00fdt", "AUX", [9, 11]], ["umiestnen\u00e9", "umiestnen\u00fd", "ADJ", [12, 22]], ["muzeum", "muzeum", "NOUN", [23, 29]], [".", ".", "PUNCT", [29, 30]]]], ["calgarske-listy_2003_unor_ocr.txt", "Ve\u013ek\u00fa pozornos\u0165 si zasluhuje interi\u00e9r kostola.", [["Ve\u013ek\u00fa", "Ve\u013ek\u00fa", "PROPN", [0, 5]], ["pozornos\u0165", "pozornos\u0165", "NOUN", [6, 15]], ["si", "se", "PRON", [16, 18]], ["zasluhuje", "zasluhovat", "VERB", [19, 28]], ["interi\u00e9r", "interi\u00e9r", "NOUN", [29, 37]], ["kostola", "kostol", "NOUN", [38, 45]], [".", ".", "PUNCT", [45, 46]]]], ["calgarske-listy_2003_unor_ocr.txt", "S\u00fa to predov\u0161etk\u00fdm gotick\u00e9 olt\u00e1re a z nich najcennej\u0161\u00ed je hlavn\u00fd olt\u00e1r.", [["S\u00fa", "st\u00e1t", "VERB", [0, 2]], ["to", "ten", "DET", [3, 5]], ["predov\u0161etk\u00fdm", "predov\u0161etk\u00fd", "ADJ", [6, 18]], ["gotick\u00e9", "gotick\u00fd", "ADJ", [19, 26]], ["olt\u00e1re", "olt\u00e1r", "NOUN", [27, 33]], ["a", "a", "CCONJ", [34, 35]], ["z", "z", "ADP", [36, 37]], ["nich", "on", "PRON", [38, 42]], ["najcennej\u0161\u00ed", "najcenn\u00fd", "ADJ", [43, 54]], ["je", "b\u00fdt", "AUX", [55, 57]], ["hlavn\u00fd", "hlavn\u00fd", "ADJ", [58, 64]], ["olt\u00e1r", "olt\u00e1r", "NOUN", [65, 70]], [".", ".", "PUNCT", [70, 71]]]], ["calgarske-listy_2003_unor_ocr.txt", "Svojimi rozmermi sa rad\u00ed medzi najv\u00e4\u010d\u0161ie olt\u00e1re na svete.", [["Svojimi", "Svojimi", "PROPN", [0, 7]], ["rozmermi", "rozmermi", "X", [8, 16]], ["sa", "sa", "X", [17, 19]], ["rad\u00ed", "radit", "VERB", [20, 24]], ["medzi", "medze", "NOUN", [25, 30]], ["najv\u00e4\u010d\u0161ie", "najv\u00e4\u010d\u0161ie", "NOUN", [31, 40]], ["olt\u00e1re", "olt\u00e1r", "NOUN", [41, 47]], ["na", "na", "ADP", [48, 50]], ["svete", "svet", "NOUN", [51, 56]], [".", ".", "PUNCT", [56, 57]]]], ["calgarske-listy_2003_unor_ocr.txt", "M\u00e1 v\u00fd\u0161ku 18,62m, cel\u00fd je z lipov\u00e9ho dreva a vznikol v rokoch 1507-1517 v dielni soch\u00e1ra Majstra Pavla z Levo\u010de.", [["M\u00e1", "m\u00edt", "VERB", [0, 2]], ["v\u00fd\u0161ku", "v\u00fd\u0161ka", "NOUN", [3, 8]], ["18", "18", "NUM", [9, 11]], [",", ",", "PUNCT", [11, 12]], ["62m", "62m", "NUM", [12, 15]], [",", ",", "PUNCT", [15, 16]], ["cel\u00fd", "cel\u00fd", "ADJ", [17, 21]], ["je", "b\u00fdt", "AUX", [22, 24]], ["z", "z", "ADP", [25, 26]], ["lipov\u00e9ho", "lipov\u00fd", "ADJ", [27, 35]], ["dreva", "drevo", "NOUN", [36, 41]], ["a", "a", "CCONJ", [42, 43]], ["vznikol", "vznikol", "NOUN", [44, 51]], ["v", "v", "ADP", [52, 53]], ["rokoch", "rok", "NOUN", [54, 60]], ["1507", "1507", "NUM", [61, 65]], ["-", "-", "PUNCT", [65, 66]], ["1517", "1517", "NUM", [66, 70]], ["v", "v", "ADP", [71, 72]], ["dielni", "diele\u0148", "NOUN", [73, 79]], ["soch\u00e1ra", "soch\u00e1r", "NOUN", [80, 87]], ["Majstra", "Majstro", "PROPN", [88, 95]], ["Pavla", "Pavel", "PROPN", [96, 101]], ["z", "z", "ADP", [102, 103]], ["Levo\u010de", "Levo\u010d", "PROPN", [104, 110]], [".", ".", "PUNCT", [110, 111]]]], ["calgarske-listy_2003_unor_ocr.txt", "Kalend\u00e1\u0159 akc\u00ed calgarsk\u00e9 pobo\u010dky \u010cSSK", [["Kalend\u00e1\u0159", "kalend\u00e1\u0159", "NOUN", [0, 8]], ["akc\u00ed", "akce", "NOUN", [9, 13]], ["calgarsk\u00e9", "calgarsk\u00fd", "ADJ", [14, 23]], ["pobo\u010dky", "pobo\u010dka", "NOUN", [24, 31]], ["\u010cSSK", "\u010cSSK", "NOUN", [32, 36]]]], ["calgarske-listy_2003_unor_ocr.txt", "V \u00fater\u00fd dne 11. b\u0159ezna 2003 v 19:00 hodin bude v ma\u010farsk\u00e9m kostele St. Elizabeth\u2019s Church (819-13 Ave. SW. ) katolick\u00e1 m\u0161e sv\u00e1t\u00e1.", [["V", "v", "ADP", [0, 1]], ["\u00fater\u00fd", "\u00fater\u00fd", "NOUN", [2, 7]], ["dne", "den", "NOUN", [8, 11]], ["11", "11", "NUM", [12, 14]], [".", ".", "PUNCT", [14, 15]], ["b\u0159ezna", "b\u0159ezen", "NOUN", [16, 22]], ["2003", "2003", "NUM", [23, 27]], ["v", "v", "ADP", [28, 29]], ["19", "19", "NUM", [30, 32]], [":", ":", "PUNCT", [32, 33]], ["00", "00", "NUM", [33, 35]], ["hodin", "hodina", "NOUN", [36, 41]], ["bude", "b\u00fdt", "AUX", [42, 46]], ["v", "v", "ADP", [47, 48]], ["ma\u010farsk\u00e9m", "ma\u010farsk\u00fd", "ADJ", [49, 58]], ["kostele", "kostel", "NOUN", [59, 66]], ["St", "St", "X", [67, 69]], [".", ".", "PUNCT", [69, 70]], ["Elizabeth", "Elizabeth", "X", [71, 80]], ["\u2019", "'", "PUNCT", [80, 81]], ["s", "s", "ADP", [81, 82]], ["Church", "Church", "X", [83, 89]], ["(", "(", "PUNCT", [90, 91]], ["819", "819", "NUM", [91, 94]], ["-", "-", "PUNCT", [94, 95]], ["13", "13", "NUM", [95, 97]], ["Ave", "ava", "NOUN", [98, 101]], [".", ".", "PUNCT", [101, 102]], ["SW", "SW", "NOUN", [103, 105]], [".", ".", "PUNCT", [105, 106]], [")", ")", "PUNCT", [107, 108]], ["katolick\u00e1", "katolick\u00fd", "ADJ", [109, 118]], ["m\u0161e", "m\u0161e", "NOUN", [119, 122]], ["sv\u00e1t\u00e1", "sv\u00e1tat", "VERB", [123, 128]], [".", ".", "PUNCT", [128, 129]]]], ["calgarske-listy_2003_unor_ocr.txt", "Spolu s Otcem Svobodou p\u0159ijede emeritn\u00ed biskup ThDr. Jaroslav \u0160karvada z Prahy.", [["Spolu", "spolu", "ADV", [0, 5]], ["s", "s", "ADP", [6, 7]], ["Otcem", "otec", "NOUN", [8, 13]], ["Svobodou", "Svoboda", "PROPN", [14, 22]], ["p\u0159ijede", "p\u0159ijet", "VERB", [23, 30]], ["emeritn\u00ed", "emeritn\u00ed", "ADJ", [31, 39]], ["biskup", "biskup", "NOUN", [40, 46]], ["ThDr", "ThDr", "PROPN", [47, 51]], [".", ".", "PUNCT", [51, 52]], ["Jaroslav", "Jaroslav", "PROPN", [53, 61]], ["\u0160karvada", "\u0160karvada", "PROPN", [62, 70]], ["z", "z", "ADP", [71, 72]], ["Prahy", "Praha", "PROPN", [73, 78]], [".", ".", "PUNCT", [78, 79]]]], ["calgarske-listy_2003_unor_ocr.txt", "Svat\u00e1 zpov\u011b\u010f za\u010d\u00edn\u00e1 v 18:30.", [["Svat\u00e1", "svat\u00fd", "ADJ", [0, 5]], ["zpov\u011b\u010f", "zpov\u011b\u010f", "NOUN", [6, 12]], ["za\u010d\u00edn\u00e1", "za\u010d\u00ednat", "VERB", [13, 19]], ["v", "v", "ADP", [20, 21]], ["18", "18", "NUM", [22, 24]], [":", ":", "PUNCT", [24, 25]], ["30", "30", "NUM", [25, 27]], [".", ".", "PUNCT", [27, 28]]]], ["calgarske-listy_2003_unor_ocr.txt", "O bli\u017e\u0161\u00ed podrobnosti m\u016f\u017eete volat Ivanu H\u00fdskovi na \u010d\u00edslo 281-7799.", [["O", "o", "ADP", [0, 1]], ["bli\u017e\u0161\u00ed", "bl\u00edzk\u00fd", "ADJ", [2, 8]], ["podrobnosti", "podrobnost", "NOUN", [9, 20]], ["m\u016f\u017eete", "moci", "VERB", [21, 27]], ["volat", "volat", "VERB", [28, 33]], ["Ivanu", "Ivan", "PROPN", [34, 39]], ["H\u00fdskovi", "H\u00fdska", "PROPN", [40, 47]], ["na", "na", "ADP", [48, 50]], ["\u010d\u00edslo", "\u010d\u00edslo", "NOUN", [51, 56]], ["281", "281", "NUM", [57, 60]], ["-", "-", "PUNCT", [60, 61]], ["7799", "7799", "NUM", [61, 65]], [".", ".", "PUNCT", [65, 66]]]], ["calgarske-listy_2003_unor_ocr.txt", "V patek dne 14. b\u0159ezna 2003 v 18.00 - V\u00fdro\u010dn\u00ed \u010dlensk\u00e1 sch\u016fze v Royal Canadian Legion 755 - 40 St. SE Forest Lawn", [["V", "v", "ADP", [0, 1]], ["patek", "patek", "NOUN", [2, 7]], ["dne", "den", "NOUN", [8, 11]], ["14", "14", "NUM", [12, 14]], [".", ".", "PUNCT", [14, 15]], ["b\u0159ezna", "b\u0159ezen", "NOUN", [16, 22]], ["2003", "2003", "NUM", [23, 27]], ["v", "v", "ADP", [28, 29]], ["18.00", "18.00", "NUM", [30, 35]], ["-", "-", "PUNCT", [36, 37]], ["V\u00fdro\u010dn\u00ed", "v\u00fdro\u010dn\u00ed", "ADJ", [38, 45]], ["\u010dlensk\u00e1", "\u010dlensk\u00fd", "ADJ", [46, 53]], ["sch\u016fze", "sch\u016fze", "NOUN", [54, 60]], ["v", "v", "ADP", [61, 62]], ["Royal", "Royal", "X", [63, 68]], ["Canadian", "Canadian", "X", [69, 77]], ["Legion", "Legion", "X", [78, 84]], ["755", "755", "NUM", [85, 88]], ["-", "-", "PUNCT", [89, 90]], ["40", "40", "NUM", [91, 93]], ["St", "st\u0159eda", "NOUN", [94, 96]], [".", ".", "PUNCT", [96, 97]], ["SE", "se", "PRON", [98, 100]], ["Forest", "Forest", "X", [101, 107]], ["Lawn", "Lawn", "X", [108, 112]]]], ["calgarske-listy_2003_unor_ocr.txt", "V sobotu dne 29. b\u0159ezna 2003 v 18.30 hod - JOSEFOVSK\u00c1 Z\u00c1BAVA v Royal Canadian Legion 755 - 40 St. SE Forest Lawn", [["V", "v", "ADP", [0, 1]], ["sobotu", "sobota", "NOUN", [2, 8]], ["dne", "den", "NOUN", [9, 12]], ["29", "29", "NUM", [13, 15]], [".", ".", "PUNCT", [15, 16]], ["b\u0159ezna", "b\u0159ezen", "NOUN", [17, 23]], ["2003", "2003", "NUM", [24, 28]], ["v", "v", "ADP", [29, 30]], ["18.30", "18.30", "NUM", [31, 36]], ["hod", "hodina", "NOUN", [37, 40]], ["-", "-", "PUNCT", [41, 42]], ["JOSEFOVSK\u00c1", "josefovsk\u00fd", "ADJ", [43, 53]], ["Z\u00c1BAVA", "z\u00e1bava", "NOUN", [54, 60]], ["v", "v", "ADP", [61, 62]], ["Royal", "Royal", "X", [63, 68]], ["Canadian", "Canadian", "X", [69, 77]], ["Legion", "Legion", "X", [78, 84]], ["755", "755", "NUM", [85, 88]], ["-", "-", "PUNCT", [89, 90]], ["40", "40", "NUM", [91, 93]], ["St", "st\u0159eda", "NOUN", [94, 96]], [".", ".", "PUNCT", [96, 97]], ["SE", "s", "ADP", [98, 100]], ["Forest", "Forest", "X", [101, 107]], ["Lawn", "Lawn", "X", [108, 112]]]], ["calgarske-listy_2003_unor_ocr.txt", "Pozv\u00e1n\u00ed : V patek 14. b\u0159ezna 2003 v 18.00 hodin se kon\u00e1 V\u00fdro\u010dn\u00ed \u010dlensk\u00e1 sch\u016fze calgarsk\u00e9 odbo\u010dky \u010cSSK v Royal Canadian Club na shora uveden\u00e9 adrese s t\u00edmto programem: 1. Zah\u00e1jen\u00ed a p\u0159iv\u00edt\u00e1n\u00ed p\u0159\u00edtomn\u00fdch 2.", [["Pozv\u00e1n\u00ed", "pozv\u00e1n\u00ed", "NOUN", [0, 7]], [":", ":", "PUNCT", [8, 9]], ["V", "v", "ADP", [10, 11]], ["patek", "patek", "NOUN", [12, 17]], ["14", "14", "NUM", [18, 20]], [".", ".", "PUNCT", [20, 21]], ["b\u0159ezna", "b\u0159ezen", "NOUN", [22, 28]], ["2003", "2003", "NUM", [29, 33]], ["v", "v", "ADP", [34, 35]], ["18.00", "18.00", "NUM", [36, 41]], ["hodin", "hodina", "NOUN", [42, 47]], ["se", "se", "PRON", [48, 50]], ["kon\u00e1", "konat", "VERB", [51, 55]], ["V\u00fdro\u010dn\u00ed", "v\u00fdro\u010dn\u00ed", "ADJ", [56, 63]], ["\u010dlensk\u00e1", "\u010dlensk\u00fd", "ADJ", [64, 71]], ["sch\u016fze", "sch\u016fze", "NOUN", [72, 78]], ["calgarsk\u00e9", "calgarsk\u00fd", "ADJ", [79, 88]], ["odbo\u010dky", "odbo\u010dka", "NOUN", [89, 96]], ["\u010cSSK", "\u010cSSK", "NOUN", [97, 101]], ["v", "v", "ADP", [102, 103]], ["Royal", "Royal", "X", [104, 109]], ["Canadian", "Canadian", "X", [110, 118]], ["Club", "Club", "X", [119, 123]], ["na", "na", "ADP", [124, 126]], ["shora", "shora", "ADV", [127, 132]], ["uveden\u00e9", "uveden\u00fd", "ADJ", [133, 140]], ["adrese", "adresa", "NOUN", [141, 147]], ["s", "s", "ADP", [148, 149]], ["t\u00edmto", "tento", "DET", [150, 155]], ["programem", "program", "NOUN", [156, 165]], [":", ":", "PUNCT", [165, 166]], ["1", "1", "NUM", [167, 168]], [".", ".", "PUNCT", [168, 169]], ["Zah\u00e1jen\u00ed", "zah\u00e1jen\u00ed", "NOUN", [170, 178]], ["a", "a", "CCONJ", [179, 180]], ["p\u0159iv\u00edt\u00e1n\u00ed", "p\u0159iv\u00edt\u00e1n\u00ed", "NOUN", [181, 190]], ["p\u0159\u00edtomn\u00fdch", "p\u0159\u00edtomn\u00fd", "ADJ", [191, 201]], ["2", "2", "NUM", [202, 203]], [".", ".", "PUNCT", [203, 204]]]], ["calgarske-listy_2003_unor_ocr.txt", "P\u0159e\u010dten\u00ed z\u00e1pisu z minul\u00e9 v\u00fdr. sch\u016fze 3.", [["P\u0159e\u010dten\u00ed", "p\u0159e\u010dten\u00ed", "NOUN", [0, 8]], ["z\u00e1pisu", "z\u00e1pis", "NOUN", [9, 15]], ["z", "z", "ADP", [16, 17]], ["minul\u00e9", "minul\u00fd", "ADJ", [18, 24]], ["v\u00fdr", "v\u00fdr", "NOUN", [25, 28]], [".", ".", "PUNCT", [28, 29]], ["sch\u016fze", "sch\u016fze", "NOUN", [30, 36]], ["3", "3", "NUM", [37, 38]], [".", ".", "PUNCT", [38, 39]]]], ["calgarske-listy_2003_unor_ocr.txt", "Pokladn\u00ed zpr\u00e1va 4. Revizn\u00ed zpr\u00e1va 5. Zpr\u00e1va p\u0159edsedy 6. Volba nov\u00e9ho v\u00fdboru 7. N\u00e1vrhy na dal\u0161\u00ed akce 8. Dizkuze.", [["Pokladn\u00ed", "pokladn\u00ed", "ADJ", [0, 8]], ["zpr\u00e1va", "zpr\u00e1va", "NOUN", [9, 15]], ["4", "4", "NUM", [16, 17]], [".", ".", "PUNCT", [17, 18]], ["Revizn\u00ed", "revizn\u00ed", "ADJ", [19, 26]], ["zpr\u00e1va", "zpr\u00e1va", "NOUN", [27, 33]], ["5", "5", "NUM", [34, 35]], [".", ".", "PUNCT", [35, 36]], ["Zpr\u00e1va", "zpr\u00e1va", "NOUN", [37, 43]], ["p\u0159edsedy", "p\u0159edseda", "NOUN", [44, 52]], ["6", "6", "NUM", [53, 54]], [".", ".", "PUNCT", [54, 55]], ["Volba", "volba", "NOUN", [56, 61]], ["nov\u00e9ho", "nov\u00fd", "ADJ", [62, 68]], ["v\u00fdboru", "v\u00fdbor", "NOUN", [69, 75]], ["7", "7", "NUM", [76, 77]], [".", ".", "PUNCT", [77, 78]], ["N\u00e1vrhy", "n\u00e1vrh", "NOUN", [79, 85]], ["na", "na", "ADP", [86, 88]], ["dal\u0161\u00ed", "dal\u0161\u00ed", "ADJ", [89, 94]], ["akce", "akce", "NOUN", [95, 99]], ["8", "8", "NUM", [100, 101]], [".", ".", "PUNCT", [101, 102]], ["Dizkuze", "Dizkuz", "PROPN", [103, 110]], [".", ".", "PUNCT", [110, 111]]]], ["calgarske-listy_2003_unor_ocr.txt", "V\u00e1\u017een\u00ed krajan\u00e9 a mili \u010dten\u00e1\u0159i, V\u00fdbor na\u0161\u00ed pobo\u010dky neml\u00e1dne.", [["V\u00e1\u017een\u00ed", "v\u00e1\u017een\u00fd", "ADJ", [0, 6]], ["krajan\u00e9", "krajan", "NOUN", [7, 14]], ["a", "a", "CCONJ", [15, 16]], ["mili", "mili", "NOUN", [17, 21]], ["\u010dten\u00e1\u0159i", "\u010dten\u00e1\u0159", "NOUN", [22, 29]], [",", ",", "PUNCT", [29, 30]], ["V\u00fdbor", "v\u00fdbor", "NOUN", [31, 36]], ["na\u0161\u00ed", "n\u00e1\u0161", "DET", [37, 41]], ["pobo\u010dky", "pobo\u010dka", "NOUN", [42, 49]], ["neml\u00e1dne", "ml\u00e1dnout", "VERB", [50, 58]], [".", ".", "PUNCT", [58, 59]]]], ["calgarske-listy_2003_unor_ocr.txt", "S pot\u011b\u0161en\u00edm a s velkou radost\u00ed up\u0159\u00edmn\u011b p\u0159iv\u00edt\u00e1me mezi n\u00e1s mlad\u0161\u00ed \u010cechoslov\u00e1ky s nov\u00fdmi n\u00e1pady nebo n\u00e1vrhy, el\u00e1nem a chut\u00ed dobrovoln\u00e9 pr\u00e1ce.", [["S", "s", "ADP", [0, 1]], ["pot\u011b\u0161en\u00edm", "pot\u011b\u0161en\u00ed", "NOUN", [2, 11]], ["a", "a", "CCONJ", [12, 13]], ["s", "s", "ADP", [14, 15]], ["velkou", "velk\u00fd", "ADJ", [16, 22]], ["radost\u00ed", "radost", "NOUN", [23, 30]], ["up\u0159\u00edmn\u011b", "up\u0159\u00edmn\u011b", "ADV", [31, 38]], ["p\u0159iv\u00edt\u00e1me", "p\u0159iv\u00edtat", "VERB", [39, 48]], ["mezi", "mezi", "ADP", [49, 53]], ["n\u00e1s", "my", "PRON", [54, 57]], ["mlad\u0161\u00ed", "mlad\u00fd", "ADJ", [58, 64]], ["\u010cechoslov\u00e1ky", "\u010cechoslov\u00e1k", "PROPN", [65, 77]], ["s", "s", "ADP", [78, 79]], ["nov\u00fdmi", "nov\u00fd", "ADJ", [80, 86]], ["n\u00e1pady", "n\u00e1pad", "NOUN", [87, 93]], ["nebo", "nebo", "CCONJ", [94, 98]], ["n\u00e1vrhy", "n\u00e1vrh", "NOUN", [99, 105]], [",", ",", "PUNCT", [105, 106]], ["el\u00e1nem", "el\u00e1n", "NOUN", [107, 113]], ["a", "a", "CCONJ", [114, 115]], ["chut\u00ed", "chu\u0165", "NOUN", [116, 121]], ["dobrovoln\u00e9", "dobrovoln\u00fd", "ADJ", [122, 132]], ["pr\u00e1ce", "pr\u00e1ce", "NOUN", [133, 138]], [".", ".", "PUNCT", [138, 139]]]], ["calgarske-listy_2003_unor_ocr.txt", "Nesty\u010fte se a p\u0159ij\u010fte mezi n\u00e1s v hojn\u00e9m po\u010dtu.", [["Nesty\u010fte", "styt", "VERB", [0, 8]], ["se", "se", "PRON", [9, 11]], ["a", "a", "CCONJ", [12, 13]], ["p\u0159ij\u010fte", "p\u0159ij\u00edt", "VERB", [14, 21]], ["mezi", "mezi", "ADP", [22, 26]], ["n\u00e1s", "my", "PRON", [27, 30]], ["v", "v", "ADP", [31, 32]], ["hojn\u00e9m", "hojn\u00fd", "ADJ", [33, 39]], ["po\u010dtu", "po\u010det", "NOUN", [40, 45]], [".", ".", "PUNCT", [45, 46]]]], ["calgarske-listy_2003_unor_ocr.txt", "T\u011b\u0161\u00edme se na v\u00e1s a d\u011bkujeme p\u0159edem za hojnou \u00fa\u010dast.", [["T\u011b\u0161\u00edme", "t\u011b\u0161it", "VERB", [0, 6]], ["se", "se", "PRON", [7, 9]], ["na", "na", "ADP", [10, 12]], ["v\u00e1s", "vy", "PRON", [13, 16]], ["a", "a", "CCONJ", [17, 18]], ["d\u011bkujeme", "d\u011bkovat", "VERB", [19, 27]], ["p\u0159edem", "p\u0159edem", "ADV", [28, 34]], ["za", "za", "ADP", [35, 37]], ["hojnou", "hojn\u00fd", "ADJ", [38, 44]], ["\u00fa\u010dast", "\u00fa\u010dast", "NOUN", [45, 50]], [".", ".", "PUNCT", [50, 51]]]], ["calgarske-listy_2003_unor_ocr.txt", "Pobo\u010dka \u010desk\u00e9ho a slovensk\u00e9ho sdru\u017een\u00ed v Calgary v\u00e1s v\u0161echny up\u0159\u00edmn\u011b zve na Josefovskou z\u00e1bavu konanou v klubu veter\u00e1n\u016f na adrese jak v\u00fd\u0161e uvedeno v sobotu 29. b\u0159ezna 2003 v 18.30 hodin.", [["Pobo\u010dka", "pobo\u010dka", "NOUN", [0, 7]], ["\u010desk\u00e9ho", "\u010desk\u00fd", "ADJ", [8, 15]], ["a", "a", "CCONJ", [16, 17]], ["slovensk\u00e9ho", "slovensk\u00fd", "ADJ", [18, 29]], ["sdru\u017een\u00ed", "sdru\u017een\u00ed", "NOUN", [30, 38]], ["v", "v", "ADP", [39, 40]], ["Calgary", "Calgary", "PROPN", [41, 48]], ["v\u00e1s", "vy", "PRON", [49, 52]], ["v\u0161echny", "v\u0161echen", "DET", [53, 60]], ["up\u0159\u00edmn\u011b", "up\u0159\u00edmn\u011b", "ADV", [61, 68]], ["zve", "zv\u00e1t", "VERB", [69, 72]], ["na", "na", "ADP", [73, 75]], ["Josefovskou", "josefovsk\u00fd", "ADJ", [76, 87]], ["z\u00e1bavu", "z\u00e1bava", "NOUN", [88, 94]], ["konanou", "konan\u00fd", "ADJ", [95, 102]], ["v", "v", "ADP", [103, 104]], ["klubu", "klub", "NOUN", [105, 110]], ["veter\u00e1n\u016f", "veter\u00e1n", "NOUN", [111, 119]], ["na", "na", "ADP", [120, 122]], ["adrese", "adresa", "NOUN", [123, 129]], ["jak", "jak", "ADV", [130, 133]], ["v\u00fd\u0161e", "vysoko", "ADV", [134, 138]], ["uvedeno", "uveden\u00fd", "ADJ", [139, 146]], ["v", "v", "ADP", [147, 148]], ["sobotu", "sobota", "NOUN", [149, 155]], ["29", "29", "NUM", [156, 158]], [".", ".", "PUNCT", [158, 159]], ["b\u0159ezna", "b\u0159ezen", "NOUN", [160, 166]], ["2003", "2003", "NUM", [167, 171]], ["v", "v", "ADP", [172, 173]], ["18.30", "18.30", "NUM", [174, 179]], ["hodin", "hodina", "NOUN", [180, 185]], [".", ".", "PUNCT", [185, 186]]]], ["calgarske-listy_2003_unor_ocr.txt", "\u010cesk\u00e9 duo JANA & DANNY bude hr\u00e1t k poslechu a tanci..", [["\u010cesk\u00e9", "\u010desk\u00fd", "ADJ", [0, 5]], ["duo", "duo", "NOUN", [6, 9]], ["JANA", "Jan", "PROPN", [10, 14]], ["&", "&", "PUNCT", [15, 16]], ["DANNY", "Danna", "PROPN", [17, 22]], ["bude", "b\u00fdt", "AUX", [23, 27]], ["hr\u00e1t", "hr\u00e1t", "VERB", [28, 32]], ["k", "k", "ADP", [33, 34]], ["poslechu", "poslech", "NOUN", [35, 43]], ["a", "a", "CCONJ", [44, 45]], ["tanci", "tanec", "NOUN", [46, 51]], [".", ".", "PUNCT", [51, 52]], [".", ".", "PUNCT", [52, 53]]]], ["calgarske-listy_2003_unor_ocr.txt", "Vstupenky po $25.00 jsou v p\u0159edprodeji do 26. b\u0159ezna na jihu u Marcely Krausov\u00e9 na tel. 278-7766 a na severu u Bo\u017eeny Kellnerov\u00e9 na tel. do pr\u00e1ce 276-7808 nebo v podve\u010der dom\u016f na tel. 295-8438.", [["Vstupenky", "vstupenka", "NOUN", [0, 9]], ["po", "po", "ADP", [10, 12]], ["$25.00", "$25.00", "NUM", [13, 19]], ["jsou", "b\u00fdt", "AUX", [20, 24]], ["v", "v", "ADP", [25, 26]], ["p\u0159edprodeji", "p\u0159edprodej", "NOUN", [27, 38]], ["do", "do", "ADP", [39, 41]], ["26", "26", "NUM", [42, 44]], [".", ".", "PUNCT", [44, 45]], ["b\u0159ezna", "b\u0159ezen", "NOUN", [46, 52]], ["na", "na", "ADP", [53, 55]], ["jihu", "jih", "NOUN", [56, 60]], ["u", "u", "ADP", [61, 62]], ["Marcely", "Marcela", "PROPN", [63, 70]], ["Krausov\u00e9", "Krausov\u00e1", "PROPN", [71, 79]], ["na", "na", "ADP", [80, 82]], ["tel", "telefon", "NOUN", [83, 86]], [".", ".", "PUNCT", [86, 87]], ["278", "278", "NUM", [88, 91]], ["-", "-", "PUNCT", [91, 92]], ["7766", "7766", "NUM", [92, 96]], ["a", "a", "CCONJ", [97, 98]], ["na", "na", "ADP", [99, 101]], ["severu", "sever", "NOUN", [102, 108]], ["u", "u", "ADP", [109, 110]], ["Bo\u017eeny", "Bo\u017eena", "PROPN", [111, 117]], ["Kellnerov\u00e9", "Kellnerov\u00e1", "PROPN", [118, 128]], ["na", "na", "ADP", [129, 131]], ["tel", "telefon", "NOUN", [132, 135]], [".", ".", "PUNCT", [135, 136]], ["do", "do", "ADP", [137, 139]], ["pr\u00e1ce", "pr\u00e1ce", "NOUN", [140, 145]], ["276", "276", "NUM", [146, 149]], ["-", "-", "PUNCT", [149, 150]], ["7808", "7808", "NUM", [150, 154]], ["nebo", "nebo", "CCONJ", [155, 159]], ["v", "v", "ADP", [160, 161]], ["podve\u010der", "podve\u010der", "NOUN", [162, 170]], ["dom\u016f", "dom\u016f", "ADV", [171, 175]], ["na", "na", "ADP", [176, 178]], ["tel", "telefon", "NOUN", [179, 182]], [".", ".", "PUNCT", [182, 183]], ["295", "295", "NUM", [184, 187]], ["-", "-", "PUNCT", [187, 188]], ["8438", "8438", "NUM", [188, 192]], [".", ".", "PUNCT", [192, 193]]]], ["calgarske-listy_2003_unor_ocr.txt", "Kvalitn\u00ed ve\u010de\u0159i (sal\u00e1t z \u010derstv\u00e9 zeleniny, moravsk\u00fd brabec se zel\u00edm a knedl\u00edkem nebo ku\u0159ec\u00ed prs\u00ed\u010dka) n\u00e1m v\u0161em p\u0159iprav\u00ed ob\u011btav\u00fd m\u00edstop\u0159edseda na\u0161\u00ed pobo\u010dky a mana\u017eer podniku Pavel Hebelka.", [["Kvalitn\u00ed", "kvalitn\u00ed", "ADJ", [0, 8]], ["ve\u010de\u0159i", "ve\u010de\u0159e", "NOUN", [9, 15]], ["(", "(", "PUNCT", [16, 17]], ["sal\u00e1t", "sal\u00e1t", "NOUN", [17, 22]], ["z", "z", "ADP", [23, 24]], ["\u010derstv\u00e9", "\u010derstv\u00fd", "ADJ", [25, 32]], ["zeleniny", "zelenina", "NOUN", [33, 41]], [",", ",", "PUNCT", [41, 42]], ["moravsk\u00fd", "moravsk\u00fd", "ADJ", [43, 51]], ["brabec", "brabec", "NOUN", [52, 58]], ["se", "s", "ADP", [59, 61]], ["zel\u00edm", "zel\u00ed", "NOUN", [62, 67]], ["a", "a", "CCONJ", [68, 69]], ["knedl\u00edkem", "knedl\u00edk", "NOUN", [70, 79]], ["nebo", "nebo", "CCONJ", [80, 84]], ["ku\u0159ec\u00ed", "ku\u0159ec\u00ed", "ADJ", [85, 91]], ["prs\u00ed\u010dka", "prs\u00ed\u010dko", "NOUN", [92, 99]], [")", ")", "PUNCT", [99, 100]], ["n\u00e1m", "my", "PRON", [101, 104]], ["v\u0161em", "v\u0161echen", "DET", [105, 109]], ["p\u0159iprav\u00ed", "p\u0159ipravit", "VERB", [110, 118]], ["ob\u011btav\u00fd", "ob\u011btav\u00fd", "ADJ", [119, 126]], ["m\u00edstop\u0159edseda", "m\u00edstop\u0159edseda", "NOUN", [127, 140]], ["na\u0161\u00ed", "n\u00e1\u0161", "DET", [141, 145]], ["pobo\u010dky", "pobo\u010dka", "NOUN", [146, 153]], ["a", "a", "CCONJ", [154, 155]], ["mana\u017eer", "mana\u017eer", "NOUN", [156, 163]], ["podniku", "podnik", "NOUN", [164, 171]], ["Pavel", "Pavel", "PROPN", [172, 177]], ["Hebelka", "Hebelka", "PROPN", [178, 185]], [".", ".", "PUNCT", [185, 186]]]], ["calgarske-listy_2003_unor_ocr.txt", "Po p\u0159\u00edpitku, ve\u010de\u0159e se bude pod\u00e1vat pouze na zakoupenou vstupenku.", [["Po", "po", "ADP", [0, 2]], ["p\u0159\u00edpitku", "p\u0159\u00edpitek", "NOUN", [3, 11]], [",", ",", "PUNCT", [11, 12]], ["ve\u010de\u0159e", "ve\u010de\u0159e", "NOUN", [13, 19]], ["se", "se", "PRON", [20, 22]], ["bude", "b\u00fdt", "AUX", [23, 27]], ["pod\u00e1vat", "pod\u00e1vat", "VERB", [28, 35]], ["pouze", "pouze", "ADV", [36, 41]], ["na", "na", "ADP", [42, 44]], ["zakoupenou", "zakoupen\u00fd", "ADJ", [45, 55]], ["vstupenku", "vstupenka", "NOUN", [56, 65]], [".", ".", "PUNCT", [65, 66]]]], ["calgarske-listy_2003_unor_ocr.txt", "Po dezertu s k\u00e1vou nebo s \u010dajem za doprovodu v\u00fdborn\u00e9 muziky a obl\u00edben\u00fdch p\u00edsni\u010dek n\u00e1sleduje tanec a p\u0159\u00edjemn\u00e1 z\u00e1bava.", [["Po", "po", "ADP", [0, 2]], ["dezertu", "dezert", "NOUN", [3, 10]], ["s", "s", "ADP", [11, 12]], ["k\u00e1vou", "k\u00e1va", "NOUN", [13, 18]], ["nebo", "nebo", "CCONJ", [19, 23]], ["s", "s", "ADP", [24, 25]], ["\u010dajem", "\u010dajem", "NOUN", [26, 31]], ["za", "za", "ADP", [32, 34]], ["doprovodu", "doprovod", "NOUN", [35, 44]], ["v\u00fdborn\u00e9", "v\u00fdborn\u00fd", "ADJ", [45, 52]], ["muziky", "muzika", "NOUN", [53, 59]], ["a", "a", "CCONJ", [60, 61]], ["obl\u00edben\u00fdch", "obl\u00edben\u00fd", "ADJ", [62, 72]], ["p\u00edsni\u010dek", "p\u00edsni\u010dka", "NOUN", [73, 81]], ["n\u00e1sleduje", "n\u00e1sledovat", "VERB", [82, 91]], ["tanec", "tanec", "NOUN", [92, 97]], ["a", "a", "CCONJ", [98, 99]], ["p\u0159\u00edjemn\u00e1", "p\u0159\u00edjemn\u00fd", "ADJ", [100, 108]], ["z\u00e1bava", "z\u00e1bava", "NOUN", [109, 115]], [".", ".", "PUNCT", [115, 116]]]], ["calgarske-listy_2003_unor_ocr.txt", "Nenech\u00e1vejte pros\u00edm nic na posledn\u00ed chv\u00edli.", [["Nenech\u00e1vejte", "nech\u00e1vat", "VERB", [0, 12]], ["pros\u00edm", "prosit", "VERB", [13, 19]], ["nic", "nic", "PRON", [20, 23]], ["na", "na", "ADP", [24, 26]], ["posledn\u00ed", "posledn\u00ed", "ADJ", [27, 35]], ["chv\u00edli", "chv\u00edle", "NOUN", [36, 42]], [".", ".", "PUNCT", [42, 43]]]], ["calgarske-listy_2003_unor_ocr.txt", "T\u011b\u0161\u00edme se na va\u0161i n\u00e1v\u0161t\u011bvu.", [["T\u011b\u0161\u00edme", "t\u011b\u0161it", "VERB", [0, 6]], ["se", "se", "PRON", [7, 9]], ["na", "na", "ADP", [10, 12]], ["va\u0161i", "v\u00e1\u0161", "DET", [13, 17]], ["n\u00e1v\u0161t\u011bvu", "n\u00e1v\u0161t\u011bva", "NOUN", [18, 26]], [".", ".", "PUNCT", [26, 27]]]], ["calgarske-listy_2003_unor_ocr.txt", "OZN\u00c1MEN\u00cd", [["OZN\u00c1MEN\u00cd", "ozn\u00e1men\u00ed", "NOUN", [0, 8]]]], ["calgarske-listy_2003_unor_ocr.txt", "Tak jako v minul\u00fdch l\u00e9tech i letos bude po\u0159\u00e1d\u00e1n pr\u00e1zdninov\u00fd kurz \u010desk\u00e9ho jazyka v \u010cesk\u00e9 republice v dob\u011b od 26.7. do 23.8.2003 ve studijn\u00edch st\u0159edisc\u00edch \u00dastavu jazykov\u00e9 a odborn\u00e9 p\u0159\u00edpravy Univerzity Karlovy v Dobru\u0161ce a v Zahr\u00e1dk\u00e1ch u \u010cesk\u00e9 L\u00edpy.", [["Tak", "tak", "ADV", [0, 3]], ["jako", "jako", "SCONJ", [4, 8]], ["v", "v", "ADP", [9, 10]], ["minul\u00fdch", "minul\u00fd", "ADJ", [11, 19]], ["l\u00e9tech", "l\u00e9ta", "NOUN", [20, 26]], ["i", "i", "CCONJ", [27, 28]], ["letos", "letos", "ADV", [29, 34]], ["bude", "b\u00fdt", "AUX", [35, 39]], ["po\u0159\u00e1d\u00e1n", "po\u0159\u00e1dan\u00fd", "ADJ", [40, 47]], ["pr\u00e1zdninov\u00fd", "pr\u00e1zdninov\u00fd", "ADJ", [48, 59]], ["kurz", "kurz", "NOUN", [60, 64]], ["\u010desk\u00e9ho", "\u010desk\u00fd", "ADJ", [65, 72]], ["jazyka", "jazyk", "NOUN", [73, 79]], ["v", "v", "ADP", [80, 81]], ["\u010cesk\u00e9", "\u010desk\u00fd", "ADJ", [82, 87]], ["republice", "republika", "NOUN", [88, 97]], ["v", "v", "ADP", [98, 99]], ["dob\u011b", "doba", "NOUN", [100, 104]], ["od", "od", "ADP", [105, 107]], ["26.7", "26.7", "NUM", [108, 112]], [".", ".", "PUNCT", [112, 113]], ["do", "do", "ADP", [114, 116]], ["23.8.2003", "23.8.2003", "NUM", [117, 126]], ["ve", "v", "ADP", [127, 129]], ["studijn\u00edch", "studijn\u00ed", "ADJ", [130, 140]], ["st\u0159edisc\u00edch", "st\u0159edisko", "NOUN", [141, 152]], ["\u00dastavu", "\u00fastav", "NOUN", [153, 159]], ["jazykov\u00e9", "jazykov\u00fd", "ADJ", [160, 168]], ["a", "a", "CCONJ", [169, 170]], ["odborn\u00e9", "odborn\u00fd", "ADJ", [171, 178]], ["p\u0159\u00edpravy", "p\u0159\u00edprava", "NOUN", [179, 187]], ["Univerzity", "univerzita", "NOUN", [188, 198]], ["Karlovy", "Karl\u016fv", "ADJ", [199, 206]], ["v", "v", "ADP", [207, 208]], ["Dobru\u0161ce", "Dobru\u0161c", "PROPN", [209, 217]], ["a", "a", "CCONJ", [218, 219]], ["v", "v", "ADP", [220, 221]], ["Zahr\u00e1dk\u00e1ch", "zahr\u00e1dka", "NOUN", [222, 232]], ["u", "u", "ADP", [233, 234]], ["\u010cesk\u00e9", "\u010desk\u00fd", "ADJ", [235, 240]], ["L\u00edpy", "l\u00edpa", "PROPN", [241, 245]], [".", ".", "PUNCT", [245, 246]]]], ["calgarske-listy_2003_unor_ocr.txt", "Z\u00e1jemci o bli\u017e\u0161\u00ed informace a p\u0159ihl\u00e1\u0161ku mohou kontaktovat Vladim\u00edra Ma\u0161atu nebo Bo\u017eenu Kellnerovou.", [["Z\u00e1jemci", "z\u00e1jemce", "NOUN", [0, 7]], ["o", "o", "ADP", [8, 9]], ["bli\u017e\u0161\u00ed", "bl\u00edzk\u00fd", "ADJ", [10, 16]], ["informace", "informace", "NOUN", [17, 26]], ["a", "a", "CCONJ", [27, 28]], ["p\u0159ihl\u00e1\u0161ku", "p\u0159ihl\u00e1\u0161ka", "NOUN", [29, 38]], ["mohou", "moci", "VERB", [39, 44]], ["kontaktovat", "kontaktovat", "VERB", [45, 56]], ["Vladim\u00edra", "Vladim\u00edr", "PROPN", [57, 66]], ["Ma\u0161atu", "Ma\u0161at", "PROPN", [67, 73]], ["nebo", "nebo", "CCONJ", [74, 78]], ["Bo\u017eenu", "Bo\u017een", "PROPN", [79, 85]], ["Kellnerovou", "Kellnerov\u00e1", "PROPN", [86, 97]], [".", ".", "PUNCT", [97, 98]]]], ["calgarske-listy_2003_unor_ocr.txt", "P\u0159ihl\u00e1\u0161ku je nutno zaslat na velvyslanectv\u00ed do 31 .b\u0159ezna 2003.", [["P\u0159ihl\u00e1\u0161ku", "p\u0159ihl\u00e1\u0161ka", "NOUN", [0, 9]], ["je", "b\u00fdt", "AUX", [10, 12]], ["nutno", "nutn\u00fd", "ADJ", [13, 18]], ["zaslat", "zaslat", "VERB", [19, 25]], ["na", "na", "ADP", [26, 28]], ["velvyslanectv\u00ed", "velvyslanectv\u00ed", "NOUN", [29, 43]], ["do", "do", "ADP", [44, 46]], ["31", "31", "NUM", [47, 49]], [".", ".", "PUNCT", [50, 51]], ["b\u0159ezna", "b\u0159ezen", "NOUN", [51, 57]], ["2003", "2003", "NUM", [58, 62]], [".", ".", "PUNCT", [62, 63]]]], ["calgarske-listy_2003_unor_ocr.txt", "OZN\u00c1MEN\u00cdo do\u010dasn\u00e9 adrese kancel\u00e1\u0159e honor\u00e1rn\u00edho konzul\u00e1tu- (po dobu \u00faprav m\u00edstnost\u00ed) Nov\u00e1 adresa honor\u00e1rn\u00edho konzul\u00e1tu \u010cesk\u00e9 republiky v Calgary: 611 - 71 st. Avenue SE Calgary, AB T2H1K4.", [["OZN\u00c1MEN\u00cdo", "ozn\u00e1men\u00edo", "NOUN", [0, 9]], ["do\u010dasn\u00e9", "do\u010dasn\u00fd", "ADJ", [10, 17]], ["adrese", "adresa", "NOUN", [18, 24]], ["kancel\u00e1\u0159e", "kancel\u00e1\u0159", "NOUN", [25, 34]], ["honor\u00e1rn\u00edho", "honor\u00e1rn\u00ed", "ADJ", [35, 46]], ["konzul\u00e1tu", "konzul\u00e1t", "NOUN", [47, 56]], ["-", "-", "PUNCT", [56, 57]], ["(", "(", "PUNCT", [58, 59]], ["po", "po", "ADP", [59, 61]], ["dobu", "doba", "NOUN", [62, 66]], ["\u00faprav", "\u00faprava", "NOUN", [67, 72]], ["m\u00edstnost\u00ed", "m\u00edstnost", "NOUN", [73, 82]], [")", ")", "PUNCT", [82, 83]], ["Nov\u00e1", "nov\u00fd", "ADJ", [84, 88]], ["adresa", "adresa", "NOUN", [89, 95]], ["honor\u00e1rn\u00edho", "honor\u00e1rn\u00ed", "ADJ", [96, 107]], ["konzul\u00e1tu", "konzul\u00e1t", "NOUN", [108, 117]], ["\u010cesk\u00e9", "\u010desk\u00fd", "ADJ", [118, 123]], ["republiky", "republika", "NOUN", [124, 133]], ["v", "v", "ADP", [134, 135]], ["Calgary", "Calgary", "PROPN", [136, 143]], [":", ":", "PUNCT", [143, 144]], ["611", "611", "NUM", [145, 148]], ["-", "-", "PUNCT", [149, 150]], ["71", "71", "NUM", [151, 153]], ["st", "stupe\u0148", "NOUN", [154, 156]], [".", ".", "PUNCT", [156, 157]], ["Avenue", "Avenue", "X", [158, 164]], ["SE", "s", "ADP", [165, 167]], ["Calgary", "Calgary", "PROPN", [168, 175]], [",", ",", "PUNCT", [175, 176]], ["AB", "AB", "NOUN", [177, 179]], ["T", "T", "NOUN", [180, 181]], ["2", "2", "NUM", [181, 182]], ["H", "H", "NOUN", [182, 183]], ["1K", "1K", "NOUN", [183, 185]], ["4", "4", "NUM", [185, 186]], [".", ".", "PUNCT", [186, 187]]]], ["calgarske-listy_2003_unor_ocr.txt", "Tel.: (403) 269-4924 Fax 261-3077 e-mail: j elinek@terramanagement.", [["Tel", "telefon", "NOUN", [0, 3]], [".", ".", "PUNCT", [3, 4]], [":", ":", "PUNCT", [4, 5]], ["(", "(", "PUNCT", [6, 7]], ["403", "403", "NUM", [7, 10]], [")", ")", "PUNCT", [10, 11]], ["269", "269", "NUM", [12, 15]], ["-", "-", "PUNCT", [15, 16]], ["4924", "4924", "NUM", [16, 20]], ["Fax", "fax", "NOUN", [21, 24]], ["261", "261", "NUM", [25, 28]], ["-", "-", "PUNCT", [28, 29]], ["3077", "3077", "NUM", [29, 33]], ["e", "e", "NOUN", [34, 35]], ["-", "-", "PUNCT", [35, 36]], ["mail", "mail", "NOUN", [36, 40]], [":", ":", "PUNCT", [40, 41]], ["j", "j", "NOUN", [42, 43]], ["elinek@terramanagement", "elinek@terramanagement", "NOUN", [44, 66]], [".", ".", "PUNCT", [66, 67]]]], ["calgarske-listy_2003_unor_ocr.txt", "com \u00da\u0159edn\u00ed hodiny konzul\u00e1tu jsou ka\u017edou st\u0159edu od 14.00 \u2014 18.00 hodin.", [["com", "com", "NOUN", [0, 3]], ["\u00da\u0159edn\u00ed", "\u00fa\u0159edn\u00ed", "ADJ", [4, 10]], ["hodiny", "hodina", "NOUN", [11, 17]], ["konzul\u00e1tu", "konzul\u00e1t", "NOUN", [18, 27]], ["jsou", "b\u00fdt", "AUX", [28, 32]], ["ka\u017edou", "ka\u017ed\u00fd", "DET", [33, 39]], ["st\u0159edu", "st\u0159eda", "NOUN", [40, 46]], ["od", "od", "ADP", [47, 49]], ["14.00", "14.00", "NUM", [50, 55]], ["\u2014", "\u2014", "PUNCT", [56, 57]], ["18.00", "18.00", "NUM", [58, 63]], ["hodin", "hodina", "NOUN", [64, 69]], [".", ".", "PUNCT", [69, 70]]]], ["calgarske-listy_2003_unor_ocr.txt", "Sch\u016fzky mus\u00ed b\u00fdt p\u0159edem dohodnuty, aby se p\u0159ede\u0161lo \u010dek\u00e1n\u00ed.", [["Sch\u016fzky", "sch\u016fzka", "NOUN", [0, 7]], ["mus\u00ed", "muset", "VERB", [8, 12]], ["b\u00fdt", "b\u00fdt", "AUX", [13, 16]], ["p\u0159edem", "p\u0159edem", "ADV", [17, 23]], ["dohodnuty", "dohodnut\u00fd", "ADJ", [24, 33]], [",", ",", "PUNCT", [33, 34]], ["aby", "aby", "SCONJ", [-3490, -3490]], ["by", "b\u00fdt", "AUX", [-3490, -3490]], ["se", "se", "PRON", [39, 41]], ["p\u0159ede\u0161lo", "p\u0159edej\u00edt", "VERB", [42, 50]], ["\u010dek\u00e1n\u00ed", "\u010dek\u00e1n\u00ed", "NOUN", [51, 57]], [".", ".", "PUNCT", [57, 58]]]], ["calgarske-listy_2003_unor_ocr.txt", "Podle posledn\u00edho sd\u011blen\u00ed, je mo\u017eno podat \u017e\u00e1dosti o \u010desk\u00e9 pasy u calgarsk\u00e9ho konzul\u00e1tu, kter\u00e9 budou vy\u0159\u00edzeny p\u0159es Montreal s t\u00edm, \u017ee pasy budou \u017eadatel\u016fm vyd\u00e1ny zde v Calgary na honor\u00e1m\u00edm konzul\u00e1tu, co\u017e V\u00e1m u\u0161et\u0159\u00ed cestu do Montre\u00e1lu.", [["Podle", "podle", "ADP", [0, 5]], ["posledn\u00edho", "posledn\u00ed", "ADJ", [6, 16]], ["sd\u011blen\u00ed", "sd\u011blen\u00ed", "NOUN", [17, 24]], [",", ",", "PUNCT", [24, 25]], ["je", "b\u00fdt", "AUX", [26, 28]], ["mo\u017eno", "mo\u017en\u00fd", "ADJ", [29, 34]], ["podat", "podat", "VERB", [35, 40]], ["\u017e\u00e1dosti", "\u017e\u00e1dost", "NOUN", [41, 48]], ["o", "o", "ADP", [49, 50]], ["\u010desk\u00e9", "\u010desk\u00fd", "ADJ", [51, 56]], ["pasy", "pas", "NOUN", [57, 61]], ["u", "u", "ADP", [62, 63]], ["calgarsk\u00e9ho", "calgarsk\u00fd", "ADJ", [64, 75]], ["konzul\u00e1tu", "konzul\u00e1t", "NOUN", [76, 85]], [",", ",", "PUNCT", [85, 86]], ["kter\u00e9", "kter\u00fd", "DET", [87, 92]], ["budou", "b\u00fdt", "AUX", [93, 98]], ["vy\u0159\u00edzeny", "vy\u0159\u00edzen\u00fd", "ADJ", [99, 107]], ["p\u0159es", "p\u0159es", "ADP", [108, 112]], ["Montreal", "Montreal", "PROPN", [113, 121]], ["s", "s", "ADP", [122, 123]], ["t\u00edm", "ten", "DET", [124, 127]], [",", ",", "PUNCT", [127, 128]], ["\u017ee", "\u017ee", "SCONJ", [129, 131]], ["pasy", "pas", "NOUN", [132, 136]], ["budou", "b\u00fdt", "AUX", [137, 142]], ["\u017eadatel\u016fm", "\u017eadatel", "NOUN", [143, 152]], ["vyd\u00e1ny", "vydan\u00fd", "ADJ", [153, 159]], ["zde", "zde", "ADV", [160, 163]], ["v", "v", "ADP", [164, 165]], ["Calgary", "Calgary", "PROPN", [166, 173]], ["na", "na", "ADP", [174, 176]], ["honor\u00e1m\u00edm", "honor\u00e1m\u00ed", "NOUN", [177, 186]], ["konzul\u00e1tu", "konzul\u00e1t", "NOUN", [187, 196]], [",", ",", "PUNCT", [196, 197]], ["co\u017e", "co\u017e", "PRON", [198, 201]], ["V\u00e1m", "vy", "PRON", [202, 205]], ["u\u0161et\u0159\u00ed", "u\u0161et\u0159it", "VERB", [206, 212]], ["cestu", "cesta", "NOUN", [213, 218]], ["do", "do", "ADP", [219, 221]], ["Montre\u00e1lu", "Montre\u00e1l", "PROPN", [222, 231]], [".", ".", "PUNCT", [231, 232]]]], ["calgarske-listy_2003_unor_ocr.txt", "Od 1. dubna 2001 cestuj\u00edc\u00ed do \u010cech s kanadsk\u00fdm pasem pot\u0159ebuj\u00ed platn\u00e9 \u010desk\u00e9 v\u00edzum.", [["Od", "od", "ADP", [0, 2]], ["1", "1", "NUM", [3, 4]], [".", ".", "PUNCT", [4, 5]], ["dubna", "duben", "NOUN", [6, 11]], ["2001", "2001", "NUM", [12, 16]], ["cestuj\u00edc\u00ed", "cestuj\u00edc\u00ed", "ADJ", [17, 26]], ["do", "do", "ADP", [27, 29]], ["\u010cech", "\u010cechy", "PROPN", [30, 34]], ["s", "s", "ADP", [35, 36]], ["kanadsk\u00fdm", "kanadsk\u00fd", "ADJ", [37, 46]], ["pasem", "pas", "NOUN", [47, 52]], ["pot\u0159ebuj\u00ed", "pot\u0159ebovat", "VERB", [53, 62]], ["platn\u00e9", "platn\u00fd", "ADJ", [63, 69]], ["\u010desk\u00e9", "\u010desk\u00fd", "ADJ", [70, 75]], ["v\u00edzum", "v\u00edzum", "NOUN", [76, 81]], [".", ".", "PUNCT", [81, 82]]]], ["calgarske-listy_2003_unor_ocr.txt", "Toto v\u00edzum m\u016f\u017ee b\u00fdt z\u00edsk\u00e1no jen u gener\u00e1ln\u00edho konzul\u00e1tu v Montre\u00e1lu na adrese: Czech gen. consulate, 1305 Quest Ave des Pines Montreal, Que. H3G 1B2.", [["Toto", "tento", "DET", [0, 4]], ["v\u00edzum", "v\u00edzum", "NOUN", [5, 10]], ["m\u016f\u017ee", "moci", "VERB", [11, 15]], ["b\u00fdt", "b\u00fdt", "AUX", [16, 19]], ["z\u00edsk\u00e1no", "z\u00edskan\u00fd", "ADJ", [20, 27]], ["jen", "jen", "PART", [28, 31]], ["u", "u", "ADP", [32, 33]], ["gener\u00e1ln\u00edho", "gener\u00e1ln\u00ed", "ADJ", [34, 45]], ["konzul\u00e1tu", "konzul\u00e1t", "NOUN", [46, 55]], ["v", "v", "ADP", [56, 57]], ["Montre\u00e1lu", "Montre\u00e1l", "PROPN", [58, 67]], ["na", "na", "ADP", [68, 70]], ["adrese", "adresa", "NOUN", [71, 77]], [":", ":", "PUNCT", [77, 78]], ["Czech", "Czech", "X", [79, 84]], ["gen", "gen", "X", [85, 88]], [".", ".", "PUNCT", [88, 89]], ["consulate", "consulate", "X", [90, 99]], [",", ",", "PUNCT", [99, 100]], ["1305", "1305", "NUM", [101, 105]], ["Quest", "Quest", "X", [106, 111]], ["Ave", "Ave", "X", [112, 115]], ["des", "des", "X", [116, 119]], ["Pines", "Pines", "X", [120, 125]], ["Montreal", "Montreal", "X", [126, 134]], [",", ",", "PUNCT", [134, 135]], ["Que", "que", "NOUN", [136, 139]], [".", ".", "PUNCT", [139, 140]], ["H", "H", "NOUN", [141, 142]], ["3", "3", "NUM", [142, 143]], ["G", "G", "NOUN", [143, 144]], ["1", "1", "NUM", [145, 146]], ["B", "B", "NOUN", [146, 147]], ["2", "2", "NUM", [147, 148]], [".", ".", "PUNCT", [148, 149]]]], ["calgarske-listy_2003_unor_ocr.txt", "Pokyny si vy\u017e\u00e1dejte na e-mail adrese : montreal@embassy.mzv.cz \u010di faxem 1(514) 849-4117.", [["Pokyny", "pokyn", "NOUN", [0, 6]], ["si", "se", "PRON", [7, 9]], ["vy\u017e\u00e1dejte", "vy\u017e\u00e1dat", "VERB", [10, 19]], ["na", "na", "ADP", [20, 22]], ["e", "e", "NOUN", [23, 24]], ["-", "-", "PUNCT", [24, 25]], ["mail", "mail", "NOUN", [25, 29]], ["adrese", "adresa", "NOUN", [30, 36]], [":", ":", "PUNCT", [37, 38]], ["montreal@embassy.mzv.cz", "montreal@embassy.mzv.cz", "NOUN", [39, 62]], ["\u010di", "\u010di", "CCONJ", [63, 65]], ["faxem", "fax", "NOUN", [66, 71]], ["1", "1", "NUM", [72, 73]], ["(", "(", "PUNCT", [73, 74]], ["514", "514", "NUM", [74, 77]], [")", ")", "PUNCT", [77, 78]], ["849", "849", "NUM", [79, 82]], ["-", "-", "PUNCT", [82, 83]], ["4117", "4117", "NUM", [83, 87]], [".", ".", "PUNCT", [87, 88]]]], ["calgarske-listy_2003_unor_ocr.txt", "V\u00edza nedostanete na hranic\u00edch \u010di na leti\u0161ti.", [["V\u00edza", "v\u00edzum", "NOUN", [0, 4]], ["nedostanete", "dostat", "VERB", [5, 16]], ["na", "na", "ADP", [17, 19]], ["hranic\u00edch", "hranice", "NOUN", [20, 29]], ["\u010di", "\u010di", "CCONJ", [30, 32]], ["na", "na", "ADP", [33, 35]], ["leti\u0161ti", "leti\u0161t\u011b", "NOUN", [36, 43]], [".", ".", "PUNCT", [43, 44]]]], ["calgarske-listy_2003_unor_ocr.txt", "N\u011bkolik tiskopis\u016f \u017e\u00e1dost\u00ed o v\u00edza a d\u00e1le o \u010deskou penzi pro ty, kdo maj\u00ed v \u010cech\u00e1ch odpracov\u00e1no v\u00edce ne\u017e 14 rok\u016f, je na sklad\u011b zde v Calgary, volejte penzistu Vladim\u00edra Ma\u0161atu na tel. 289 -7244. 2  PO\u010c\u00cdTA\u010cE, PO\u010c\u00cdTA\u010cE, PO\u010c\u00cdTA\u010cE, PO\u010c\u00cdTA\u010cE, PO\u010c\u00cdTA\u010cE, PO\u010c\u00cdTA\u010cE, V\u0161em t\u011bm na\u0161im krajan\u016fm, kte\u0159\u00ed si do v\u00fdbavy sv\u00e9 dom\u00e1cnosti ji\u017e natrvalo po\u0159\u00eddili po\u010d\u00edta\u010d a pou\u017e\u00edvaj\u00ed toto n\u00e1\u0159ad\u00ed s p\u0159ehledem, se jist\u011b bude hodit n\u011bkolik d\u016fle\u017eit\u00fdch adres: AVAVAV.czcanada.", [["N\u011bkolik", "n\u011bkolik", "DET", [0, 7]], ["tiskopis\u016f", "tiskopis", "NOUN", [8, 17]], ["\u017e\u00e1dost\u00ed", "\u017e\u00e1dost", "NOUN", [18, 25]], ["o", "o", "ADP", [26, 27]], ["v\u00edza", "v\u00edzum", "NOUN", [28, 32]], ["a", "a", "CCONJ", [33, 34]], ["d\u00e1le", "d\u00e1le", "ADV", [35, 39]], ["o", "o", "ADP", [40, 41]], ["\u010deskou", "\u010desk\u00fd", "ADJ", [42, 48]], ["penzi", "penze", "NOUN", [49, 54]], ["pro", "pro", "ADP", [55, 58]], ["ty", "ten", "DET", [59, 61]], [",", ",", "PUNCT", [61, 62]], ["kdo", "kdo", "PRON", [63, 66]], ["maj\u00ed", "m\u00edt", "VERB", [67, 71]], ["v", "v", "ADP", [72, 73]], ["\u010cech\u00e1ch", "\u010cechy", "PROPN", [74, 81]], ["odpracov\u00e1no", "odpracovan\u00fd", "ADJ", [82, 93]], ["v\u00edce", "v\u00edce", "ADV", [94, 98]], ["ne\u017e", "ne\u017e", "SCONJ", [99, 102]], ["14", "14", "NUM", [103, 105]], ["rok\u016f", "rok", "NOUN", [106, 110]], [",", ",", "PUNCT", [110, 111]], ["je", "b\u00fdt", "AUX", [112, 114]], ["na", "na", "ADP", [115, 117]], ["sklad\u011b", "sklad", "NOUN", [118, 124]], ["zde", "zde", "ADV", [125, 128]], ["v", "v", "ADP", [129, 130]], ["Calgary", "Calgary", "PROPN", [131, 138]], [",", ",", "PUNCT", [138, 139]], ["volejte", "volat", "VERB", [140, 147]], ["penzistu", "penzista", "NOUN", [148, 156]], ["Vladim\u00edra", "Vladim\u00edr", "PROPN", [157, 166]], ["Ma\u0161atu", "Ma\u0161at", "PROPN", [167, 173]], ["na", "na", "ADP", [174, 176]], ["tel", "telefon", "NOUN", [177, 180]], [".", ".", "PUNCT", [180, 181]], ["289", "289", "NUM", [182, 185]], ["-", "-", "PUNCT", [186, 187]], ["7244", "7244", "NUM", [187, 191]], [".", ".", "PUNCT", [191, 192]], ["2", "2", "NUM", [193, 194]], ["PO\u010c\u00cdTA\u010cE", "po\u010d\u00edta\u010de", "NOUN", [196, 204]], [",", ",", "PUNCT", [204, 205]], ["PO\u010c\u00cdTA\u010cE", "po\u010d\u00edta\u010de", "NOUN", [206, 214]], [",", ",", "PUNCT", [214, 215]], ["PO\u010c\u00cdTA\u010cE", "po\u010d\u00edta\u010de", "NOUN", [216, 224]], [",", ",", "PUNCT", [224, 225]], ["PO\u010c\u00cdTA\u010cE", "po\u010d\u00edta\u010de", "NOUN", [226, 234]], [",", ",", "PUNCT", [234, 235]], ["PO\u010c\u00cdTA\u010cE", "po\u010d\u00edta\u010de", "NOUN", [236, 244]], [",", ",", "PUNCT", [244, 245]], ["PO\u010c\u00cdTA\u010cE", "po\u010d\u00edta\u010de", "NOUN", [246, 254]], [",", ",", "PUNCT", [254, 255]], ["V\u0161em", "v\u0161echen", "DET", [256, 260]], ["t\u011bm", "ten", "DET", [261, 264]], ["na\u0161im", "n\u00e1\u0161", "DET", [265, 270]], ["krajan\u016fm", "krajan", "NOUN", [271, 279]], [",", ",", "PUNCT", [279, 280]], ["kte\u0159\u00ed", "kter\u00fd", "DET", [281, 286]], ["si", "se", "PRON", [287, 289]], ["do", "do", "ADP", [290, 292]], ["v\u00fdbavy", "v\u00fdbava", "NOUN", [293, 299]], ["sv\u00e9", "sv\u016fj", "DET", [300, 303]], ["dom\u00e1cnosti", "dom\u00e1cnost", "NOUN", [304, 314]], ["ji\u017e", "ji\u017e", "ADV", [315, 318]], ["natrvalo", "natrvalo", "ADV", [319, 327]], ["po\u0159\u00eddili", "po\u0159\u00eddit", "VERB", [328, 336]], ["po\u010d\u00edta\u010d", "po\u010d\u00edta\u010d", "NOUN", [337, 344]], ["a", "a", "CCONJ", [345, 346]], ["pou\u017e\u00edvaj\u00ed", "pou\u017e\u00edvat", "VERB", [347, 356]], ["toto", "tento", "DET", [357, 361]], ["n\u00e1\u0159ad\u00ed", "n\u00e1\u0159ad\u00ed", "NOUN", [362, 368]], ["s", "s", "ADP", [369, 370]], ["p\u0159ehledem", "p\u0159ehled", "NOUN", [371, 380]], [",", ",", "PUNCT", [380, 381]], ["se", "se", "PRON", [382, 384]], ["jist\u011b", "jist\u011b", "ADV", [385, 390]], ["bude", "b\u00fdt", "AUX", [391, 395]], ["hodit", "hodit", "VERB", [396, 401]], ["n\u011bkolik", "n\u011bkolik", "DET", [402, 409]], ["d\u016fle\u017eit\u00fdch", "d\u016fle\u017eit\u00fd", "ADJ", [410, 420]], ["adres", "adresa", "NOUN", [421, 426]], [":", ":", "PUNCT", [426, 427]], ["AVAVAV", "avavav", "NOUN", [428, 434]], [".", ".", "PUNCT", [434, 435]], ["czcanada", "czcanada", "NOUN", [435, 443]], [".", ".", "PUNCT", [443, 444]]]], ["calgarske-listy_2003_unor_ocr.txt", "com ivww.boldpages.", [["com", "com", "NOUN", [0, 3]], ["ivww", "ivww", "NOUN", [4, 8]], [".", ".", "PUNCT", [8, 9]], ["boldpages", "boldpages", "X", [9, 18]], [".", ".", "PUNCT", [18, 19]]]], ["calgarske-listy_2003_unor_ocr.txt", "com AVAvw.Google.", [["com", "com", "NOUN", [0, 3]], ["AVAvw", "AVAvw", "NOUN", [4, 9]], [".", ".", "PUNCT", [9, 10]], ["Google", "Google", "PROPN", [10, 16]], [".", ".", "PUNCT", [16, 17]]]], ["calgarske-listy_2003_unor_ocr.txt", "com AVAVw.seznam.cz AVAVAV.lidovky.", [["com", "com", "NOUN", [0, 3]], ["AVAVw", "avavw", "NOUN", [4, 9]], [".", ".", "PUNCT", [9, 10]], ["seznam", "seznam", "NOUN", [10, 16]], [".", ".", "PUNCT", [16, 17]], ["cz", "cz", "NOUN", [17, 19]], ["AVAVAV", "avavav", "NOUN", [20, 26]], [".", ".", "PUNCT", [26, 27]], ["lidovky", "lidovka", "NOUN", [27, 34]], [".", ".", "PUNCT", [34, 35]]]], ["calgarske-listy_2003_unor_ocr.txt", "cz AVAVw.eCesty.", [["cz", "cz", "NOUN", [0, 2]], ["AVAVw", "avavw", "NOUN", [3, 8]], [".", ".", "PUNCT", [8, 9]], ["eCesty", "eCest", "NOUN", [9, 15]], [".", ".", "PUNCT", [15, 16]]]], ["calgarske-listy_2003_unor_ocr.txt", "cz AVAVW.C\u00cdC.gC.", [["cz", "cz", "NOUN", [0, 2]], ["AVAVW", "AVAVW", "NOUN", [3, 8]], [".", ".", "PUNCT", [8, 9]], ["C\u00cdC", "c\u00edc", "NOUN", [9, 12]], [".", ".", "PUNCT", [12, 13]], ["g", "g", "NOUN", [13, 14]], ["C", "C", "NOUN", [14, 15]], [".", ".", "PUNCT", [15, 16]]]], ["calgarske-listy_2003_unor_ocr.txt", "Ca Internetov\u00e1 str\u00e1nka p\u0159in\u00e1\u0161ej\u00ed informace o calgarsk\u00e9 pobo\u010dce \u010desk\u00e9ho a slovensk\u00e9ho sdru\u017een\u00ed.", [["Ca", "Ca", "NOUN", [0, 2]], ["Internetov\u00e1", "internetov\u00fd", "ADJ", [3, 14]], ["str\u00e1nka", "str\u00e1nka", "NOUN", [15, 22]], ["p\u0159in\u00e1\u0161ej\u00ed", "p\u0159in\u00e1\u0161et", "VERB", [23, 32]], ["informace", "informace", "NOUN", [33, 42]], ["o", "o", "ADP", [43, 44]], ["calgarsk\u00e9", "calgarsk\u00fd", "ADJ", [45, 54]], ["pobo\u010dce", "pobo\u010dka", "NOUN", [55, 62]], ["\u010desk\u00e9ho", "\u010desk\u00fd", "ADJ", [63, 70]], ["a", "a", "CCONJ", [71, 72]], ["slovensk\u00e9ho", "slovensk\u00fd", "ADJ", [73, 84]], ["sdru\u017een\u00ed", "sdru\u017een\u00ed", "NOUN", [85, 93]], [".", ".", "PUNCT", [93, 94]]]], ["calgarske-listy_2003_unor_ocr.txt", "Rychl\u00e9 vyhled\u00e1v\u00e1n\u00ed chytr\u00fdch informac\u00ed na Internetu v \u010desk\u00e9 verzi.", [["Rychl\u00e9", "rychl\u00fd", "ADJ", [0, 6]], ["vyhled\u00e1v\u00e1n\u00ed", "vyhled\u00e1v\u00e1n\u00ed", "NOUN", [7, 18]], ["chytr\u00fdch", "chytr\u00fd", "ADJ", [19, 27]], ["informac\u00ed", "informace", "NOUN", [28, 37]], ["na", "na", "ADP", [38, 40]], ["Internetu", "internet", "PROPN", [41, 50]], ["v", "v", "ADP", [51, 52]], ["\u010desk\u00e9", "\u010desk\u00fd", "ADJ", [53, 58]], ["verzi", "verze", "NOUN", [59, 64]], [".", ".", "PUNCT", [64, 65]]]], ["calgarske-listy_2003_unor_ocr.txt", "Vyhled\u00e1va\u010d informac\u00ed na Internetu.", [["Vyhled\u00e1va\u010d", "vyhled\u00e1va\u010d", "NOUN", [0, 10]], ["informac\u00ed", "informace", "NOUN", [11, 20]], ["na", "na", "ADP", [21, 23]], ["Internetu", "internet", "PROPN", [24, 33]], [".", ".", "PUNCT", [33, 34]]]], ["calgarske-listy_2003_unor_ocr.txt", "\u010cesk\u00fd vyhled\u00e1va\u010d.", [["\u010cesk\u00fd", "\u010desk\u00fd", "ADJ", [0, 5]], ["vyhled\u00e1va\u010d", "vyhled\u00e1va\u010d", "NOUN", [6, 16]], [".", ".", "PUNCT", [16, 17]]]], ["calgarske-listy_2003_unor_ocr.txt", "\u010cesk\u00fd den\u00edk.", [["\u010cesk\u00fd", "\u010desk\u00fd", "ADJ", [0, 5]], ["den\u00edk", "den\u00edk", "NOUN", [6, 11]], [".", ".", "PUNCT", [11, 12]]]], ["calgarske-listy_2003_unor_ocr.txt", "Cestopisy \u010desky Ministerstvo Imigr.", [["Cestopisy", "cestopis", "NOUN", [0, 9]], ["\u010desky", "\u010desky", "ADV", [10, 15]], ["Ministerstvo", "ministerstvo", "NOUN", [16, 28]], ["Imigr", "Imigr", "PROPN", [29, 34]], [".", ".", "PUNCT", [34, 35]]]], ["calgarske-listy_2003_unor_ocr.txt", "WAvw.bountifulbazaar.", [["WAvw", "WAvw", "NOUN", [0, 4]], [".", ".", "PUNCT", [4, 5]], ["bountifulbazaar", "bountifulbazaar", "NOUN", [5, 20]], [".", ".", "PUNCT", [20, 21]]]], ["calgarske-listy_2003_unor_ocr.txt", "com katalogov\u00fd prodej AVAVAV.czech-books.com \u010cesk\u00e9 knihy a muzika www, czech-slovak-assoc. ca Associace v Kanad\u011b wAVAv.canada.sk/calgary.", [["com", "com", "NOUN", [0, 3]], ["katalogov\u00fd", "katalogov\u00fd", "ADJ", [4, 14]], ["prodej", "prodej", "NOUN", [15, 21]], ["AVAVAV", "avavav", "NOUN", [22, 28]], [".", ".", "PUNCT", [28, 29]], ["czech", "czech", "X", [29, 34]], ["-", "-", "PUNCT", [34, 35]], ["books", "books", "X", [35, 40]], [".", ".", "PUNCT", [40, 41]], ["com", "com", "X", [41, 44]], ["\u010cesk\u00e9", "\u010desk\u00fd", "ADJ", [45, 50]], ["knihy", "kniha", "NOUN", [51, 56]], ["a", "a", "CCONJ", [57, 58]], ["muzika", "muzika", "NOUN", [59, 65]], ["www", "www", "NOUN", [66, 69]], [",", ",", "PUNCT", [69, 70]], ["czech", "czech", "X", [71, 76]], ["-", "-", "PUNCT", [76, 77]], ["slovak", "slovak", "X", [77, 83]], ["-", "-", "PUNCT", [83, 84]], ["assoc", "assoc", "NOUN", [84, 89]], [".", ".", "PUNCT", [89, 90]], ["ca", "ca", "X", [91, 93]], ["Associace", "Associace", "PROPN", [94, 103]], ["v", "v", "ADP", [104, 105]], ["Kanad\u011b", "Kanada", "PROPN", [106, 112]], ["wAVAv", "wavav", "NOUN", [113, 118]], [".", ".", "PUNCT", [118, 119]], ["canada", "canada", "NOUN", [119, 125]], [".", ".", "PUNCT", [125, 126]], ["sk", "skupek", "NOUN", [126, 128]], ["/", "/", "PUNCT", [128, 129]], ["calgary", "calgary", "PROPN", [129, 136]], [".", ".", "PUNCT", [136, 137]]]], ["calgarske-listy_2003_unor_ocr.txt", "htm slovensk\u00fd klub", [["htm", "htm", "NOUN", [0, 3]], ["slovensk\u00fd", "slovensk\u00fd", "ADJ", [4, 13]], ["klub", "klub", "NOUN", [14, 18]]]], ["calgarske-listy_2003_unor_ocr.txt", "Mo\u017enosti studia \u010desk\u00fdch z\u00e1kladn\u00edch a st\u0159edn\u00edch \u0161kol p\u0159es interner.", [["Mo\u017enosti", "mo\u017enost", "NOUN", [0, 8]], ["studia", "studium", "NOUN", [9, 15]], ["\u010desk\u00fdch", "\u010desk\u00fd", "ADJ", [16, 23]], ["z\u00e1kladn\u00edch", "z\u00e1kladn\u00ed", "ADJ", [24, 34]], ["a", "a", "CCONJ", [35, 36]], ["st\u0159edn\u00edch", "st\u0159edn\u00ed", "ADJ", [37, 46]], ["\u0161kol", "\u0161kola", "NOUN", [47, 51]], ["p\u0159es", "p\u0159es", "ADP", [52, 56]], ["interner", "interner", "NOUN", [57, 65]], [".", ".", "PUNCT", [65, 66]]]], ["calgarske-listy_2003_unor_ocr.txt", "V\u00e1\u017een\u00e1 pan\u00ed, v\u00e1\u017een\u00fd pane, Va\u0161e d\u011bti \u0161kolou povinn\u00e9 maj\u00ed nyn\u00ed mo\u017enost p\u0159ipravovat se systematicky do \u010desk\u00e9 \u0161koly i p\u0159i Va\u0161em zahrani\u010dn\u00edm pobytu.", [["V\u00e1\u017een\u00e1", "v\u00e1\u017een\u00fd", "ADJ", [0, 6]], ["pan\u00ed", "pan\u00ed", "NOUN", [7, 11]], [",", ",", "PUNCT", [11, 12]], ["v\u00e1\u017een\u00fd", "v\u00e1\u017een\u00fd", "ADJ", [13, 19]], ["pane", "pan", "INTJ", [20, 24]], [",", ",", "PUNCT", [24, 25]], ["Va\u0161e", "v\u00e1\u0161", "DET", [26, 30]], ["d\u011bti", "d\u00edt\u011b", "NOUN", [31, 35]], ["\u0161kolou", "\u0161kola", "NOUN", [36, 42]], ["povinn\u00e9", "povinn\u00fd", "ADJ", [43, 50]], ["maj\u00ed", "m\u00edt", "VERB", [51, 55]], ["nyn\u00ed", "nyn\u00ed", "ADV", [56, 60]], ["mo\u017enost", "mo\u017enost", "NOUN", [61, 68]], ["p\u0159ipravovat", "p\u0159ipravovat", "VERB", [69, 80]], ["se", "se", "PRON", [81, 83]], ["systematicky", "systematicky", "ADV", [84, 96]], ["do", "do", "ADP", [97, 99]], ["\u010desk\u00e9", "\u010desk\u00fd", "ADJ", [100, 105]], ["\u0161koly", "\u0161kola", "NOUN", [106, 111]], ["i", "i", "CCONJ", [112, 113]], ["p\u0159i", "p\u0159i", "ADP", [114, 117]], ["Va\u0161em", "v\u00e1\u0161", "DET", [118, 123]], ["zahrani\u010dn\u00edm", "zahrani\u010dn\u00ed", "ADJ", [124, 135]], ["pobytu", "pobyt", "NOUN", [136, 142]], [".", ".", "PUNCT", [142, 143]]]], ["calgarske-listy_2003_unor_ocr.txt", "Mohou toti\u017e kdykoliv vyu\u017e\u00edt internetov\u00e9ho dom\u00e1c\u00edho u\u010ditele - slu\u017eby \u0160kola za \u0161kolou.", [["Mohou", "moci", "VERB", [0, 5]], ["toti\u017e", "toti\u017e", "CCONJ", [6, 11]], ["kdykoliv", "kdykoliv", "ADV", [12, 20]], ["vyu\u017e\u00edt", "vyu\u017e\u00edt", "VERB", [21, 27]], ["internetov\u00e9ho", "internetov\u00fd", "ADJ", [28, 41]], ["dom\u00e1c\u00edho", "dom\u00e1c\u00ed", "ADJ", [42, 50]], ["u\u010ditele", "u\u010ditel", "NOUN", [51, 58]], ["-", "-", "PUNCT", [59, 60]], ["slu\u017eby", "slu\u017eba", "NOUN", [61, 67]], ["\u0160kola", "\u0161kola", "NOUN", [68, 73]], ["za", "za", "ADP", [74, 76]], ["\u0161kolou", "\u0161kola", "NOUN", [77, 83]], [".", ".", "PUNCT", [83, 84]]]], ["calgarske-listy_2003_unor_ocr.txt", "Slu\u017eba obsahuje u\u010debnice z dev\u00edti z\u00e1kladn\u00edch p\u0159edm\u011bt\u016f, kter\u00e9 se b\u011b\u017en\u011b u\u017e\u00edvaj\u00ed v 6.-9. t\u0159\u00edd\u011b z\u00e1kladn\u00edch \u0161kol a prim\u011b a\u017e kvart\u011b v\u00edcelet\u00fdch gymn\u00e1zi\u00ed.", [["Slu\u017eba", "slu\u017eba", "NOUN", [0, 6]], ["obsahuje", "obsahovat", "VERB", [7, 15]], ["u\u010debnice", "u\u010debnice", "NOUN", [16, 24]], ["z", "z", "ADP", [25, 26]], ["dev\u00edti", "dev\u011bt", "NUM", [27, 33]], ["z\u00e1kladn\u00edch", "z\u00e1kladn\u00ed", "ADJ", [34, 44]], ["p\u0159edm\u011bt\u016f", "p\u0159edm\u011bt", "NOUN", [45, 53]], [",", ",", "PUNCT", [53, 54]], ["kter\u00e9", "kter\u00fd", "DET", [55, 60]], ["se", "se", "PRON", [61, 63]], ["b\u011b\u017en\u011b", "b\u011b\u017en\u011b", "ADV", [64, 69]], ["u\u017e\u00edvaj\u00ed", "u\u017e\u00edvat", "VERB", [70, 77]], ["v", "v", "ADP", [78, 79]], ["6", "6", "NUM", [80, 81]], [".", ".", "PUNCT", [81, 82]], ["-", "-", "PUNCT", [82, 83]], ["9", "9", "NUM", [83, 84]], [".", ".", "PUNCT", [84, 85]], ["t\u0159\u00edd\u011b", "t\u0159\u00edda", "NOUN", [86, 91]], ["z\u00e1kladn\u00edch", "z\u00e1kladn\u00ed", "ADJ", [92, 102]], ["\u0161kol", "\u0161kola", "NOUN", [103, 107]], ["a", "a", "CCONJ", [108, 109]], ["prim\u011b", "prime", "NOUN", [110, 115]], ["a\u017e", "a\u017e", "PART", [116, 118]], ["kvart\u011b", "kvarta", "NOUN", [119, 125]], ["v\u00edcelet\u00fdch", "v\u00edcelet\u00fd", "ADJ", [126, 136]], ["gymn\u00e1zi\u00ed", "gymn\u00e1zium", "NOUN", [137, 145]], [".", ".", "PUNCT", [145, 146]]]], ["calgarske-listy_2003_unor_ocr.txt", "\u0160kolu za \u0161kolou u\u017e nyn\u00ed vyu\u017e\u00edvaj\u00ed nap\u0159\u00edklad d\u011bti \u010desk\u00fdch diplomat\u016f v \u010c\u00edn\u011b.", [["\u0160kolu", "\u0161kola", "NOUN", [0, 5]], ["za", "za", "ADP", [6, 8]], ["\u0161kolou", "\u0161kola", "NOUN", [9, 15]], ["u\u017e", "u\u017e", "ADV", [16, 18]], ["nyn\u00ed", "nyn\u00ed", "ADV", [19, 23]], ["vyu\u017e\u00edvaj\u00ed", "vyu\u017e\u00edvat", "VERB", [24, 33]], ["nap\u0159\u00edklad", "nap\u0159\u00edklad", "PART", [34, 43]], ["d\u011bti", "d\u00edt\u011b", "NOUN", [44, 48]], ["\u010desk\u00fdch", "\u010desk\u00fd", "ADJ", [49, 56]], ["diplomat\u016f", "diplomat", "NOUN", [57, 66]], ["v", "v", "ADP", [67, 68]], ["\u010c\u00edn\u011b", "\u010c\u00edna", "PROPN", [69, 73]], [".", ".", "PUNCT", [73, 74]]]], ["calgarske-listy_2003_unor_ocr.txt", "\u017d\u00e1ci a studenti maj\u00ed prost\u0159ednictv\u00edm internetu mo\u017enost kdykoliv a kdekoliv na sv\u011bt\u011b: 1. u\u010dit se p\u0159esn\u011b podle obsahu \u010desk\u00fdch u\u010debnic, ze kter\u00e9ho budou ve \u0161kole p\u0159ezkou\u0161eny po va\u0161em n\u00e1vratu, 2. z\u00edsk\u00e1vat v\u011bdomosti pomoc\u00ed \u0159e\u0161en\u00fdch p\u0159\u00edklad\u016f, v\u00fdkladu, aktivn\u00edch obr\u00e1zk\u016f \u010di pokus\u016f, 3. procvi\u010dit si mj. p\u0159\u00edklady z matematiky, \u010deskou gramatiku, v\u011btn\u00e9 rozbory, napsat si dikt\u00e1t, u\u010dit se zem\u011bpisu pomoc\u00ed slep\u00fdch map, 4. otestovat si nau\u010den\u00e9 znalosti - formou procvi\u010d\u011bn\u00ed a r\u016fzn\u00fdch test\u00edk\u016f.", [["\u017d\u00e1ci", "\u017e\u00e1k", "NOUN", [0, 4]], ["a", "a", "CCONJ", [5, 6]], ["studenti", "student", "NOUN", [7, 15]], ["maj\u00ed", "m\u00edt", "VERB", [16, 20]], ["prost\u0159ednictv\u00edm", "prost\u0159ednictv\u00ed", "NOUN", [21, 36]], ["internetu", "internet", "NOUN", [37, 46]], ["mo\u017enost", "mo\u017enost", "NOUN", [47, 54]], ["kdykoliv", "kdykoliv", "ADV", [55, 63]], ["a", "a", "CCONJ", [64, 65]], ["kdekoliv", "kdekoliv", "ADV", [66, 74]], ["na", "na", "ADP", [75, 77]], ["sv\u011bt\u011b", "sv\u011bt", "NOUN", [78, 83]], [":", ":", "PUNCT", [83, 84]], ["1", "1", "NUM", [85, 86]], [".", ".", "PUNCT", [86, 87]], ["u\u010dit", "u\u010dit", "VERB", [88, 92]], ["se", "se", "PRON", [93, 95]], ["p\u0159esn\u011b", "p\u0159esn\u011b", "ADV", [96, 102]], ["podle", "podle", "ADP", [103, 108]], ["obsahu", "obsah", "NOUN", [109, 115]], ["\u010desk\u00fdch", "\u010desk\u00fd", "ADJ", [116, 123]], ["u\u010debnic", "u\u010debnice", "NOUN", [124, 131]], [",", ",", "PUNCT", [131, 132]], ["ze", "z", "ADP", [133, 135]], ["kter\u00e9ho", "kter\u00fd", "DET", [136, 143]], ["budou", "b\u00fdt", "AUX", [144, 149]], ["ve", "v", "ADP", [150, 152]], ["\u0161kole", "\u0161kola", "NOUN", [153, 158]], ["p\u0159ezkou\u0161eny", "p\u0159ezkou\u0161en\u00fd", "ADJ", [159, 170]], ["po", "po", "ADP", [171, 173]], ["va\u0161em", "v\u00e1\u0161", "DET", [174, 179]], ["n\u00e1vratu", "n\u00e1vrat", "NOUN", [180, 187]], [",", ",", "PUNCT", [187, 188]], ["2", "2", "NUM", [189, 190]], [".", ".", "PUNCT", [190, 191]], ["z\u00edsk\u00e1vat", "z\u00edsk\u00e1vat", "VERB", [192, 200]], ["v\u011bdomosti", "v\u011bdomost", "NOUN", [201, 210]], ["pomoc\u00ed", "pomoc\u00ed", "ADP", [211, 217]], ["\u0159e\u0161en\u00fdch", "\u0159e\u0161en\u00fd", "ADJ", [218, 226]], ["p\u0159\u00edklad\u016f", "p\u0159\u00edklad", "NOUN", [227, 235]], [",", ",", "PUNCT", [235, 236]], ["v\u00fdkladu", "v\u00fdklad", "NOUN", [237, 244]], [",", ",", "PUNCT", [244, 245]], ["aktivn\u00edch", "aktivn\u00ed", "ADJ", [246, 255]], ["obr\u00e1zk\u016f", "obr\u00e1zek", "NOUN", [256, 263]], ["\u010di", "\u010di", "CCONJ", [264, 266]], ["pokus\u016f", "pokus", "NOUN", [267, 273]], [",", ",", "PUNCT", [273, 274]], ["3", "3", "NUM", [275, 276]], [".", ".", "PUNCT", [276, 277]], ["procvi\u010dit", "procvi\u010dit", "VERB", [278, 287]], ["si", "se", "PRON", [288, 290]], ["mj", "mj", "ADV", [291, 293]], [".", ".", "PUNCT", [293, 294]], ["p\u0159\u00edklady", "p\u0159\u00edklad", "NOUN", [295, 303]], ["z", "z", "ADP", [304, 305]], ["matematiky", "matematika", "NOUN", [306, 316]], [",", ",", "PUNCT", [316, 317]], ["\u010deskou", "\u010desk\u00fd", "ADJ", [318, 324]], ["gramatiku", "gramatika", "NOUN", [325, 334]], [",", ",", "PUNCT", [334, 335]], ["v\u011btn\u00e9", "v\u011btn\u00fd", "ADJ", [336, 341]], ["rozbory", "rozbor", "NOUN", [342, 349]], [",", ",", "PUNCT", [349, 350]], ["napsat", "napsat", "VERB", [351, 357]], ["si", "se", "PRON", [358, 360]], ["dikt\u00e1t", "dikt\u00e1t", "NOUN", [361, 367]], [",", ",", "PUNCT", [367, 368]], ["u\u010dit", "u\u010dit", "VERB", [369, 373]], ["se", "se", "PRON", [374, 376]], ["zem\u011bpisu", "zem\u011bpis", "NOUN", [377, 385]], ["pomoc\u00ed", "pomoc\u00ed", "ADP", [386, 392]], ["slep\u00fdch", "slep\u00fd", "ADJ", [393, 400]], ["map", "mapa", "NOUN", [401, 404]], [",", ",", "PUNCT", [404, 405]], ["4", "4", "NUM", [406, 407]], [".", ".", "PUNCT", [407, 408]], ["otestovat", "otestovat", "VERB", [409, 418]], ["si", "se", "PRON", [419, 421]], ["nau\u010den\u00e9", "nau\u010den\u00fd", "ADJ", [422, 429]], ["znalosti", "znalost", "NOUN", [430, 438]], ["-", "-", "PUNCT", [439, 440]], ["formou", "forma", "NOUN", [441, 447]], ["procvi\u010d\u011bn\u00ed", "procvi\u010d\u011bn\u00ed", "NOUN", [448, 458]], ["a", "a", "CCONJ", [459, 460]], ["r\u016fzn\u00fdch", "r\u016fzn\u00fd", "ADJ", [461, 468]], ["test\u00edk\u016f", "test\u00edk", "NOUN", [469, 476]], [".", ".", "PUNCT", [476, 477]]]], ["calgarske-listy_2003_unor_ocr.txt", "Pr\u00e1ce s moduly je poutav\u00e1 a z\u00e1bavn\u00e1 d\u00edky pou\u017eit\u00e9 grafice a dal\u0161\u00edm mo\u017enostem komunikace na internetu.", [["Pr\u00e1ce", "pr\u00e1ce", "NOUN", [0, 5]], ["s", "s", "ADP", [6, 7]], ["moduly", "modul", "NOUN", [8, 14]], ["je", "b\u00fdt", "AUX", [15, 17]], ["poutav\u00e1", "poutav\u00fd", "ADJ", [18, 25]], ["a", "a", "CCONJ", [26, 27]], ["z\u00e1bavn\u00e1", "z\u00e1bavn\u00fd", "ADJ", [28, 35]], ["d\u00edky", "d\u00edky", "ADP", [36, 40]], ["pou\u017eit\u00e9", "pou\u017eit\u00fd", "ADJ", [41, 48]], ["grafice", "grafika", "NOUN", [49, 56]], ["a", "a", "CCONJ", [57, 58]], ["dal\u0161\u00edm", "dal\u0161\u00ed", "ADJ", [59, 65]], ["mo\u017enostem", "mo\u017enost", "NOUN", [66, 75]], ["komunikace", "komunikace", "NOUN", [76, 86]], ["na", "na", "ADP", [87, 89]], ["internetu", "internet", "NOUN", [90, 99]], [".", ".", "PUNCT", [99, 100]]]], ["calgarske-listy_2003_unor_ocr.txt", "Pot\u0159ebuje-li d\u00edt\u011b poradit, zept\u00e1 se v diskusi d\u011bt\u00ed, kter\u00e9 se pr\u00e1v\u011b v\u011bnuj\u00ed stejn\u00e9 l\u00e1tce.", [["Pot\u0159ebuje", "pot\u0159ebovat", "VERB", [0, 9]], ["-", "-", "PUNCT", [9, 10]], ["li", "li", "SCONJ", [10, 12]], ["d\u00edt\u011b", "d\u00edt\u011b", "NOUN", [13, 17]], ["poradit", "poradit", "VERB", [18, 25]], [",", ",", "PUNCT", [25, 26]], ["zept\u00e1", "zeptat", "VERB", [27, 32]], ["se", "se", "PRON", [33, 35]], ["v", "v", "ADP", [36, 37]], ["diskusi", "diskuse", "NOUN", [38, 45]], ["d\u011bt\u00ed", "d\u00edt\u011b", "NOUN", [46, 50]], [",", ",", "PUNCT", [50, 51]], ["kter\u00e9", "kter\u00fd", "DET", [52, 57]], ["se", "se", "PRON", [58, 60]], ["pr\u00e1v\u011b", "pr\u00e1v\u011b", "ADV", [61, 66]], ["v\u011bnuj\u00ed", "v\u011bnovat", "VERB", [67, 73]], ["stejn\u00e9", "stejn\u00fd", "ADJ", [74, 80]], ["l\u00e1tce", "l\u00e1tka", "NOUN", [81, 86]], [".", ".", "PUNCT", [86, 87]]]], ["calgarske-listy_2003_unor_ocr.txt", "Pomoci a vysv\u011btlit komplikovanou l\u00e1tku m\u016f\u017ee i m\u00faza Elvira, nebo \u017eiv\u00fd lektor v off-line \u010di on-line re\u017eimu.", [["Pomoci", "pomoci", "VERB", [0, 6]], ["a", "a", "CCONJ", [7, 8]], ["vysv\u011btlit", "vysv\u011btlit", "VERB", [9, 18]], ["komplikovanou", "komplikovan\u00fd", "ADJ", [19, 32]], ["l\u00e1tku", "l\u00e1tka", "NOUN", [33, 38]], ["m\u016f\u017ee", "moci", "VERB", [39, 43]], ["i", "i", "CCONJ", [44, 45]], ["m\u00faza", "m\u00faza", "NOUN", [46, 50]], ["Elvira", "Elvir", "PROPN", [51, 57]], [",", ",", "PUNCT", [57, 58]], ["nebo", "nebo", "CCONJ", [59, 63]], ["\u017eiv\u00fd", "\u017eiv\u00fd", "ADJ", [64, 68]], ["lektor", "lektor", "NOUN", [69, 75]], ["v", "v", "ADP", [76, 77]], ["off", "off", "X", [78, 81]], ["-", "-", "PUNCT", [81, 82]], ["line", "line", "X", [82, 86]], ["\u010di", "\u010di", "CCONJ", [87, 89]], ["on", "on", "X", [90, 92]], ["-", "-", "PUNCT", [92, 93]], ["line", "line", "X", [93, 97]], ["re\u017eimu", "re\u017eim", "NOUN", [98, 104]], [".", ".", "PUNCT", [104, 105]]]], ["calgarske-listy_2003_unor_ocr.txt", "Vy se m\u016f\u017eete p\u0159esv\u011bd\u010dit o \u00fasp\u011b\u0161nosti jeho p\u0159\u00edpravy pravidelnou kontrolou rubriky Moje v\u00fdsledky a od \u00fanora prost\u0159ednictv\u00edm Rodi\u010dovsk\u00e9ho modulu.", [["Vy", "vy", "PRON", [0, 2]], ["se", "se", "PRON", [3, 5]], ["m\u016f\u017eete", "moci", "VERB", [6, 12]], ["p\u0159esv\u011bd\u010dit", "p\u0159esv\u011bd\u010dit", "VERB", [13, 23]], ["o", "o", "ADP", [24, 25]], ["\u00fasp\u011b\u0161nosti", "\u00fasp\u011b\u0161nost", "NOUN", [26, 36]], ["jeho", "jeho", "DET", [37, 41]], ["p\u0159\u00edpravy", "p\u0159\u00edprava", "NOUN", [42, 50]], ["pravidelnou", "pravideln\u00fd", "ADJ", [51, 62]], ["kontrolou", "kontrola", "NOUN", [63, 72]], ["rubriky", "rubrika", "NOUN", [73, 80]], ["Moje", "m\u016fj", "DET", [81, 85]], ["v\u00fdsledky", "v\u00fdsledek", "NOUN", [86, 94]], ["a", "a", "CCONJ", [95, 96]], ["od", "od", "ADP", [97, 99]], ["\u00fanora", "\u00fanor", "NOUN", [100, 105]], ["prost\u0159ednictv\u00edm", "prost\u0159ednictv\u00ed", "NOUN", [106, 121]], ["Rodi\u010dovsk\u00e9ho", "rodi\u010dovsk\u00fd", "ADJ", [122, 134]], ["modulu", "modul", "NOUN", [135, 141]], [".", ".", "PUNCT", [141, 142]]]], ["calgarske-listy_2003_unor_ocr.txt", "U\u017eivatel \u0160koly za \u0161kolou pot\u0159ebuje b\u011b\u017en\u00fd po\u010d\u00edta\u010d p\u0159ipojen\u00fd na internet, vybaven\u00fd prost\u0159ed\u00edm MS Office a prohl\u00ed\u017ee\u010dem Internet Explorer verze 5.0 a vy\u0161\u0161\u00ed.", [["U\u017eivatel", "u\u017eivatel", "NOUN", [0, 8]], ["\u0160koly", "\u0161kola", "NOUN", [9, 14]], ["za", "za", "ADP", [15, 17]], ["\u0161kolou", "\u0161kola", "NOUN", [18, 24]], ["pot\u0159ebuje", "pot\u0159ebovat", "VERB", [25, 34]], ["b\u011b\u017en\u00fd", "b\u011b\u017en\u00fd", "ADJ", [35, 40]], ["po\u010d\u00edta\u010d", "po\u010d\u00edta\u010d", "NOUN", [41, 48]], ["p\u0159ipojen\u00fd", "p\u0159ipojen\u00fd", "ADJ", [49, 58]], ["na", "na", "ADP", [59, 61]], ["internet", "internet", "NOUN", [62, 70]], [",", ",", "PUNCT", [70, 71]], ["vybaven\u00fd", "vybaven\u00fd", "ADJ", [72, 80]], ["prost\u0159ed\u00edm", "prost\u0159ed\u00ed", "NOUN", [81, 91]], ["MS", "MS", "NOUN", [92, 94]], ["Office", "Office", "PROPN", [95, 101]], ["a", "a", "CCONJ", [102, 103]], ["prohl\u00ed\u017ee\u010dem", "prohl\u00ed\u017ee\u010d", "NOUN", [104, 115]], ["Internet", "internet", "X", [116, 124]], ["Explorer", "Explorer", "X", [125, 133]], ["verze", "verze", "NOUN", [134, 139]], ["5.0", "5.0", "NUM", [140, 143]], ["a", "a", "CCONJ", [144, 145]], ["vy\u0161\u0161\u00ed", "vysok\u00fd", "ADJ", [146, 151]], [".", ".", "PUNCT", [151, 152]]]], ["calgarske-listy_2003_unor_ocr.txt", "Slu\u017ebu si m\u016f\u017eete prohl\u00e9dnout a vyzkou\u0161et prost\u0159ednictv\u00edm interaktivn\u00ed uk\u00e1zky v\u00fdukov\u00fdch lekc\u00ed na str\u00e1nce AvwAv.zaskolou.", [["Slu\u017ebu", "slu\u017eba", "NOUN", [0, 6]], ["si", "se", "PRON", [7, 9]], ["m\u016f\u017eete", "moci", "VERB", [10, 16]], ["prohl\u00e9dnout", "prohl\u00e9dnout", "VERB", [17, 28]], ["a", "a", "CCONJ", [29, 30]], ["vyzkou\u0161et", "vyzkou\u0161et", "VERB", [31, 40]], ["prost\u0159ednictv\u00edm", "prost\u0159ednictv\u00ed", "NOUN", [41, 56]], ["interaktivn\u00ed", "interaktivn\u00ed", "ADJ", [57, 69]], ["uk\u00e1zky", "uk\u00e1zka", "NOUN", [70, 76]], ["v\u00fdukov\u00fdch", "v\u00fdukov\u00fd", "ADJ", [77, 86]], ["lekc\u00ed", "lekce", "NOUN", [87, 92]], ["na", "na", "ADP", [93, 95]], ["str\u00e1nce", "str\u00e1nka", "NOUN", [96, 103]], ["AvwAv", "avwav", "NOUN", [104, 109]], [".", ".", "PUNCT", [109, 110]], ["zaskolou", "zaskolat", "VERB", [110, 118]], [".", ".", "PUNCT", [118, 119]]]], ["calgarske-listy_2003_unor_ocr.txt", "cz, kde najdete i dal\u0161\u00ed informace.", [["cz", "cz", "NOUN", [0, 2]], [",", ",", "PUNCT", [2, 3]], ["kde", "kde", "ADV", [4, 7]], ["najdete", "naj\u00edt", "VERB", [8, 15]], ["i", "i", "CCONJ", [16, 17]], ["dal\u0161\u00ed", "dal\u0161\u00ed", "ADJ", [18, 23]], ["informace", "informace", "NOUN", [24, 33]], [".", ".", "PUNCT", [33, 34]]]], ["calgarske-listy_2003_unor_ocr.txt", "Na z\u00e1v\u011br bychom V\u00e1s r\u00e1di po\u017e\u00e1dali, abyste o \u0160kole za \u0161kolou informoval \u010desk\u00e9 subjekty a krajansk\u00e9 spolky ve Va\u0161em teritoriu.", [["Na", "na", "ADP", [0, 2]], ["z\u00e1v\u011br", "z\u00e1v\u011br", "NOUN", [3, 8]], ["bychom", "b\u00fdt", "AUX", [9, 15]], ["V\u00e1s", "vy", "PRON", [16, 19]], ["r\u00e1di", "r\u00e1d", "ADJ", [20, 24]], ["po\u017e\u00e1dali", "po\u017e\u00e1dat", "VERB", [25, 33]], [",", ",", "PUNCT", [33, 34]], ["aby", "aby", "SCONJ", [-6877, -6877]], ["byste", "b\u00fdt", "AUX", [-6877, -6877]], ["o", "o", "ADP", [42, 43]], ["\u0160kole", "\u0161kola", "NOUN", [44, 49]], ["za", "za", "ADP", [50, 52]], ["\u0161kolou", "\u0161kola", "NOUN", [53, 59]], ["informoval", "informovat", "VERB", [60, 70]], ["\u010desk\u00e9", "\u010desk\u00fd", "ADJ", [71, 76]], ["subjekty", "subjekt", "NOUN", [77, 85]], ["a", "a", "CCONJ", [86, 87]], ["krajansk\u00e9", "krajansk\u00fd", "ADJ", [88, 97]], ["spolky", "spolek", "NOUN", [98, 104]], ["ve", "v", "ADP", [105, 107]], ["Va\u0161em", "v\u00e1\u0161", "DET", [108, 113]], ["teritoriu", "teritorium", "NOUN", [114, 123]], [".", ".", "PUNCT", [123, 124]]]], ["calgarske-listy_2003_unor_ocr.txt", "Jak\u00e9koliv Va\u0161e dotazy jsme p\u0159ipraveni odpov\u011bd\u011bt telefonicky \u010di e-mailem.", [["Jak\u00e9koliv", "jak\u00fdkoliv", "DET", [0, 9]], ["Va\u0161e", "v\u00e1\u0161", "DET", [10, 14]], ["dotazy", "dotaz", "NOUN", [15, 21]], ["jsme", "b\u00fdt", "AUX", [22, 26]], ["p\u0159ipraveni", "p\u0159ipraven\u00fd", "ADJ", [27, 37]], ["odpov\u011bd\u011bt", "odpov\u011bd\u011bt", "VERB", [38, 47]], ["telefonicky", "telefonicky", "ADV", [48, 59]], ["\u010di", "\u010di", "CCONJ", [60, 62]], ["e", "e", "NOUN", [63, 64]], ["-", "-", "PUNCT", [64, 65]], ["mailem", "mail", "PROPN", [65, 71]], [".", ".", "PUNCT", [71, 72]]]], ["calgarske-listy_2003_unor_ocr.txt", "D\u011bkujeme za V\u00e1\u0161 \u010das a p\u0159ejeme \u00fasp\u011b\u0161n\u00fd pobyt v zahrani\u010d\u00ed, Jan Kala, \u0159editel spole\u010dnosti wAVAv.zaskolou.", [["D\u011bkujeme", "d\u011bkovat", "VERB", [0, 8]], ["za", "za", "ADP", [9, 11]], ["V\u00e1\u0161", "v\u00e1\u0161", "DET", [12, 15]], ["\u010das", "\u010das", "NOUN", [16, 19]], ["a", "a", "CCONJ", [20, 21]], ["p\u0159ejeme", "p\u0159\u00e1t", "VERB", [22, 29]], ["\u00fasp\u011b\u0161n\u00fd", "\u00fasp\u011b\u0161n\u00fd", "ADJ", [30, 37]], ["pobyt", "pobyt", "NOUN", [38, 43]], ["v", "v", "ADP", [44, 45]], ["zahrani\u010d\u00ed", "zahrani\u010d\u00ed", "NOUN", [46, 55]], [",", ",", "PUNCT", [55, 56]], ["Jan", "Jan", "PROPN", [57, 60]], ["Kala", "Kala", "PROPN", [61, 65]], [",", ",", "PUNCT", [65, 66]], ["\u0159editel", "\u0159editel", "NOUN", [67, 74]], ["spole\u010dnosti", "spole\u010dnost", "NOUN", [75, 86]], ["wAVAv", "wavav", "NOUN", [87, 92]], [".", ".", "PUNCT", [92, 93]], ["zaskolou", "zaskolat", "VERB", [93, 101]], [".", ".", "PUNCT", [101, 102]]]], ["calgarske-listy_2003_unor_ocr.txt", "cz Centre for Modern Education (CZ), s.r.o. Janovsk\u00e9ho 11/979, 170 00 Praha 7, tel.: 00420 266 711 582, 00420 220 873 605", [["cz", "cz", "X", [0, 2]], ["Centre", "Centre", "X", [3, 9]], ["for", "for", "X", [10, 13]], ["Modern", "Modern", "X", [14, 20]], ["Education", "Education", "X", [21, 30]], ["(", "(", "PUNCT", [31, 32]], ["CZ", "CZ", "NOUN", [32, 34]], [")", ")", "PUNCT", [34, 35]], [",", ",", "PUNCT", [35, 36]], ["s", "spole\u010dnost", "NOUN", [37, 38]], [".", ".", "PUNCT", [38, 39]], ["r", "rok", "NOUN", [39, 40]], [".", ".", "PUNCT", [40, 41]], ["o", "omezen\u00fd", "ADJ", [41, 42]], [".", ".", "PUNCT", [42, 43]], ["Janovsk\u00e9ho", "Janovsk\u00fd", "PROPN", [44, 54]], ["11", "11", "NUM", [55, 57]], ["/", "/", "PUNCT", [57, 58]], ["979", "979", "NUM", [58, 61]], [",", ",", "PUNCT", [61, 62]], ["170", "170", "NUM", [63, 66]], ["00", "00", "NUM", [67, 69]], ["Praha", "Praha", "PROPN", [70, 75]], ["7", "7", "NUM", [76, 77]], [",", ",", "PUNCT", [77, 78]], ["tel", "telefon", "NOUN", [79, 82]], [".", ".", "PUNCT", [82, 83]], [":", ":", "PUNCT", [83, 84]], ["00420", "00420", "NUM", [85, 90]], ["266", "266", "NUM", [91, 94]], ["711", "711", "NUM", [95, 98]], ["582", "582", "NUM", [99, 102]], [",", ",", "PUNCT", [102, 103]], ["00420", "00420", "NUM", [104, 109]], ["220", "220", "NUM", [110, 113]], ["873", "873", "NUM", [114, 117]], ["605", "605", "NUM", [118, 121]]]], ["calgarske-listy_2003_unor_ocr.txt", "Pov\u00edd\u00e1n\u00ed o tom, jak jsem se sna\u017eil si chytit \u0160t\u011bdrove\u010dern\u00ed rybu.", [["Pov\u00edd\u00e1n\u00ed", "pov\u00edd\u00e1n\u00ed", "NOUN", [0, 8]], ["o", "o", "ADP", [9, 10]], ["tom", "ten", "DET", [11, 14]], [",", ",", "PUNCT", [14, 15]], ["jak", "jak", "ADV", [16, 19]], ["jsem", "b\u00fdt", "AUX", [20, 24]], ["se", "se", "PRON", [25, 27]], ["sna\u017eil", "sna\u017eit", "VERB", [28, 34]], ["si", "se", "PRON", [35, 37]], ["chytit", "chytit", "VERB", [38, 44]], ["\u0160t\u011bdrove\u010dern\u00ed", "\u0161t\u011bdrove\u010dern\u00ed", "ADJ", [45, 58]], ["rybu", "ryba", "NOUN", [59, 63]], [".", ".", "PUNCT", [63, 64]]]], ["calgarske-listy_2003_unor_ocr.txt", "Dr. V\u00e1clav Hoyer.", [["Dr", "Dr", "NOUN", [0, 2]], [".", ".", "PUNCT", [2, 3]], ["V\u00e1clav", "V\u00e1clav", "PROPN", [4, 10]], ["Hoyer", "Hoyer", "PROPN", [11, 16]], [".", ".", "PUNCT", [16, 17]]]], ["calgarske-listy_2003_unor_ocr.txt", "Pro na\u0161e t\u0159et\u00ed V\u00e1noce tr\u00e1ven\u00e9 na Hawaji jsem si sv\u011bdomit\u011b p\u0159edem zajistil dv\u011b akce, vy\u017eaduj\u00edc\u00ed p\u0159\u00edpravu v p\u0159edstihu.", [["Pro", "pro", "ADP", [0, 3]], ["na\u0161e", "n\u00e1\u0161", "DET", [4, 8]], ["t\u0159et\u00ed", "t\u0159et\u00ed", "ADJ", [9, 14]], ["V\u00e1noce", "V\u00e1noce", "NOUN", [15, 21]], ["tr\u00e1ven\u00e9", "tr\u00e1ven\u00fd", "ADJ", [22, 29]], ["na", "na", "ADP", [30, 32]], ["Hawaji", "Hawaj", "PROPN", [33, 39]], ["jsem", "b\u00fdt", "AUX", [40, 44]], ["si", "se", "PRON", [45, 47]], ["sv\u011bdomit\u011b", "sv\u011bdomit\u011b", "ADV", [48, 57]], ["p\u0159edem", "p\u0159edem", "ADV", [58, 64]], ["zajistil", "zajistit", "VERB", [65, 73]], ["dv\u011b", "dva", "NUM", [74, 77]], ["akce", "akce", "NOUN", [78, 82]], [",", ",", "PUNCT", [82, 83]], ["vy\u017eaduj\u00edc\u00ed", "vy\u017eaduj\u00edc\u00ed", "ADJ", [84, 94]], ["p\u0159\u00edpravu", "p\u0159\u00edprava", "NOUN", [95, 103]], ["v", "v", "ADP", [104, 105]], ["p\u0159edstihu", "p\u0159edstih", "NOUN", [106, 115]], [".", ".", "PUNCT", [115, 116]]]], ["calgarske-listy_2003_unor_ocr.txt", "P\u0159ijeli jsme tentokr\u00e1t na pln\u00e9 dva t\u00fddny: jakkoli m\u00e1m pobyt u mo\u0159e r\u00e1d, tak mus\u00edm p\u0159edeslat, \u017ee na dlouh\u00e9 povalov\u00e1n\u00ed na pl\u00e1\u017ei m\u011b moc neu\u017eije.", [["P\u0159ijeli", "p\u0159ijet", "VERB", [0, 7]], ["jsme", "b\u00fdt", "AUX", [8, 12]], ["tentokr\u00e1t", "tentokr\u00e1t", "ADV", [13, 22]], ["na", "na", "ADP", [23, 25]], ["pln\u00e9", "pln\u00fd", "ADJ", [26, 30]], ["dva", "dva", "NUM", [31, 34]], ["t\u00fddny", "t\u00fdden", "NOUN", [35, 40]], [":", ":", "PUNCT", [40, 41]], ["jakkoli", "jakkoli", "ADV", [42, 49]], ["m\u00e1m", "m\u00edt", "VERB", [50, 53]], ["pobyt", "pobyt", "NOUN", [54, 59]], ["u", "u", "ADP", [60, 61]], ["mo\u0159e", "mo\u0159e", "NOUN", [62, 66]], ["r\u00e1d", "r\u00e1d", "ADJ", [67, 70]], [",", ",", "PUNCT", [70, 71]], ["tak", "tak", "ADV", [72, 75]], ["mus\u00edm", "muset", "VERB", [76, 81]], ["p\u0159edeslat", "p\u0159edeslat", "VERB", [82, 91]], [",", ",", "PUNCT", [91, 92]], ["\u017ee", "\u017ee", "SCONJ", [93, 95]], ["na", "na", "ADP", [96, 98]], ["dlouh\u00e9", "dlouh\u00fd", "ADJ", [99, 105]], ["povalov\u00e1n\u00ed", "povalov\u00e1n\u00ed", "NOUN", [106, 116]], ["na", "na", "ADP", [117, 119]], ["pl\u00e1\u017ei", "pl\u00e1\u017e", "NOUN", [120, 125]], ["m\u011b", "j\u00e1", "PRON", [126, 128]], ["moc", "moc", "ADV", [129, 132]], ["neu\u017eije", "u\u017e\u00edt", "VERB", [133, 140]], [".", ".", "PUNCT", [140, 141]]]], ["calgarske-listy_2003_unor_ocr.txt", "A tak jsem si letos p\u0159ivezl laptop abych slovesn\u011b tvo\u0159il a vyrovnal skluz v m\u00e9 liter\u00e1rn\u00ed \u010dinnosti, kter\u00fd mi nar\u016fst\u00e1 ji\u017e \u0159adu m\u011bs\u00edc\u016f.", [["A", "a", "CCONJ", [0, 1]], ["tak", "tak", "ADV", [2, 5]], ["jsem", "b\u00fdt", "AUX", [6, 10]], ["si", "se", "PRON", [11, 13]], ["letos", "letos", "ADV", [14, 19]], ["p\u0159ivezl", "p\u0159iv\u00e9zt", "VERB", [20, 27]], ["laptop", "laptop", "NOUN", [28, 34]], ["aby", "aby", "SCONJ", [-7641, -7641]], ["bych", "b\u00fdt", "AUX", [-7641, -7641]], ["slovesn\u011b", "slovesn\u011b", "ADV", [41, 49]], ["tvo\u0159il", "tvo\u0159it", "VERB", [50, 56]], ["a", "a", "CCONJ", [57, 58]], ["vyrovnal", "vyrovnat", "VERB", [59, 67]], ["skluz", "skluz", "NOUN", [68, 73]], ["v", "v", "ADP", [74, 75]], ["m\u00e9", "m\u016fj", "DET", [76, 78]], ["liter\u00e1rn\u00ed", "liter\u00e1rn\u00ed", "ADJ", [79, 88]], ["\u010dinnosti", "\u010dinnost", "NOUN", [89, 97]], [",", ",", "PUNCT", [97, 98]], ["kter\u00fd", "kter\u00fd", "DET", [99, 104]], ["mi", "j\u00e1", "PRON", [105, 107]], ["nar\u016fst\u00e1", "nar\u016fstat", "VERB", [108, 115]], ["ji\u017e", "ji\u017e", "ADV", [116, 119]], ["\u0159adu", "\u0159ada", "NOUN", [120, 124]], ["m\u011bs\u00edc\u016f", "m\u011bs\u00edc", "NOUN", [125, 131]], [".", ".", "PUNCT", [131, 132]]]], ["calgarske-listy_2003_unor_ocr.txt", "Co se zm\u00edn\u011bn\u00fdch akc\u00ed t\u00fd\u010de, objednal jsem si jednodenn\u00ed ryb\u00e1\u0159skou vyj\u00ed\u017e\u010fku a vybavil se na dvoudenn\u00ed v\u00fd\u0161lap na m\u00edstn\u00ed t\u0159\u00edtis\u00edcovku.", [["Co", "co", "PRON", [0, 2]], ["se", "se", "PRON", [3, 5]], ["zm\u00edn\u011bn\u00fdch", "zm\u00edn\u011bn\u00fd", "ADJ", [6, 15]], ["akc\u00ed", "akce", "NOUN", [16, 20]], ["t\u00fd\u010de", "t\u00fdkat", "VERB", [21, 25]], [",", ",", "PUNCT", [25, 26]], ["objednal", "objednat", "VERB", [27, 35]], ["jsem", "b\u00fdt", "AUX", [36, 40]], ["si", "se", "PRON", [41, 43]], ["jednodenn\u00ed", "jednodenn\u00ed", "ADJ", [44, 54]], ["ryb\u00e1\u0159skou", "ryb\u00e1\u0159sk\u00fd", "ADJ", [55, 64]], ["vyj\u00ed\u017e\u010fku", "vyj\u00ed\u017e", "NOUN", [65, 73]], ["a", "a", "CCONJ", [74, 75]], ["vybavil", "vybavit", "VERB", [76, 83]], ["se", "se", "PRON", [84, 86]], ["na", "na", "ADP", [87, 89]], ["dvoudenn\u00ed", "dvoudenn\u00ed", "ADJ", [90, 99]], ["v\u00fd\u0161lap", "v\u00fd\u0161lap", "NOUN", [100, 106]], ["na", "na", "ADP", [107, 109]], ["m\u00edstn\u00ed", "m\u00edstn\u00ed", "ADJ", [110, 116]], ["t\u0159\u00edtis\u00edcovku", "t\u0159\u00edtis\u00edcovka", "NOUN", [117, 129]], [".", ".", "PUNCT", [129, 130]]]], ["calgarske-listy_2003_unor_ocr.txt", "V kon\u010din\u00e1ch, kde \u017eiji a v jejich bl\u00edzk\u00e9m skol\u00ed ryb ub\u00fdv\u00e1, jsou st\u00e1le men\u0161\u00ed, asi je to t\u00edm, \u017ee p\u0159ib\u00fdv\u00e1 ryb\u00e1\u0159\u016f, s t\u00edm, jak p\u0159ib\u00fdv\u00e1 obyvatel\u016f Alberty.", [["V", "v", "ADP", [0, 1]], ["kon\u010din\u00e1ch", "kon\u010dina", "NOUN", [2, 11]], [",", ",", "PUNCT", [11, 12]], ["kde", "kde", "ADV", [13, 16]], ["\u017eiji", "\u017e\u00edt", "VERB", [17, 21]], ["a", "a", "CCONJ", [22, 23]], ["v", "v", "ADP", [24, 25]], ["jejich", "jeho", "DET", [26, 32]], ["bl\u00edzk\u00e9m", "bl\u00edzk\u00fd", "ADJ", [33, 40]], ["skol\u00ed", "skol\u00ed", "NOUN", [41, 46]], ["ryb", "ryba", "NOUN", [47, 50]], ["ub\u00fdv\u00e1", "ub\u00fdvat", "VERB", [51, 56]], [",", ",", "PUNCT", [56, 57]], ["jsou", "b\u00fdt", "AUX", [58, 62]], ["st\u00e1le", "st\u00e1le", "ADV", [63, 68]], ["men\u0161\u00ed", "mal\u00fd", "ADJ", [69, 74]], [",", ",", "PUNCT", [74, 75]], ["asi", "asi", "PART", [76, 79]], ["je", "b\u00fdt", "AUX", [80, 82]], ["to", "ten", "DET", [83, 85]], ["t\u00edm", "ten", "DET", [86, 89]], [",", ",", "PUNCT", [89, 90]], ["\u017ee", "\u017ee", "SCONJ", [91, 93]], ["p\u0159ib\u00fdv\u00e1", "p\u0159ib\u00fdvat", "VERB", [94, 101]], ["ryb\u00e1\u0159\u016f", "ryb\u00e1\u0159", "NOUN", [102, 108]], [",", ",", "PUNCT", [108, 109]], ["s", "s", "ADP", [110, 111]], ["t\u00edm", "ten", "DET", [112, 115]], [",", ",", "PUNCT", [115, 116]], ["jak", "jak", "ADV", [117, 120]], ["p\u0159ib\u00fdv\u00e1", "p\u0159ib\u00fdvat", "VERB", [121, 128]], ["obyvatel\u016f", "obyvatel", "NOUN", [129, 138]], ["Alberty", "Alberta", "PROPN", [139, 146]], [".", ".", "PUNCT", [146, 147]]]], ["calgarske-listy_2003_unor_ocr.txt", "A tak nepom\u00e1h\u00e1 ani to, \u017ee se pravidla zp\u0159\u00eds\u0148uj\u00ed a kv\u00f3ty sni\u017euj\u00ed.", [["A", "a", "CCONJ", [0, 1]], ["tak", "tak", "ADV", [2, 5]], ["nepom\u00e1h\u00e1", "pom\u00e1hat", "VERB", [6, 14]], ["ani", "ani", "CCONJ", [15, 18]], ["to", "ten", "DET", [19, 21]], [",", ",", "PUNCT", [21, 22]], ["\u017ee", "\u017ee", "SCONJ", [23, 25]], ["se", "se", "PRON", [26, 28]], ["pravidla", "pravidlo", "NOUN", [29, 37]], ["zp\u0159\u00eds\u0148uj\u00ed", "zp\u0159\u00eds\u0148ovat", "VERB", [38, 47]], ["a", "a", "CCONJ", [48, 49]], ["kv\u00f3ty", "kv\u00f3ta", "NOUN", [50, 55]], ["sni\u017euj\u00ed", "sni\u017eovat", "VERB", [56, 63]], [".", ".", "PUNCT", [63, 64]]]], ["calgarske-listy_2003_unor_ocr.txt", "Za rybami se mus\u00ed st\u00e1le d\u00e1le od Calgary, bu\u010fto \u00eda sever, kde jsou st\u00e1le jezera pln\u00e1 hladov\u00fdch ryb, ale a jsou p\u0159\u00edstupna jen hydropl\u00e1nem nebo v\u00fd\u0161e do hor k \u00ed\u010dkter\u00fdm odlehl\u00fdm jez\u00edrk\u016fm, kam se \u010dlov\u011bk vy\u0161kr\u00e1be sice po sv\u00fdch, ale ne snadno.", [["Za", "za", "ADP", [0, 2]], ["rybami", "ryba", "NOUN", [3, 9]], ["se", "se", "PRON", [10, 12]], ["mus\u00ed", "muset", "VERB", [13, 17]], ["st\u00e1le", "st\u00e1le", "ADV", [18, 23]], ["d\u00e1le", "d\u00e1le", "ADV", [24, 28]], ["od", "od", "ADP", [29, 31]], ["Calgary", "Calgary", "PROPN", [32, 39]], [",", ",", "PUNCT", [39, 40]], ["bu\u010fto", "bu\u010fto", "CCONJ", [41, 46]], ["\u00eda", "\u00eda", "VERB", [47, 49]], ["sever", "sever", "NOUN", [50, 55]], [",", ",", "PUNCT", [55, 56]], ["kde", "kde", "ADV", [57, 60]], ["jsou", "b\u00fdt", "AUX", [61, 65]], ["st\u00e1le", "st\u00e1le", "ADV", [66, 71]], ["jezera", "jezero", "NOUN", [72, 78]], ["pln\u00e1", "pln\u00fd", "ADJ", [79, 83]], ["hladov\u00fdch", "hladov\u00fd", "ADJ", [84, 93]], ["ryb", "ryba", "NOUN", [94, 97]], [",", ",", "PUNCT", [97, 98]], ["ale", "ale", "CCONJ", [99, 102]], ["a", "a", "CCONJ", [103, 104]], ["jsou", "b\u00fdt", "AUX", [105, 109]], ["p\u0159\u00edstupna", "p\u0159\u00edstupn\u00fd", "ADJ", [110, 119]], ["jen", "jen", "PART", [120, 123]], ["hydropl\u00e1nem", "hydropl\u00e1n", "NOUN", [124, 135]], ["nebo", "nebo", "CCONJ", [136, 140]], ["v\u00fd\u0161e", "v\u00fd\u0161e", "NOUN", [141, 145]], ["do", "do", "ADP", [146, 148]], ["hor", "hora", "NOUN", [149, 152]], ["k", "k", "ADP", [153, 154]], ["\u00ed\u010dkter\u00fdm", "\u00ed\u010dkter\u00fd", "ADJ", [155, 163]], ["odlehl\u00fdm", "odlehl\u00fd", "ADJ", [164, 172]], ["jez\u00edrk\u016fm", "jez\u00edrek", "NOUN", [173, 181]], [",", ",", "PUNCT", [181, 182]], ["kam", "kam", "ADV", [183, 186]], ["se", "se", "PRON", [187, 189]], ["\u010dlov\u011bk", "\u010dlov\u011bk", "NOUN", [190, 196]], ["vy\u0161kr\u00e1be", "vy\u0161kr\u00e1b\u011bt", "VERB", [197, 205]], ["sice", "sice", "CCONJ", [206, 210]], ["po", "po", "ADP", [211, 213]], ["sv\u00fdch", "sv\u016fj", "DET", [214, 219]], [",", ",", "PUNCT", [219, 220]], ["ale", "ale", "CCONJ", [221, 224]], ["ne", "ne", "PART", [225, 227]], ["snadno", "snadno", "ADV", [228, 234]], [".", ".", "PUNCT", [234, 235]]]], ["calgarske-listy_2003_unor_ocr.txt", "Proto se st\u00e1le v\u00edce orientuji na chyt\u00e1n\u00ed ryb na mo\u0159i, bu\u010fto s n\u011bk\u00fdm z m\u00edstn\u00edch p\u0159\u00e1tel vlastn\u00edc\u00edch lo\u010f a v\u00fdbavu anebo, co\u017e je \u010dast\u011bj\u0161\u00ed a produktivn\u011bj\u0161\u00ed, najmut\u00edm tzv. charteru, lodi s pos\u00e1dkou a za\u0159\u00edzen\u00edm pro sportovn\u00ed rybolov.", [["Proto", "proto", "CCONJ", [0, 5]], ["se", "se", "PRON", [6, 8]], ["st\u00e1le", "st\u00e1le", "ADV", [9, 14]], ["v\u00edce", "v\u00edce", "ADV", [15, 19]], ["orientuji", "orientovat", "VERB", [20, 29]], ["na", "na", "ADP", [30, 32]], ["chyt\u00e1n\u00ed", "chyt\u00e1n\u00ed", "NOUN", [33, 40]], ["ryb", "ryba", "NOUN", [41, 44]], ["na", "na", "ADP", [45, 47]], ["mo\u0159i", "mo\u0159e", "NOUN", [48, 52]], [",", ",", "PUNCT", [52, 53]], ["bu\u010fto", "bu\u010fto", "CCONJ", [54, 59]], ["s", "s", "ADP", [60, 61]], ["n\u011bk\u00fdm", "n\u011bkdo", "PRON", [62, 67]], ["z", "z", "ADP", [68, 69]], ["m\u00edstn\u00edch", "m\u00edstn\u00ed", "ADJ", [70, 78]], ["p\u0159\u00e1tel", "p\u0159\u00edtel", "NOUN", [79, 85]], ["vlastn\u00edc\u00edch", "vlastn\u00edc\u00ed", "ADJ", [86, 97]], ["lo\u010f", "lo\u010f", "NOUN", [98, 101]], ["a", "a", "CCONJ", [102, 103]], ["v\u00fdbavu", "v\u00fdbava", "NOUN", [104, 110]], ["anebo", "anebo", "CCONJ", [111, 116]], [",", ",", "PUNCT", [116, 117]], ["co\u017e", "co\u017e", "PRON", [118, 121]], ["je", "b\u00fdt", "AUX", [122, 124]], ["\u010dast\u011bj\u0161\u00ed", "\u010dast\u00fd", "ADJ", [125, 133]], ["a", "a", "CCONJ", [134, 135]], ["produktivn\u011bj\u0161\u00ed", "produktivn\u00ed", "ADJ", [136, 150]], [",", ",", "PUNCT", [150, 151]], ["najmut\u00edm", "najmut\u00ed", "NOUN", [152, 160]], ["tzv", "takzvan\u00fd", "ADJ", [161, 164]], [".", ".", "PUNCT", [164, 165]], ["charteru", "charter", "NOUN", [166, 174]], [",", ",", "PUNCT", [174, 175]], ["lodi", "lo\u010f", "NOUN", [176, 180]], ["s", "s", "ADP", [181, 182]], ["pos\u00e1dkou", "pos\u00e1dka", "NOUN", [183, 191]], ["a", "a", "CCONJ", [192, 193]], ["za\u0159\u00edzen\u00edm", "za\u0159\u00edzen\u00ed", "NOUN", [194, 203]], ["pro", "pro", "ADP", [204, 207]], ["sportovn\u00ed", "sportovn\u00ed", "ADJ", [208, 217]], ["rybolov", "rybolov", "NOUN", [218, 225]], [".", ".", "PUNCT", [225, 226]]]], ["calgarske-listy_2003_unor_ocr.txt", "Nen\u00ed to pr\u00e1v\u011b levn\u00e1 z\u00e1le\u017eitost, v sou\u010dasn\u00e9 dob\u011b to vyjde tak na dv\u011b st\u011b dolar\u016f na osobu denn\u011b (\u010d\u00edm\u017e se rozum\u00ed osm hodin), v Kanad\u011b v Dolarech kanadsk\u00fdch a zde na Hawaji v \u201eZelen\u00fdch\u201c (Green Bucks), co\u017e je podstatn\u011b v\u00edce, p\u0159esn\u011bji \u0159e\u010deno jednacel\u00e1\u0161est kr\u00e1t tolik.", [["Nen\u00ed", "b\u00fdt", "AUX", [0, 4]], ["to", "ten", "DET", [5, 7]], ["pr\u00e1v\u011b", "pr\u00e1v\u011b", "ADV", [8, 13]], ["levn\u00e1", "levn\u00fd", "ADJ", [14, 19]], ["z\u00e1le\u017eitost", "z\u00e1le\u017eitost", "NOUN", [20, 30]], [",", ",", "PUNCT", [30, 31]], ["v", "v", "ADP", [32, 33]], ["sou\u010dasn\u00e9", "sou\u010dasn\u00fd", "ADJ", [34, 42]], ["dob\u011b", "doba", "NOUN", [43, 47]], ["to", "ten", "DET", [48, 50]], ["vyjde", "vyj\u00edt", "VERB", [51, 56]], ["tak", "tak", "ADV", [57, 60]], ["na", "na", "ADP", [61, 63]], ["dv\u011b", "dva", "NUM", [64, 67]], ["st\u011b", "sto", "NUM", [68, 71]], ["dolar\u016f", "dolar", "NOUN", [72, 78]], ["na", "na", "ADP", [79, 81]], ["osobu", "osoba", "NOUN", [82, 87]], ["denn\u011b", "denn\u011b", "ADV", [88, 93]], ["(", "(", "PUNCT", [94, 95]], ["\u010d\u00edm\u017e", "co\u017e", "PRON", [95, 99]], ["se", "se", "PRON", [100, 102]], ["rozum\u00ed", "rozum\u011bt", "VERB", [103, 109]], ["osm", "osm", "NUM", [110, 113]], ["hodin", "hodina", "NOUN", [114, 119]], [")", ")", "PUNCT", [119, 120]], [",", ",", "PUNCT", [120, 121]], ["v", "v", "ADP", [122, 123]], ["Kanad\u011b", "Kanada", "PROPN", [124, 130]], ["v", "v", "ADP", [131, 132]], ["Dolarech", "dolar", "NOUN", [133, 141]], ["kanadsk\u00fdch", "kanadsk\u00fd", "ADJ", [142, 152]], ["a", "a", "CCONJ", [153, 154]], ["zde", "zde", "ADV", [155, 158]], ["na", "na", "ADP", [159, 161]], ["Hawaji", "Hawaj", "PROPN", [162, 168]], ["v", "v", "ADP", [169, 170]], ["\u201e", "\"", "PUNCT", [171, 172]], ["Zelen\u00fdch", "zelen\u00fd", "ADJ", [172, 180]], ["\u201c", "\"", "PUNCT", [180, 181]], ["(", "(", "PUNCT", [182, 183]], ["Green", "Green", "X", [183, 188]], ["Bucks", "Bucks", "X", [189, 194]], [")", ")", "PUNCT", [194, 195]], [",", ",", "PUNCT", [195, 196]], ["co\u017e", "co\u017e", "PRON", [197, 200]], ["je", "b\u00fdt", "AUX", [201, 203]], ["podstatn\u011b", "podstatn\u011b", "ADV", [204, 213]], ["v\u00edce", "v\u00edce", "ADV", [214, 218]], [",", ",", "PUNCT", [218, 219]], ["p\u0159esn\u011bji", "p\u0159esn\u011b", "ADV", [220, 228]], ["\u0159e\u010deno", "\u0159e\u010den\u00fd", "ADJ", [229, 235]], ["jednacel\u00e1\u0161est", "jednacel\u00e1\u0161est", "NOUN", [236, 249]], ["kr\u00e1t", "kr\u00e1t", "ADV", [250, 254]], ["tolik", "tolik", "DET", [255, 260]], [".", ".", "PUNCT", [260, 261]]]], ["calgarske-listy_2003_unor_ocr.txt", "Pen\u011bz je to nem\u00e1lo, ale kdy\u017e se spo\u010d\u00edtaj\u00ed n\u00e1klady na \u010dlun a jeho udr\u017eov\u00e1n\u00ed, ryb\u00e1\u0159sk\u00fd vercajk a cena paliva, tak se perspektiva pon\u011bkud zm\u011bn\u00ed.", [["Pen\u011bz", "pen\u00edze", "NOUN", [0, 5]], ["je", "b\u00fdt", "AUX", [6, 8]], ["to", "ten", "DET", [9, 11]], ["nem\u00e1lo", "nem\u00e1lo", "DET", [12, 18]], [",", ",", "PUNCT", [18, 19]], ["ale", "ale", "CCONJ", [20, 23]], ["kdy\u017e", "kdy\u017e", "SCONJ", [24, 28]], ["se", "se", "PRON", [29, 31]], ["spo\u010d\u00edtaj\u00ed", "spo\u010d\u00edtat", "VERB", [32, 41]], ["n\u00e1klady", "n\u00e1klad", "NOUN", [42, 49]], ["na", "na", "ADP", [50, 52]], ["\u010dlun", "\u010dlun", "NOUN", [53, 57]], ["a", "a", "CCONJ", [58, 59]], ["jeho", "jeho", "DET", [60, 64]], ["udr\u017eov\u00e1n\u00ed", "udr\u017eov\u00e1n\u00ed", "NOUN", [65, 74]], [",", ",", "PUNCT", [74, 75]], ["ryb\u00e1\u0159sk\u00fd", "ryb\u00e1\u0159sk\u00fd", "ADJ", [76, 84]], ["vercajk", "vercajk", "NOUN", [85, 92]], ["a", "a", "CCONJ", [93, 94]], ["cena", "cena", "NOUN", [95, 99]], ["paliva", "palivo", "NOUN", [100, 106]], [",", ",", "PUNCT", [106, 107]], ["tak", "tak", "ADV", [108, 111]], ["se", "se", "PRON", [112, 114]], ["perspektiva", "perspektiva", "NOUN", [115, 126]], ["pon\u011bkud", "pon\u011bkud", "ADV", [127, 134]], ["zm\u011bn\u00ed", "zm\u011bnit", "VERB", [135, 140]], [".", ".", "PUNCT", [140, 141]]]], ["calgarske-listy_2003_unor_ocr.txt", "Ze sv\u00fdch ryb\u00e1\u0159sk\u00fdch v\u00fdlet\u016f na Pacifik si zpravidla p\u0159ivezu tolik, \u017ee to napln\u00ed mraz\u00e1k na rok, tak\u017ee p\u0159i sou\u010dasn\u00fdch cen\u00e1ch ryb se mohu pochlubit faktem, \u017ee se cena chycen\u00fdch ryb alespo\u0148 p\u0159ibl\u00ed\u017e\u00ed cen\u011b v supermarketu.", [["Ze", "z", "ADP", [0, 2]], ["sv\u00fdch", "sv\u016fj", "DET", [3, 8]], ["ryb\u00e1\u0159sk\u00fdch", "ryb\u00e1\u0159sk\u00fd", "ADJ", [9, 19]], ["v\u00fdlet\u016f", "v\u00fdlet", "NOUN", [20, 26]], ["na", "na", "ADP", [27, 29]], ["Pacifik", "Pacifik", "PROPN", [30, 37]], ["si", "se", "PRON", [38, 40]], ["zpravidla", "zpravidla", "ADV", [41, 50]], ["p\u0159ivezu", "p\u0159iv\u00e9zt", "VERB", [51, 58]], ["tolik", "tolik", "DET", [59, 64]], [",", ",", "PUNCT", [64, 65]], ["\u017ee", "\u017ee", "SCONJ", [66, 68]], ["to", "ten", "DET", [69, 71]], ["napln\u00ed", "naplnit", "VERB", [72, 78]], ["mraz\u00e1k", "mraz\u00e1k", "NOUN", [79, 85]], ["na", "na", "ADP", [86, 88]], ["rok", "rok", "NOUN", [89, 92]], [",", ",", "PUNCT", [92, 93]], ["tak\u017ee", "tak\u017ee", "SCONJ", [94, 99]], ["p\u0159i", "p\u0159i", "ADP", [100, 103]], ["sou\u010dasn\u00fdch", "sou\u010dasn\u00fd", "ADJ", [104, 114]], ["cen\u00e1ch", "cena", "NOUN", [115, 121]], ["ryb", "ryba", "NOUN", [122, 125]], ["se", "se", "PRON", [126, 128]], ["mohu", "moci", "VERB", [129, 133]], ["pochlubit", "pochlubit", "VERB", [134, 143]], ["faktem", "fakt", "NOUN", [144, 150]], [",", ",", "PUNCT", [150, 151]], ["\u017ee", "\u017ee", "SCONJ", [152, 154]], ["se", "se", "PRON", [155, 157]], ["cena", "cena", "NOUN", [158, 162]], ["chycen\u00fdch", "chycen\u00fd", "ADJ", [163, 172]], ["ryb", "ryba", "NOUN", [173, 176]], ["alespo\u0148", "alespo\u0148", "ADV", [177, 184]], ["p\u0159ibl\u00ed\u017e\u00ed", "p\u0159ibl\u00ed\u017eit", "VERB", [185, 193]], ["cen\u011b", "cena", "NOUN", [194, 198]], ["v", "v", "ADP", [199, 200]], ["supermarketu", "supermarket", "NOUN", [201, 213]], [".", ".", "PUNCT", [213, 214]]]], ["calgarske-listy_2003_unor_ocr.txt", "D\u016fvodem, pro\u010d jsem se rozhodl si zaplatit den na mo\u0159i s profesion\u00e1ly nebyla jenom touha si \u0160t\u011bdrove\u010dern\u00ed rybu chytit, ale hlavn\u011b skute\u010dnost, \u017ee jsem cht\u011bl zkusit n\u011bco nov\u00e9ho, nebo\u0165 v t\u011bchto vod\u00e1ch jsem je\u0161t\u011b nechytal.", [["D\u016fvodem", "d\u016fvod", "NOUN", [0, 7]], [",", ",", "PUNCT", [7, 8]], ["pro\u010d", "pro\u010d", "ADV", [9, 13]], ["jsem", "b\u00fdt", "AUX", [14, 18]], ["se", "se", "PRON", [19, 21]], ["rozhodl", "rozhodnout", "VERB", [22, 29]], ["si", "se", "PRON", [30, 32]], ["zaplatit", "zaplatit", "VERB", [33, 41]], ["den", "den", "NOUN", [42, 45]], ["na", "na", "ADP", [46, 48]], ["mo\u0159i", "mo\u0159e", "NOUN", [49, 53]], ["s", "s", "ADP", [54, 55]], ["profesion\u00e1ly", "profesion\u00e1l", "NOUN", [56, 68]], ["nebyla", "b\u00fdt", "AUX", [69, 75]], ["jenom", "jenom", "PART", [76, 81]], ["touha", "touha", "NOUN", [82, 87]], ["si", "se", "PRON", [88, 90]], ["\u0160t\u011bdrove\u010dern\u00ed", "\u0161t\u011bdrove\u010dern\u00ed", "ADJ", [91, 104]], ["rybu", "ryba", "NOUN", [105, 109]], ["chytit", "chytit", "VERB", [110, 116]], [",", ",", "PUNCT", [116, 117]], ["ale", "ale", "CCONJ", [118, 121]], ["hlavn\u011b", "hlavn\u011b", "ADV", [122, 128]], ["skute\u010dnost", "skute\u010dnost", "NOUN", [129, 139]], [",", ",", "PUNCT", [139, 140]], ["\u017ee", "\u017ee", "SCONJ", [141, 143]], ["jsem", "b\u00fdt", "AUX", [144, 148]], ["cht\u011bl", "cht\u00edt", "VERB", [149, 154]], ["zkusit", "zkusit", "VERB", [155, 161]], ["n\u011bco", "n\u011bco", "PRON", [162, 166]], ["nov\u00e9ho", "nov\u00fd", "ADJ", [167, 173]], [",", ",", "PUNCT", [173, 174]], ["nebo\u0165", "nebo\u0165", "CCONJ", [175, 180]], ["v", "v", "ADP", [181, 182]], ["t\u011bchto", "tento", "DET", [183, 189]], ["vod\u00e1ch", "voda", "NOUN", [190, 196]], ["jsem", "b\u00fdt", "AUX", [197, 201]], ["je\u0161t\u011b", "je\u0161t\u011b", "ADV", [202, 207]], ["nechytal", "chytat", "VERB", [208, 216]], [".", ".", "PUNCT", [216, 217]]]], ["calgarske-listy_2003_unor_ocr.txt", "Tak\u00e9 jsem 3  doufal m\u00edt t\u00e9ma na dal\u0161\u00ed pov\u00edd\u00e1n\u00ed, nebo\u0165 jsem o\u010dek\u00e1val nev\u0161edn\u00ed ryb\u00e1\u0159sk\u00fd z\u00e1\u017eitek.", [["Tak\u00e9", "tak\u00e9", "ADV", [0, 4]], ["jsem", "b\u00fdt", "AUX", [5, 9]], ["3", "3", "NUM", [10, 11]], ["doufal", "doufat", "VERB", [13, 19]], ["m\u00edt", "m\u00edt", "VERB", [20, 23]], ["t\u00e9ma", "t\u00e9ma", "NOUN", [24, 28]], ["na", "na", "ADP", [29, 31]], ["dal\u0161\u00ed", "dal\u0161\u00ed", "ADJ", [32, 37]], ["pov\u00edd\u00e1n\u00ed", "pov\u00edd\u00e1n\u00ed", "NOUN", [38, 46]], [",", ",", "PUNCT", [46, 47]], ["nebo\u0165", "nebo\u0165", "CCONJ", [48, 53]], ["jsem", "b\u00fdt", "AUX", [54, 58]], ["o\u010dek\u00e1val", "o\u010dek\u00e1vat", "VERB", [59, 67]], ["nev\u0161edn\u00ed", "v\u0161edn\u00ed", "ADJ", [68, 76]], ["ryb\u00e1\u0159sk\u00fd", "ryb\u00e1\u0159sk\u00fd", "ADJ", [77, 85]], ["z\u00e1\u017eitek", "z\u00e1\u017eitek", "NOUN", [86, 93]], [".", ".", "PUNCT", [93, 94]]]], ["calgarske-listy_2003_unor_ocr.txt", "Dost jsem se zklamal; kdo \u010dek\u00e1 popis boje s n\u011bkolika metr\u00e1kovou obludou ve stylu Hemingwaye a jeho Starce a mo\u0159e nebude t\u00edmto pov\u00edd\u00e1n\u00edm uspokojen a nebude to jen proto, \u017ee nejsem Hemingway.", [["Dost", "dost", "ADV", [0, 4]], ["jsem", "b\u00fdt", "AUX", [5, 9]], ["se", "se", "PRON", [10, 12]], ["zklamal", "zklamat", "VERB", [13, 20]], [";", ";", "PUNCT", [20, 21]], ["kdo", "kdo", "PRON", [22, 25]], ["\u010dek\u00e1", "\u010dekat", "VERB", [26, 30]], ["popis", "popis", "NOUN", [31, 36]], ["boje", "boj", "NOUN", [37, 41]], ["s", "s", "ADP", [42, 43]], ["n\u011bkolika", "n\u011bkolik", "DET", [44, 52]], ["metr\u00e1kovou", "metr\u00e1kov\u00fd", "ADJ", [53, 63]], ["obludou", "obluda", "NOUN", [64, 71]], ["ve", "v", "ADP", [72, 74]], ["stylu", "styl", "NOUN", [75, 80]], ["Hemingwaye", "Hemingway", "PROPN", [81, 91]], ["a", "a", "CCONJ", [92, 93]], ["jeho", "jeho", "DET", [94, 98]], ["Starce", "sta\u0159ec", "NOUN", [99, 105]], ["a", "a", "CCONJ", [106, 107]], ["mo\u0159e", "mo\u0159e", "NOUN", [108, 112]], ["nebude", "b\u00fdt", "AUX", [113, 119]], ["t\u00edmto", "tento", "DET", [120, 125]], ["pov\u00edd\u00e1n\u00edm", "pov\u00edd\u00e1n\u00ed", "NOUN", [126, 135]], ["uspokojen", "uspokojen\u00fd", "ADJ", [136, 145]], ["a", "a", "CCONJ", [146, 147]], ["nebude", "b\u00fdt", "AUX", [148, 154]], ["to", "ten", "DET", [155, 157]], ["jen", "jen", "ADV", [158, 161]], ["proto", "proto", "ADV", [162, 167]], [",", ",", "PUNCT", [167, 168]], ["\u017ee", "\u017ee", "SCONJ", [169, 171]], ["nejsem", "b\u00fdt", "AUX", [172, 178]], ["Hemingway", "Hemingway", "PROPN", [179, 188]], [".", ".", "PUNCT", [188, 189]]]], ["calgarske-listy_2003_unor_ocr.txt", "P\u0159em\u00fd\u0161lel jsem, jestli o tomto sv\u00e9m z\u00e1\u017eitku m\u00e1m v\u016fbec ps\u00e1t, ale pak jsem se rozhodl, \u017ee ano, v nejhor\u0161\u00edm to podstr\u010d\u00edm panu Ma\u0161atovi do Calgarsk\u00fdch list\u016f za V\u00e1no\u010dn\u00ed pov\u00eddku.", [["P\u0159em\u00fd\u0161lel", "p\u0159em\u00fd\u0161let", "VERB", [0, 9]], ["jsem", "b\u00fdt", "AUX", [10, 14]], [",", ",", "PUNCT", [14, 15]], ["jestli", "jestli", "SCONJ", [16, 22]], ["o", "o", "ADP", [23, 24]], ["tomto", "tento", "DET", [25, 30]], ["sv\u00e9m", "sv\u016fj", "DET", [31, 35]], ["z\u00e1\u017eitku", "z\u00e1\u017eitek", "NOUN", [36, 43]], ["m\u00e1m", "m\u00edt", "VERB", [44, 47]], ["v\u016fbec", "v\u016fbec", "PART", [48, 53]], ["ps\u00e1t", "ps\u00e1t", "VERB", [54, 58]], [",", ",", "PUNCT", [58, 59]], ["ale", "ale", "CCONJ", [60, 63]], ["pak", "pak", "ADV", [64, 67]], ["jsem", "b\u00fdt", "AUX", [68, 72]], ["se", "se", "PRON", [73, 75]], ["rozhodl", "rozhodnout", "VERB", [76, 83]], [",", ",", "PUNCT", [83, 84]], ["\u017ee", "\u017ee", "SCONJ", [85, 87]], ["ano", "ano", "PART", [88, 91]], [",", ",", "PUNCT", [91, 92]], ["v", "v", "ADP", [93, 94]], ["nejhor\u0161\u00edm", "hor\u0161\u00ed", "ADJ", [95, 104]], ["to", "ten", "DET", [105, 107]], ["podstr\u010d\u00edm", "podstr\u010d\u00ed", "ADJ", [108, 117]], ["panu", "pan", "NOUN", [118, 122]], ["Ma\u0161atovi", "Ma\u0161at", "PROPN", [123, 131]], ["do", "do", "ADP", [132, 134]], ["Calgarsk\u00fdch", "calgarsk\u00fd", "ADJ", [135, 146]], ["list\u016f", "list", "NOUN", [147, 152]], ["za", "za", "ADP", [153, 155]], ["V\u00e1no\u010dn\u00ed", "v\u00e1no\u010dn\u00ed", "ADJ", [156, 163]], ["pov\u00eddku", "pov\u00eddka", "NOUN", [164, 171]], [".", ".", "PUNCT", [171, 172]]]], ["calgarske-listy_2003_unor_ocr.txt", "V m\u00edstn\u00edch tepl\u00fdch a hlubok\u00fdch mo\u0159\u00edch je ryb habad\u011bj.", [["V", "v", "ADP", [0, 1]], ["m\u00edstn\u00edch", "m\u00edstn\u00ed", "ADJ", [2, 10]], ["tepl\u00fdch", "tepl\u00fd", "ADJ", [11, 18]], ["a", "a", "CCONJ", [19, 20]], ["hlubok\u00fdch", "hlubok\u00fd", "ADJ", [21, 30]], ["mo\u0159\u00edch", "mo\u0159e", "NOUN", [31, 37]], ["je", "b\u00fdt", "AUX", [38, 40]], ["ryb", "ryba", "NOUN", [41, 44]], ["habad\u011bj", "habad\u011bj", "ADV", [45, 52]], [".", ".", "PUNCT", [52, 53]]]], ["calgarske-listy_2003_unor_ocr.txt", "Mus\u00ed b\u00fdt, proto\u017ee nen\u00ed t\u0159eba \u017e\u00e1dn\u00e9ho povolen\u00ed ani poplatku a to dokonce ani ne pro cizince, rybolov je zdarma a pos\u00e1dka sm\u00ed ryby prodat m\u00edstn\u00edm restaurac\u00edm, co\u017e v p\u0159\u00edpad\u011b \u00fasp\u011b\u0161n\u00e9ho lovu s radost\u00ed \u010din\u00ed.", [["Mus\u00ed", "muset", "VERB", [0, 4]], ["b\u00fdt", "b\u00fdt", "AUX", [5, 8]], [",", ",", "PUNCT", [8, 9]], ["proto\u017ee", "proto\u017ee", "SCONJ", [10, 17]], ["nen\u00ed", "b\u00fdt", "AUX", [18, 22]], ["t\u0159eba", "t\u0159eba", "ADV", [23, 28]], ["\u017e\u00e1dn\u00e9ho", "\u017e\u00e1dn\u00fd", "DET", [29, 36]], ["povolen\u00ed", "povolen\u00ed", "NOUN", [37, 45]], ["ani", "ani", "CCONJ", [46, 49]], ["poplatku", "poplatek", "NOUN", [50, 58]], ["a", "a", "CCONJ", [59, 60]], ["to", "to", "PART", [61, 63]], ["dokonce", "dokonce", "ADV", [64, 71]], ["ani", "ani", "CCONJ", [72, 75]], ["ne", "ne", "PART", [76, 78]], ["pro", "pro", "ADP", [79, 82]], ["cizince", "cizinec", "NOUN", [83, 90]], [",", ",", "PUNCT", [90, 91]], ["rybolov", "rybolov", "NOUN", [92, 99]], ["je", "b\u00fdt", "AUX", [100, 102]], ["zdarma", "zdarma", "ADV", [103, 109]], ["a", "a", "CCONJ", [110, 111]], ["pos\u00e1dka", "pos\u00e1dka", "NOUN", [112, 119]], ["sm\u00ed", "sm\u011bt", "VERB", [120, 123]], ["ryby", "ryba", "NOUN", [124, 128]], ["prodat", "prodat", "VERB", [129, 135]], ["m\u00edstn\u00edm", "m\u00edstn\u00ed", "ADJ", [136, 143]], ["restaurac\u00edm", "restaurace", "NOUN", [144, 155]], [",", ",", "PUNCT", [155, 156]], ["co\u017e", "co\u017e", "PRON", [157, 160]], ["v", "v", "ADP", [161, 162]], ["p\u0159\u00edpad\u011b", "p\u0159\u00edpad", "NOUN", [163, 170]], ["\u00fasp\u011b\u0161n\u00e9ho", "\u00fasp\u011b\u0161n\u00fd", "ADJ", [171, 180]], ["lovu", "lov", "NOUN", [181, 185]], ["s", "s", "ADP", [186, 187]], ["radost\u00ed", "radost", "NOUN", [188, 195]], ["\u010din\u00ed", "\u010dinit", "VERB", [196, 200]], [".", ".", "PUNCT", [200, 201]]]], ["calgarske-listy_2003_unor_ocr.txt", "V Kanad\u011b maj\u00ed podobn\u00e1 privilegia jenom Indi\u00e1ni a Eskym\u00e1ci.", [["V", "v", "ADP", [0, 1]], ["Kanad\u011b", "Kanada", "PROPN", [2, 8]], ["maj\u00ed", "m\u00edt", "VERB", [9, 13]], ["podobn\u00e1", "podobn\u00fd", "ADJ", [14, 21]], ["privilegia", "privilegium", "NOUN", [22, 32]], ["jenom", "jenom", "PART", [33, 38]], ["Indi\u00e1ni", "Indi\u00e1n", "PROPN", [39, 46]], ["a", "a", "CCONJ", [47, 48]], ["Eskym\u00e1ci", "Eskym\u00e1k", "PROPN", [49, 57]], [".", ".", "PUNCT", [57, 58]]]], ["calgarske-listy_2003_unor_ocr.txt", "Lov\u00ed se hlavn\u011b Mariin (mysl\u00edm, \u017ee jde o Me\u010douna, Swordfish, Xiphias Gladius, ale nejsem si jist), kter\u00fd nez\u0159\u00eddka dosahuje v\u00e1hy p\u0159es dva metr\u00e1ky, s rekordn\u00edmi \u00falovky k p\u011bti metr\u00e1k\u016fm, d\u00e1le delfinovit\u00e1 ryba Mahi Mahi ( Dorade, Bluefish, Coryphaena hippurus), dva druhy tu\u0148\u00e1k\u016f zvan\u00fdch m\u00edstn\u011b Aku (Skipjack tuna, Katsuwonus Pelamis) a Ahi ( Yellow fin tuna) a makrelovit\u00e1 ryba zvan\u00e1 Ono anebo Wahoo (Acanthocybium solandri), abych jmenoval ty nejroz\u0161\u00ed\u0159en\u011bj\u0161\u00ed.", [["Lov\u00ed", "lovit", "VERB", [0, 4]], ["se", "se", "PRON", [5, 7]], ["hlavn\u011b", "hlavn\u011b", "ADV", [8, 14]], ["Mariin", "Mariin", "PROPN", [15, 21]], ["(", "(", "PUNCT", [22, 23]], ["mysl\u00edm", "myslit", "VERB", [23, 29]], [",", ",", "PUNCT", [29, 30]], ["\u017ee", "\u017ee", "SCONJ", [31, 33]], ["jde", "j\u00edt", "VERB", [34, 37]], ["o", "o", "ADP", [38, 39]], ["Me\u010douna", "Me\u010doun", "PROPN", [40, 47]], [",", ",", "PUNCT", [47, 48]], ["Swordfish", "Swordfish", "PROPN", [49, 58]], [",", ",", "PUNCT", [58, 59]], ["Xiphias", "Xiphias", "PROPN", [60, 67]], ["Gladius", "Gladius", "PROPN", [68, 75]], [",", ",", "PUNCT", [75, 76]], ["ale", "ale", "CCONJ", [77, 80]], ["nejsem", "b\u00fdt", "AUX", [81, 87]], ["si", "se", "PRON", [88, 90]], ["jist", "jist\u00fd", "ADJ", [91, 95]], [")", ")", "PUNCT", [95, 96]], [",", ",", "PUNCT", [96, 97]], ["kter\u00fd", "kter\u00fd", "DET", [98, 103]], ["nez\u0159\u00eddka", "z\u0159\u00eddka", "ADV", [104, 112]], ["dosahuje", "dosahovat", "VERB", [113, 121]], ["v\u00e1hy", "v\u00e1ha", "NOUN", [122, 126]], ["p\u0159es", "p\u0159es", "ADP", [127, 131]], ["dva", "dva", "NUM", [132, 135]], ["metr\u00e1ky", "metr\u00e1k", "NOUN", [136, 143]], [",", ",", "PUNCT", [143, 144]], ["s", "s", "ADP", [145, 146]], ["rekordn\u00edmi", "rekordn\u00ed", "ADJ", [147, 157]], ["\u00falovky", "\u00falovek", "NOUN", [158, 164]], ["k", "k", "ADP", [165, 166]], ["p\u011bti", "p\u011bt", "NUM", [167, 171]], ["metr\u00e1k\u016fm", "metr\u00e1k", "NOUN", [172, 180]], [",", ",", "PUNCT", [180, 181]], ["d\u00e1le", "d\u00e1le", "ADV", [182, 186]], ["delfinovit\u00e1", "delfinovit\u00fd", "ADJ", [187, 198]], ["ryba", "ryba", "NOUN", [199, 203]], ["Mahi", "Mahi", "PROPN", [204, 208]], ["Mahi", "Mahi", "PROPN", [209, 213]], ["(", "(", "PUNCT", [214, 215]], ["Dorade", "Dorade", "PROPN", [216, 222]], [",", ",", "PUNCT", [222, 223]], ["Bluefish", "Bluefish", "PROPN", [224, 232]], [",", ",", "PUNCT", [232, 233]], ["Coryphaena", "Coryphaena", "PROPN", [234, 244]], ["hippurus", "hippurus", "X", [245, 253]], [")", ")", "PUNCT", [253, 254]], [",", ",", "PUNCT", [254, 255]], ["dva", "dva", "NUM", [256, 259]], ["druhy", "druh", "NOUN", [260, 265]], ["tu\u0148\u00e1k\u016f", "tu\u0148\u00e1k", "NOUN", [266, 272]], ["zvan\u00fdch", "zvan\u00fd", "ADJ", [273, 280]], ["m\u00edstn\u011b", "m\u00edstn\u011b", "ADV", [281, 287]], ["Aku", "ako", "NOUN", [288, 291]], ["(", "(", "PUNCT", [292, 293]], ["Skipjack", "Skipjack", "PROPN", [293, 301]], ["tuna", "tuna", "NOUN", [302, 306]], [",", ",", "PUNCT", [306, 307]], ["Katsuwonus", "Katsuwonus", "PROPN", [308, 318]], ["Pelamis", "Pelamis", "X", [319, 326]], [")", ")", "PUNCT", [326, 327]], ["a", "a", "CCONJ", [328, 329]], ["Ahi", "Ahi", "PROPN", [330, 333]], ["(", "(", "PUNCT", [334, 335]], ["Yellow", "Yellow", "X", [336, 342]], ["fin", "fin", "X", [343, 346]], ["tuna", "tuna", "X", [347, 351]], [")", ")", "PUNCT", [351, 352]], ["a", "a", "CCONJ", [353, 354]], ["makrelovit\u00e1", "makrelovit\u00fd", "ADJ", [355, 366]], ["ryba", "ryba", "NOUN", [367, 371]], ["zvan\u00e1", "zvan\u00fd", "ADJ", [372, 377]], ["Ono", "onen", "DET", [378, 381]], ["anebo", "anebo", "CCONJ", [382, 387]], ["Wahoo", "Wahoo", "PROPN", [388, 393]], ["(", "(", "PUNCT", [394, 395]], ["Acanthocybium", "Acanthocybium", "PROPN", [395, 408]], ["solandri", "solandri", "X", [409, 417]], [")", ")", "PUNCT", [417, 418]], [",", ",", "PUNCT", [418, 419]], ["aby", "aby", "SCONJ", [-10191, -10191]], ["bych", "b\u00fdt", "AUX", [-10191, -10191]], ["jmenoval", "jmenovat", "VERB", [426, 434]], ["ty", "ten", "DET", [435, 437]], ["nejroz\u0161\u00ed\u0159en\u011bj\u0161\u00ed", "roz\u0161\u00ed\u0159en\u00fd", "ADJ", [438, 453]], [".", ".", "PUNCT", [453, 454]]]], ["calgarske-listy_2003_unor_ocr.txt", "V\u00fdb\u011br ryb\u00e1\u0159sk\u00fdch chartern je pom\u011brn\u011b bohat\u00fd, na\u0161el jsem si je na Internetu a vytipoval ty nejvhodn\u011bj\u0161\u00ed ji\u017e n\u011bkolik t\u00fddn\u016f p\u0159edem a dva t\u00fddny p\u0159ed odjezdem ud\u011blal kone\u010dn\u00e9 rozhodnut\u00ed, vybral a objednal.", [["V\u00fdb\u011br", "v\u00fdb\u011br", "NOUN", [0, 5]], ["ryb\u00e1\u0159sk\u00fdch", "ryb\u00e1\u0159sk\u00fd", "ADJ", [6, 16]], ["chartern", "chartern", "NOUN", [17, 25]], ["je", "b\u00fdt", "AUX", [26, 28]], ["pom\u011brn\u011b", "pom\u011brn\u011b", "ADV", [29, 36]], ["bohat\u00fd", "bohat\u00fd", "ADJ", [37, 43]], [",", ",", "PUNCT", [43, 44]], ["na\u0161el", "naj\u00edt", "VERB", [45, 50]], ["jsem", "b\u00fdt", "AUX", [51, 55]], ["si", "se", "PRON", [56, 58]], ["je", "b\u00fdt", "AUX", [59, 61]], ["na", "na", "ADP", [62, 64]], ["Internetu", "internet", "PROPN", [65, 74]], ["a", "a", "CCONJ", [75, 76]], ["vytipoval", "vytipovat", "VERB", [77, 86]], ["ty", "ten", "DET", [87, 89]], ["nejvhodn\u011bj\u0161\u00ed", "vhodn\u00fd", "ADJ", [90, 102]], ["ji\u017e", "ji\u017e", "ADV", [103, 106]], ["n\u011bkolik", "n\u011bkolik", "DET", [107, 114]], ["t\u00fddn\u016f", "t\u00fdden", "NOUN", [115, 120]], ["p\u0159edem", "p\u0159edem", "ADV", [121, 127]], ["a", "a", "CCONJ", [128, 129]], ["dva", "dva", "NUM", [130, 133]], ["t\u00fddny", "t\u00fdden", "NOUN", [134, 139]], ["p\u0159ed", "p\u0159ed", "ADP", [140, 144]], ["odjezdem", "odjezd", "NOUN", [145, 153]], ["ud\u011blal", "ud\u011blat", "VERB", [154, 160]], ["kone\u010dn\u00e9", "kone\u010dn\u00fd", "ADJ", [161, 168]], ["rozhodnut\u00ed", "rozhodnut\u00ed", "NOUN", [169, 179]], [",", ",", "PUNCT", [179, 180]], ["vybral", "vybrat", "VERB", [181, 187]], ["a", "a", "CCONJ", [188, 189]], ["objednal", "objednat", "VERB", [190, 198]], [".", ".", "PUNCT", [198, 199]]]], ["calgarske-listy_2003_unor_ocr.txt", "Den p\u0159ed \u0160t\u011bdr\u00fdm dnem 2002 p\u0159ed v\u00fdchodem slunce zaj\u00ed\u017ed\u00edm do p\u0159\u00edstavu Lahaina, asi 45 km daleko od Kihei, kde z\u016fst\u00e1v\u00e1me.", [["Den", "den", "NOUN", [0, 3]], ["p\u0159ed", "p\u0159ed", "ADP", [4, 8]], ["\u0160t\u011bdr\u00fdm", "\u0161t\u011bdr\u00fd", "ADJ", [9, 16]], ["dnem", "den", "NOUN", [17, 21]], ["2002", "2002", "NUM", [22, 26]], ["p\u0159ed", "p\u0159ed", "ADP", [27, 31]], ["v\u00fdchodem", "v\u00fdchod", "NOUN", [32, 40]], ["slunce", "slunce", "NOUN", [41, 47]], ["zaj\u00ed\u017ed\u00edm", "zaj\u00ed\u017ed\u011bt", "VERB", [48, 56]], ["do", "do", "ADP", [57, 59]], ["p\u0159\u00edstavu", "p\u0159\u00edstav", "NOUN", [60, 68]], ["Lahaina", "Lahain", "PROPN", [69, 76]], [",", ",", "PUNCT", [76, 77]], ["asi", "asi", "PART", [78, 81]], ["45", "45", "NUM", [82, 84]], ["km", "kilometr", "NOUN", [85, 87]], ["daleko", "daleko", "ADV", [88, 94]], ["od", "od", "ADP", [95, 97]], ["Kihei", "Kihei", "PROPN", [98, 103]], [",", ",", "PUNCT", [103, 104]], ["kde", "kde", "ADV", [105, 108]], ["z\u016fst\u00e1v\u00e1me", "z\u016fst\u00e1vat", "VERB", [109, 118]], [".", ".", "PUNCT", [118, 119]]]], ["calgarske-listy_2003_unor_ocr.txt", "Kotv\u00ed zde \u0159ada ryb\u00e1\u0159sk\u00fdch \u010dlun\u016f, ned\u011bl\u00e1 mi obt\u00ed\u017ee nal\u00e9zt ten spr\u00e1vn\u00fd, Hinatea, kde m\u011b v\u00edt\u00e1 pos\u00e1dka Mark a Kevin.", [["Kotv\u00ed", "kotvit", "VERB", [0, 5]], ["zde", "zde", "ADV", [6, 9]], ["\u0159ada", "\u0159ada", "NOUN", [10, 14]], ["ryb\u00e1\u0159sk\u00fdch", "ryb\u00e1\u0159sk\u00fd", "ADJ", [15, 25]], ["\u010dlun\u016f", "\u010dlun", "NOUN", [26, 31]], [",", ",", "PUNCT", [31, 32]], ["ned\u011bl\u00e1", "d\u011blat", "VERB", [33, 39]], ["mi", "j\u00e1", "PRON", [40, 42]], ["obt\u00ed\u017ee", "obt\u00ed\u017e", "NOUN", [43, 49]], ["nal\u00e9zt", "naleznout", "VERB", [50, 56]], ["ten", "ten", "DET", [57, 60]], ["spr\u00e1vn\u00fd", "spr\u00e1vn\u00fd", "ADJ", [61, 68]], [",", ",", "PUNCT", [68, 69]], ["Hinatea", "Hinatea", "PROPN", [70, 77]], [",", ",", "PUNCT", [77, 78]], ["kde", "kde", "ADV", [79, 82]], ["m\u011b", "j\u00e1", "PRON", [83, 85]], ["v\u00edt\u00e1", "v\u00edtat", "VERB", [86, 90]], ["pos\u00e1dka", "pos\u00e1dka", "NOUN", [91, 98]], ["Mark", "Mark", "PROPN", [99, 103]], ["a", "a", "CCONJ", [104, 105]], ["Kevin", "Kevin", "PROPN", [106, 111]], [".", ".", "PUNCT", [111, 112]]]], ["calgarske-listy_2003_unor_ocr.txt", "\u010clun m\u00e1 42 stop, je solidn\u011b stav\u011bn\u00fd a dob\u0159e udr\u017eovan\u00fd, i kdy\u017e na designu a \u0159ad\u011b detail\u016f je vid\u011bt, \u017ee u\u017e br\u00e1zd\u00ed m\u00edstn\u00ed vody p\u0159es 40 let.", [["\u010clun", "\u010dlun", "NOUN", [0, 4]], ["m\u00e1", "m\u00edt", "VERB", [5, 7]], ["42", "42", "NUM", [8, 10]], ["stop", "stopa", "NOUN", [11, 15]], [",", ",", "PUNCT", [15, 16]], ["je", "b\u00fdt", "AUX", [17, 19]], ["solidn\u011b", "solidn\u011b", "ADV", [20, 27]], ["stav\u011bn\u00fd", "stav\u011bn\u00fd", "ADJ", [28, 35]], ["a", "a", "CCONJ", [36, 37]], ["dob\u0159e", "dob\u0159e", "ADV", [38, 43]], ["udr\u017eovan\u00fd", "udr\u017eovan\u00fd", "ADJ", [44, 53]], [",", ",", "PUNCT", [53, 54]], ["i", "i", "CCONJ", [55, 56]], ["kdy\u017e", "kdy\u017e", "SCONJ", [57, 61]], ["na", "na", "ADP", [62, 64]], ["designu", "design", "NOUN", [65, 72]], ["a", "a", "CCONJ", [73, 74]], ["\u0159ad\u011b", "\u0159ada", "NOUN", [75, 79]], ["detail\u016f", "detail", "NOUN", [80, 87]], ["je", "b\u00fdt", "AUX", [88, 90]], ["vid\u011bt", "vid\u011bt", "VERB", [91, 96]], [",", ",", "PUNCT", [96, 97]], ["\u017ee", "\u017ee", "SCONJ", [98, 100]], ["u\u017e", "u\u017e", "ADV", [101, 103]], ["br\u00e1zd\u00ed", "br\u00e1zdit", "VERB", [104, 110]], ["m\u00edstn\u00ed", "m\u00edstn\u00ed", "ADJ", [111, 117]], ["vody", "voda", "NOUN", [118, 122]], ["p\u0159es", "p\u0159es", "ADP", [123, 127]], ["40", "40", "NUM", [128, 130]], ["let", "l\u00e9ta", "NOUN", [131, 134]], [".", ".", "PUNCT", [134, 135]]]], ["calgarske-listy_2003_unor_ocr.txt", "Je uzp\u016fsoben tak, \u017ee m\u016f\u017ee pojmout a\u017e osm z\u00e1kazn\u00edk\u016f, z nich\u017e \u010dty\u0159i a\u017e \u0161est m\u016f\u017ee chytat sou\u010dasn\u011b, z\u00e1le\u017e\u00ed na typu rybolovu.", [["Je", "b\u00fdt", "AUX", [0, 2]], ["uzp\u016fsoben", "uzp\u016fsoben\u00fd", "ADJ", [3, 12]], ["tak", "tak", "ADV", [13, 16]], [",", ",", "PUNCT", [16, 17]], ["\u017ee", "\u017ee", "SCONJ", [18, 20]], ["m\u016f\u017ee", "moci", "VERB", [21, 25]], ["pojmout", "pojmout", "VERB", [26, 33]], ["a\u017e", "a\u017e", "PART", [34, 36]], ["osm", "osm", "NUM", [37, 40]], ["z\u00e1kazn\u00edk\u016f", "z\u00e1kazn\u00edk", "NOUN", [41, 50]], [",", ",", "PUNCT", [50, 51]], ["z", "z", "ADP", [52, 53]], ["nich\u017e", "jen\u017e", "PRON", [54, 59]], ["\u010dty\u0159i", "\u010dty\u0159i", "NUM", [60, 65]], ["a\u017e", "a\u017e", "CCONJ", [66, 68]], ["\u0161est", "\u0161est", "NUM", [69, 73]], ["m\u016f\u017ee", "moci", "VERB", [74, 78]], ["chytat", "chytat", "VERB", [79, 85]], ["sou\u010dasn\u011b", "sou\u010dasn\u011b", "ADV", [86, 94]], [",", ",", "PUNCT", [94, 95]], ["z\u00e1le\u017e\u00ed", "z\u00e1le\u017eet", "VERB", [96, 102]], ["na", "na", "ADP", [103, 105]], ["typu", "typ", "NOUN", [106, 110]], ["rybolovu", "rybolov", "NOUN", [111, 119]], [".", ".", "PUNCT", [119, 120]]]], ["calgarske-listy_2003_unor_ocr.txt", "Se mnou je tam tento den pouze je\u0161t\u011b otec s dosp\u011bl\u00fdm synem odkudsi z Nevady.", [["Se", "s", "ADP", [0, 2]], ["mnou", "j\u00e1", "PRON", [3, 7]], ["je", "b\u00fdt", "AUX", [8, 10]], ["tam", "tam", "ADV", [11, 14]], ["tento", "tento", "DET", [15, 20]], ["den", "den", "NOUN", [21, 24]], ["pouze", "pouze", "ADV", [25, 30]], ["je\u0161t\u011b", "je\u0161t\u011b", "ADV", [31, 36]], ["otec", "otec", "NOUN", [37, 41]], ["s", "s", "ADP", [42, 43]], ["dosp\u011bl\u00fdm", "dosp\u011bl\u00fd", "ADJ", [44, 52]], ["synem", "syn", "NOUN", [53, 58]], ["odkudsi", "odkuds", "NOUN", [59, 66]], ["z", "z", "ADP", [67, 68]], ["Nevady", "Nevada", "PROPN", [69, 75]], [".", ".", "PUNCT", [75, 76]]]], ["calgarske-listy_2003_unor_ocr.txt", "D\u00e1v\u00e1me se do \u0159e\u010di a libujeme si, \u017ee je n\u00e1s tak m\u00e1lo a v\u0161ichni se t\u0159eseme na to, jak si zaryba\u0159\u00edme.", [["D\u00e1v\u00e1me", "d\u00e1vat", "VERB", [0, 6]], ["se", "se", "PRON", [7, 9]], ["do", "do", "ADP", [10, 12]], ["\u0159e\u010di", "\u0159e\u010d", "NOUN", [13, 17]], ["a", "a", "CCONJ", [18, 19]], ["libujeme", "libovat", "VERB", [20, 28]], ["si", "se", "PRON", [29, 31]], [",", ",", "PUNCT", [31, 32]], ["\u017ee", "\u017ee", "SCONJ", [33, 35]], ["je", "b\u00fdt", "AUX", [36, 38]], ["n\u00e1s", "my", "PRON", [39, 42]], ["tak", "tak", "ADV", [43, 46]], ["m\u00e1lo", "m\u00e1lo", "DET", [47, 51]], ["a", "a", "CCONJ", [52, 53]], ["v\u0161ichni", "v\u0161echen", "DET", [54, 61]], ["se", "se", "PRON", [62, 64]], ["t\u0159eseme", "t\u0159\u00e1st", "VERB", [65, 72]], ["na", "na", "ADP", [73, 75]], ["to", "ten", "DET", [76, 78]], [",", ",", "PUNCT", [78, 79]], ["jak", "jak", "ADV", [80, 83]], ["si", "se", "PRON", [84, 86]], ["zaryba\u0159\u00edme", "zaryba\u0159it", "VERB", [87, 97]], [".", ".", "PUNCT", [97, 98]]]], ["calgarske-listy_2003_unor_ocr.txt", "Hned p\u0159i vstupu na lo\u010f upout\u00e1v\u00e1 moji pozornost ryb\u00e1\u0159sk\u00e9 n\u00e1dob\u00ed\u010dko.", [["Hned", "hned", "ADV", [0, 4]], ["p\u0159i", "p\u0159i", "ADP", [5, 8]], ["vstupu", "vstup", "NOUN", [9, 15]], ["na", "na", "ADP", [16, 18]], ["lo\u010f", "lo\u010f", "NOUN", [19, 22]], ["upout\u00e1v\u00e1", "upout\u00e1vat", "VERB", [23, 31]], ["moji", "m\u016fj", "DET", [32, 36]], ["pozornost", "pozornost", "NOUN", [37, 46]], ["ryb\u00e1\u0159sk\u00e9", "ryb\u00e1\u0159sk\u00fd", "ADJ", [47, 55]], ["n\u00e1dob\u00ed\u010dko", "n\u00e1dob\u00ed\u010dko", "NOUN", [56, 65]], [".", ".", "PUNCT", [65, 66]]]], ["calgarske-listy_2003_unor_ocr.txt", "Kr\u00e1tk\u00e9 masivn\u00ed pruty s je\u0161t\u011b masivn\u011bj\u0161\u00edmi navij\u00e1ky o pr\u016fm\u011bru p\u0159es 20 cm se silonov\u00fdm filamentem o p\u016fm\u011bru dvou milimetr\u016f.", [["Kr\u00e1tk\u00e9", "kr\u00e1tk\u00fd", "ADJ", [0, 6]], ["masivn\u00ed", "masivn\u00ed", "ADJ", [7, 14]], ["pruty", "prut", "NOUN", [15, 20]], ["s", "s", "ADP", [21, 22]], ["je\u0161t\u011b", "je\u0161t\u011b", "ADV", [23, 28]], ["masivn\u011bj\u0161\u00edmi", "masivn\u00ed", "ADJ", [29, 41]], ["navij\u00e1ky", "navij\u00e1k", "NOUN", [42, 50]], ["o", "o", "ADP", [51, 52]], ["pr\u016fm\u011bru", "pr\u016fm\u011br", "NOUN", [53, 60]], ["p\u0159es", "p\u0159es", "ADP", [61, 65]], ["20", "20", "NUM", [66, 68]], ["cm", "centimetr", "NOUN", [69, 71]], ["se", "s", "ADP", [72, 74]], ["silonov\u00fdm", "silonov\u00fd", "ADJ", [75, 84]], ["filamentem", "filament", "NOUN", [85, 95]], ["o", "o", "ADP", [96, 97]], ["p\u016fm\u011bru", "p\u016fm\u011bra", "NOUN", [98, 104]], ["dvou", "dva", "NUM", [105, 109]], ["milimetr\u016f", "milimetr", "NOUN", [110, 119]], [".", ".", "PUNCT", [119, 120]]]], ["calgarske-listy_2003_unor_ocr.txt", "Nikdy jsem je\u0161t\u011b s podobn\u00fdmi nechytal.", [["Nikdy", "nikdy", "ADV", [0, 5]], ["jsem", "b\u00fdt", "AUX", [6, 10]], ["je\u0161t\u011b", "je\u0161t\u011b", "ADV", [11, 16]], ["s", "s", "ADP", [17, 18]], ["podobn\u00fdmi", "podobn\u00fd", "ADJ", [19, 28]], ["nechytal", "chytat", "VERB", [29, 37]], [".", ".", "PUNCT", [37, 38]]]], ["calgarske-listy_2003_unor_ocr.txt", "Pruty jsou nav\u00edc ji\u0161t\u011bny silonov\u00fdm lanem k ocelov\u00fdm ok\u016fm p\u0159ikovan\u00fdm k podlaze \u010dlunu.", [["Pruty", "prut", "NOUN", [0, 5]], ["jsou", "b\u00fdt", "AUX", [6, 10]], ["nav\u00edc", "nav\u00edc", "ADV", [11, 16]], ["ji\u0161t\u011bny", "ji\u0161t\u011bn\u00fd", "ADJ", [17, 24]], ["silonov\u00fdm", "silonov\u00fd", "ADJ", [25, 34]], ["lanem", "lano", "NOUN", [35, 40]], ["k", "k", "ADP", [41, 42]], ["ocelov\u00fdm", "ocelov\u00fd", "ADJ", [43, 51]], ["ok\u016fm", "oko", "NOUN", [52, 56]], ["p\u0159ikovan\u00fdm", "p\u0159ikovan\u00fd", "ADJ", [57, 67]], ["k", "k", "ADP", [68, 69]], ["podlaze", "podlaha", "NOUN", [70, 77]], ["\u010dlunu", "\u010dlun", "NOUN", [78, 83]], [".", ".", "PUNCT", [83, 84]]]], ["calgarske-listy_2003_unor_ocr.txt", "\u00dapln\u011b chyb\u00ed za\u0159\u00edzen\u00ed zvan\u00e9 downrigger (jak pak se to asi \u0159ekne \u010desky??), kter\u00e9 m\u00e1 za \u00fakol p\u0159i trolov\u00e1n\u00ed udr\u017eet n\u00e1vnadu ve zvolen\u00e9 hloubce a\u017e do cca 100 metr\u016f.", [["\u00dapln\u011b", "\u00fapln\u011b", "ADV", [0, 5]], ["chyb\u00ed", "chyb\u011bt", "VERB", [6, 11]], ["za\u0159\u00edzen\u00ed", "za\u0159\u00edzen\u00ed", "NOUN", [12, 20]], ["zvan\u00e9", "zvan\u00fd", "ADJ", [21, 26]], ["downrigger", "downrigger", "NOUN", [27, 37]], ["(", "(", "PUNCT", [38, 39]], ["jak", "jak", "ADV", [39, 42]], ["pak", "pak", "ADV", [43, 46]], ["se", "se", "PRON", [47, 49]], ["to", "ten", "DET", [50, 52]], ["asi", "asi", "PART", [53, 56]], ["\u0159ekne", "\u0159\u00edci", "VERB", [57, 62]], ["\u010desky", "\u010desky", "ADV", [63, 68]], ["?", "?", "PUNCT", [68, 69]], ["?", "?", "PUNCT", [69, 70]], [")", ")", "PUNCT", [70, 71]], [",", ",", "PUNCT", [71, 72]], ["kter\u00e9", "kter\u00fd", "DET", [73, 78]], ["m\u00e1", "m\u00edt", "VERB", [79, 81]], ["za", "za", "ADP", [82, 84]], ["\u00fakol", "\u00fakol", "NOUN", [85, 89]], ["p\u0159i", "p\u0159i", "ADP", [90, 93]], ["trolov\u00e1n\u00ed", "trolov\u00e1n\u00ed", "NOUN", [94, 103]], ["udr\u017eet", "udr\u017eet", "VERB", [104, 110]], ["n\u00e1vnadu", "n\u00e1vnada", "NOUN", [111, 118]], ["ve", "v", "ADP", [119, 121]], ["zvolen\u00e9", "zvolen\u00fd", "ADJ", [122, 129]], ["hloubce", "hloubka", "NOUN", [130, 137]], ["a\u017e", "a\u017e", "PART", [138, 140]], ["do", "do", "ADP", [141, 143]], ["cca", "cirka", "ADV", [144, 147]], ["100", "100", "NUM", [148, 151]], ["metr\u016f", "metr", "NOUN", [152, 157]], [".", ".", "PUNCT", [157, 158]]]], ["calgarske-listy_2003_unor_ocr.txt", "Brzy vid\u00edm pro\u010d, troluje se pouze na povrchu, a to nezvykle vysokou rychlost\u00ed sedmi a p\u016fl uzlu za hodinu.", [["Brzy", "brzy", "ADV", [0, 4]], ["vid\u00edm", "vid\u011bt", "VERB", [5, 10]], ["pro\u010d", "pro\u010d", "ADV", [11, 15]], [",", ",", "PUNCT", [15, 16]], ["troluje", "trolovat", "VERB", [17, 24]], ["se", "se", "PRON", [25, 27]], ["pouze", "pouze", "ADV", [28, 33]], ["na", "na", "ADP", [34, 36]], ["povrchu", "povrch", "NOUN", [37, 44]], [",", ",", "PUNCT", [44, 45]], ["a", "a", "CCONJ", [46, 47]], ["to", "to", "PART", [48, 50]], ["nezvykle", "nezvykle", "ADV", [51, 59]], ["vysokou", "vysok\u00fd", "ADJ", [60, 67]], ["rychlost\u00ed", "rychlost", "NOUN", [68, 77]], ["sedmi", "sedm", "NUM", [78, 83]], ["a", "a", "CCONJ", [84, 85]], ["p\u016fl", "p\u016fl", "NUM", [86, 89]], ["uzlu", "uzel", "NOUN", [90, 94]], ["za", "za", "ADP", [95, 97]], ["hodinu", "hodina", "NOUN", [98, 104]], [".", ".", "PUNCT", [104, 105]]]], ["calgarske-listy_2003_unor_ocr.txt", "P\u0159i lovu losos\u016f nikdy netrolujeme rychleji ne\u017e dva uzle, zpravidla je\u0161t\u011b pomaleji.", [["P\u0159i", "p\u0159i", "ADP", [0, 3]], ["lovu", "lov", "NOUN", [4, 8]], ["losos\u016f", "losos", "NOUN", [9, 15]], ["nikdy", "nikdy", "ADV", [16, 21]], ["netrolujeme", "trolovat", "VERB", [22, 33]], ["rychleji", "rychle", "ADV", [34, 42]], ["ne\u017e", "ne\u017e", "SCONJ", [43, 46]], ["dva", "dva", "NUM", [47, 50]], ["uzle", "uzle", "NOUN", [51, 55]], [",", ",", "PUNCT", [55, 56]], ["zpravidla", "zpravidla", "ADV", [57, 66]], ["je\u0161t\u011b", "je\u0161t\u011b", "ADV", [67, 72]], ["pomaleji", "pomalu", "ADV", [73, 81]], [".", ".", "PUNCT", [81, 82]]]], ["calgarske-listy_2003_unor_ocr.txt", "Uvelebujeme se v pohodln\u00e9 a prostorn\u00e9 kajut\u011b a Mark n\u00e1m hned p\u0159ekl\u00e1d\u00e1 dv\u011b rozs\u00e1hl\u00e1 pon\u011bkud ohmatan\u00e1 alba s mno\u017estv\u00edm fotografi\u00ed ryb\u00edch trofej\u00ed v\u0161ech mo\u017en\u00fdch velikost\u00ed, v\u010detn\u011b pat\u0159i\u010dn\u011b rozesm\u00e1t\u00fdch a v\u016fbec dob\u0159e nalad\u011bn\u00fdch pos\u00e1dek.", [["Uvelebujeme", "uvelebovat", "VERB", [0, 11]], ["se", "se", "PRON", [12, 14]], ["v", "v", "ADP", [15, 16]], ["pohodln\u00e9", "pohodln\u00fd", "ADJ", [17, 25]], ["a", "a", "CCONJ", [26, 27]], ["prostorn\u00e9", "prostorn\u00fd", "ADJ", [28, 37]], ["kajut\u011b", "kajuta", "NOUN", [38, 44]], ["a", "a", "CCONJ", [45, 46]], ["Mark", "Mark", "PROPN", [47, 51]], ["n\u00e1m", "my", "PRON", [52, 55]], ["hned", "hned", "ADV", [56, 60]], ["p\u0159ekl\u00e1d\u00e1", "p\u0159ekl\u00e1dat", "VERB", [61, 69]], ["dv\u011b", "dva", "NUM", [70, 73]], ["rozs\u00e1hl\u00e1", "rozs\u00e1hl\u00fd", "ADJ", [74, 82]], ["pon\u011bkud", "pon\u011bkud", "ADV", [83, 90]], ["ohmatan\u00e1", "ohmatan\u00fd", "ADJ", [91, 99]], ["alba", "album", "NOUN", [100, 104]], ["s", "s", "ADP", [105, 106]], ["mno\u017estv\u00edm", "mno\u017estv\u00ed", "NOUN", [107, 116]], ["fotografi\u00ed", "fotografie", "NOUN", [117, 127]], ["ryb\u00edch", "ryb\u00ed", "ADJ", [128, 134]], ["trofej\u00ed", "trofej", "NOUN", [135, 142]], ["v\u0161ech", "v\u0161echen", "DET", [143, 148]], ["mo\u017en\u00fdch", "mo\u017en\u00fd", "ADJ", [149, 156]], ["velikost\u00ed", "velikost", "NOUN", [157, 166]], [",", ",", "PUNCT", [166, 167]], ["v\u010detn\u011b", "v\u010detn\u011b", "ADP", [168, 174]], ["pat\u0159i\u010dn\u011b", "pat\u0159i\u010dn\u011b", "ADV", [175, 183]], ["rozesm\u00e1t\u00fdch", "rozesm\u00e1t\u00fd", "ADJ", [184, 195]], ["a", "a", "CCONJ", [196, 197]], ["v\u016fbec", "v\u016fbec", "PART", [198, 203]], ["dob\u0159e", "dob\u0159e", "ADV", [204, 209]], ["nalad\u011bn\u00fdch", "nalad\u011bn\u00fd", "ADJ", [210, 220]], ["pos\u00e1dek", "pos\u00e1dka", "NOUN", [221, 228]], [".", ".", "PUNCT", [228, 229]]]], ["calgarske-listy_2003_unor_ocr.txt", "Nejl\u00e9pe se na fotografi\u00edch vyj\u00edmaj\u00ed n\u011bkolikametrov\u00ed Marlinov\u00e9 vis\u00edc\u00ed na \u0159et\u011bzu z je\u0159\u00e1bu hlavou dol\u016f, s tabulkou uv\u00e1d\u011bj\u00edc\u00ed d\u00e9lku ryby a jej\u00ed v\u00e1hu p\u0159ipevn\u011bnou k ocasu.", [["Nejl\u00e9pe", "l\u00e9pe", "ADV", [0, 7]], ["se", "se", "PRON", [8, 10]], ["na", "na", "ADP", [11, 13]], ["fotografi\u00edch", "fotografie", "NOUN", [14, 26]], ["vyj\u00edmaj\u00ed", "vyj\u00edmat", "VERB", [27, 35]], ["n\u011bkolikametrov\u00ed", "n\u011bkolikametrov\u00fd", "ADJ", [36, 51]], ["Marlinov\u00e9", "Marlin", "PROPN", [52, 61]], ["vis\u00edc\u00ed", "vis\u00edc\u00ed", "ADJ", [62, 68]], ["na", "na", "ADP", [69, 71]], ["\u0159et\u011bzu", "\u0159et\u011bz", "NOUN", [72, 78]], ["z", "z", "ADP", [79, 80]], ["je\u0159\u00e1bu", "je\u0159\u00e1b", "NOUN", [81, 87]], ["hlavou", "hlava", "NOUN", [88, 94]], ["dol\u016f", "dol\u016f", "ADV", [95, 99]], [",", ",", "PUNCT", [99, 100]], ["s", "s", "ADP", [101, 102]], ["tabulkou", "tabulka", "NOUN", [103, 111]], ["uv\u00e1d\u011bj\u00edc\u00ed", "uv\u00e1d\u011bj\u00edc\u00ed", "ADJ", [112, 121]], ["d\u00e9lku", "d\u00e9lka", "NOUN", [122, 127]], ["ryby", "ryba", "NOUN", [128, 132]], ["a", "a", "CCONJ", [133, 134]], ["jej\u00ed", "jeho", "DET", [135, 139]], ["v\u00e1hu", "v\u00e1ha", "NOUN", [140, 144]], ["p\u0159ipevn\u011bnou", "p\u0159ipevn\u011bn\u00fd", "ADJ", [145, 156]], ["k", "k", "ADP", [157, 158]], ["ocasu", "ocas", "NOUN", [159, 164]], [".", ".", "PUNCT", [164, 165]]]], ["calgarske-listy_2003_unor_ocr.txt", "Je to dobr\u00e1 propaganda na za\u010d\u00e1tek, na\u0161e fotografie ov\u0161em nakonec album neobohatila, proto\u017ee ta na\u0161e hrom\u00e1dka p\u016flkilov\u00fdch a\u017e kilov\u00fdch ahi by jist\u011b moc sl\u00e1vy pos\u00e1dce a jej\u00ed lodi nep\u0159inesla...", [["Je", "b\u00fdt", "AUX", [0, 2]], ["to", "ten", "DET", [3, 5]], ["dobr\u00e1", "dobr\u00fd", "ADJ", [6, 11]], ["propaganda", "propaganda", "NOUN", [12, 22]], ["na", "na", "ADP", [23, 25]], ["za\u010d\u00e1tek", "za\u010d\u00e1tek", "NOUN", [26, 33]], [",", ",", "PUNCT", [33, 34]], ["na\u0161e", "n\u00e1\u0161", "DET", [35, 39]], ["fotografie", "fotografie", "NOUN", [40, 50]], ["ov\u0161em", "ov\u0161em", "PART", [51, 56]], ["nakonec", "nakonec", "ADV", [57, 64]], ["album", "album", "NOUN", [65, 70]], ["neobohatila", "obohatit", "VERB", [71, 82]], [",", ",", "PUNCT", [82, 83]], ["proto\u017ee", "proto\u017ee", "SCONJ", [84, 91]], ["ta", "ten", "DET", [92, 94]], ["na\u0161e", "n\u00e1\u0161", "DET", [95, 99]], ["hrom\u00e1dka", "hrom\u00e1dka", "NOUN", [100, 108]], ["p\u016flkilov\u00fdch", "p\u016flkilov\u00fd", "ADJ", [109, 120]], ["a\u017e", "a\u017e", "CCONJ", [121, 123]], ["kilov\u00fdch", "kilov\u00fd", "ADJ", [124, 132]], ["ahi", "ahi", "NOUN", [133, 136]], ["by", "b\u00fdt", "AUX", [137, 139]], ["jist\u011b", "jist\u011b", "ADV", [140, 145]], ["moc", "moc", "ADV", [146, 149]], ["sl\u00e1vy", "sl\u00e1va", "NOUN", [150, 155]], ["pos\u00e1dce", "pos\u00e1dka", "NOUN", [156, 163]], ["a", "a", "CCONJ", [164, 165]], ["jej\u00ed", "jeho", "DET", [166, 170]], ["lodi", "lo\u010f", "NOUN", [171, 175]], ["nep\u0159inesla", "p\u0159in\u00e9st", "VERB", [176, 186]], [".", ".", "PUNCT", [186, 187]], [".", ".", "PUNCT", [187, 188]], [".", ".", "PUNCT", [188, 189]]]], ["calgarske-listy_2003_unor_ocr.txt", "Ale abych nep\u0159edb\u00edhal.", [["Ale", "ale", "CCONJ", [0, 3]], ["aby", "aby", "SCONJ", [-12758, -12758]], ["bych", "b\u00fdt", "AUX", [-12758, -12758]], ["nep\u0159edb\u00edhal", "p\u0159edb\u00edhat", "VERB", [10, 21]], [".", ".", "PUNCT", [21, 22]]]], ["calgarske-listy_2003_unor_ocr.txt", "Kdy\u017e asi po t\u0159i \u010dtvrt\u011b hodin\u00e1ch plavby za\u010d\u00edn\u00e1me chytat, tak m\u011b hned od po\u010d\u00e1tku vad\u00ed, \u017ee m\u016fj p\u0159\u00ednos je zminimalizov\u00e1n na p\u0159ita\u017een\u00ed ryby k lodi.", [["Kdy\u017e", "kdy\u017e", "SCONJ", [0, 4]], ["asi", "asi", "PART", [5, 8]], ["po", "po", "ADP", [9, 11]], ["t\u0159i", "t\u0159i", "NUM", [12, 15]], ["\u010dtvrt\u011b", "\u010dtvrt", "NUM", [16, 22]], ["hodin\u00e1ch", "hodina", "NOUN", [23, 31]], ["plavby", "plavba", "NOUN", [32, 38]], ["za\u010d\u00edn\u00e1me", "za\u010d\u00ednat", "VERB", [39, 47]], ["chytat", "chytat", "VERB", [48, 54]], [",", ",", "PUNCT", [54, 55]], ["tak", "tak", "ADV", [56, 59]], ["m\u011b", "j\u00e1", "PRON", [60, 62]], ["hned", "hned", "ADV", [63, 67]], ["od", "od", "ADP", [68, 70]], ["po\u010d\u00e1tku", "po\u010d\u00e1tek", "NOUN", [71, 78]], ["vad\u00ed", "vadit", "VERB", [79, 83]], [",", ",", "PUNCT", [83, 84]], ["\u017ee", "\u017ee", "SCONJ", [85, 87]], ["m\u016fj", "m\u016fj", "DET", [88, 91]], ["p\u0159\u00ednos", "p\u0159\u00ednos", "NOUN", [92, 98]], ["je", "b\u00fdt", "AUX", [99, 101]], ["zminimalizov\u00e1n", "zminimalizovan\u00fd", "ADJ", [102, 116]], ["na", "na", "ADP", [117, 119]], ["p\u0159ita\u017een\u00ed", "p\u0159ita\u017een\u00ed", "NOUN", [120, 129]], ["ryby", "ryba", "NOUN", [130, 134]], ["k", "k", "ADP", [135, 136]], ["lodi", "lo\u010f", "NOUN", [137, 141]], [".", ".", "PUNCT", [141, 142]]]], ["calgarske-listy_2003_unor_ocr.txt", "P\u0159\u00edpravu prutu, zaseknut\u00ed a kone\u010dn\u00e9 vyta\u017een\u00ed na palubu d\u011bl\u00e1 v\u017edy jeden ze \u010dlen\u016f pos\u00e1dky.", [["P\u0159\u00edpravu", "p\u0159\u00edprava", "NOUN", [0, 8]], ["prutu", "prut", "NOUN", [9, 14]], [",", ",", "PUNCT", [14, 15]], ["zaseknut\u00ed", "zaseknut\u00ed", "NOUN", [16, 25]], ["a", "a", "CCONJ", [26, 27]], ["kone\u010dn\u00e9", "kone\u010dn\u00fd", "ADJ", [28, 35]], ["vyta\u017een\u00ed", "vyta\u017een\u00ed", "NOUN", [36, 44]], ["na", "na", "ADP", [45, 47]], ["palubu", "paluba", "NOUN", [48, 54]], ["d\u011bl\u00e1", "d\u011blat", "VERB", [55, 59]], ["v\u017edy", "v\u017edy", "ADV", [60, 64]], ["jeden", "jeden", "NUM", [65, 70]], ["ze", "z", "ADP", [71, 73]], ["\u010dlen\u016f", "\u010dlen", "NOUN", [74, 79]], ["pos\u00e1dky", "pos\u00e1dka", "NOUN", [80, 87]], [".", ".", "PUNCT", [87, 88]]]], ["calgarske-listy_2003_unor_ocr.txt", "P\u0159ipou\u0161t\u00edm \u017ee s rutinou a eleganc\u00ed, kter\u00e9 bych se nemohl p\u0159ibl\u00ed\u017eit.", [["P\u0159ipou\u0161t\u00edm", "p\u0159ipou\u0161t\u011bt", "VERB", [0, 10]], ["\u017ee", "\u017ee", "SCONJ", [11, 13]], ["s", "s", "ADP", [14, 15]], ["rutinou", "rutina", "NOUN", [16, 23]], ["a", "a", "CCONJ", [24, 25]], ["eleganc\u00ed", "elegance", "NOUN", [26, 34]], [",", ",", "PUNCT", [34, 35]], ["kter\u00e9", "kter\u00fd", "DET", [36, 41]], ["bych", "b\u00fdt", "AUX", [42, 46]], ["se", "se", "PRON", [47, 49]], ["nemohl", "moci", "VERB", [50, 56]], ["p\u0159ibl\u00ed\u017eit", "p\u0159ibl\u00ed\u017eit", "VERB", [57, 66]], [".", ".", "PUNCT", [66, 67]]]], ["calgarske-listy_2003_unor_ocr.txt", "Ale toto nen\u00ed z\u00e1\u017eitek, za kter\u00fd jsem ochoten zaplatit ten nemal\u00fd pen\u00edz a pro kter\u00fd se pou\u0161t\u00edm na mo\u0159e.", [["Ale", "ale", "CCONJ", [0, 3]], ["toto", "tento", "DET", [4, 8]], ["nen\u00ed", "b\u00fdt", "AUX", [9, 13]], ["z\u00e1\u017eitek", "z\u00e1\u017eitek", "NOUN", [14, 21]], [",", ",", "PUNCT", [21, 22]], ["za", "za", "ADP", [23, 25]], ["kter\u00fd", "kter\u00fd", "DET", [26, 31]], ["jsem", "b\u00fdt", "AUX", [32, 36]], ["ochoten", "ochotn\u00fd", "ADJ", [37, 44]], ["zaplatit", "zaplatit", "VERB", [45, 53]], ["ten", "ten", "DET", [54, 57]], ["nemal\u00fd", "mal\u00fd", "ADJ", [58, 64]], ["pen\u00edz", "pen\u00edz", "NOUN", [65, 70]], ["a", "a", "CCONJ", [71, 72]], ["pro", "pro", "ADP", [73, 76]], ["kter\u00fd", "kter\u00fd", "DET", [77, 82]], ["se", "se", "PRON", [83, 85]], ["pou\u0161t\u00edm", "pou\u0161t\u011bt", "VERB", [86, 93]], ["na", "na", "ADP", [94, 96]], ["mo\u0159e", "mo\u0159e", "NOUN", [97, 101]], [".", ".", "PUNCT", [101, 102]]]], ["calgarske-listy_2003_unor_ocr.txt", "Navij\u00e1ky jsou se\u0159\u00edzeny tak, abych se jich ani nedotkl.", [["Navij\u00e1ky", "navij\u00e1k", "NOUN", [0, 8]], ["jsou", "b\u00fdt", "AUX", [9, 13]], ["se\u0159\u00edzeny", "se\u0159\u00edzen\u00fd", "ADJ", [14, 22]], ["tak", "tak", "ADV", [23, 26]], [",", ",", "PUNCT", [26, 27]], ["aby", "aby", "SCONJ", [-13184, -13184]], ["bych", "b\u00fdt", "AUX", [-13184, -13184]], ["se", "se", "PRON", [34, 36]], ["jich", "on", "PRON", [37, 41]], ["ani", "ani", "CCONJ", [42, 45]], ["nedotkl", "dotknout", "VERB", [46, 53]], [".", ".", "PUNCT", [53, 54]]]], ["calgarske-listy_2003_unor_ocr.txt", "Dvakr\u00e1t nebo t\u0159ikr\u00e1t, kdy\u017e t\u00e1hnu mr\u0148av\u00e9ho tu\u0148\u00e1ka, kter\u00fd trochu v\u00edce bojuje a navij\u00e1k prokluzuje v\u00edce ne\u017e je zdr\u00e1vo, se pokus\u00edm s\u00e1hnout na brzdu, ale Mark je ve st\u0159ehu a dosti ne\u0161etrn\u011b mi odstr\u010d\u00ed ruku a ud\u011bl\u00e1 to s\u00e1m.", [["Dvakr\u00e1t", "dvakr\u00e1t", "ADV", [0, 7]], ["nebo", "nebo", "CCONJ", [8, 12]], ["t\u0159ikr\u00e1t", "t\u0159ikr\u00e1t", "ADV", [13, 20]], [",", ",", "PUNCT", [20, 21]], ["kdy\u017e", "kdy\u017e", "SCONJ", [22, 26]], ["t\u00e1hnu", "t\u00e1hen", "NOUN", [27, 32]], ["mr\u0148av\u00e9ho", "mr\u0148av\u00fd", "ADJ", [33, 41]], ["tu\u0148\u00e1ka", "tu\u0148\u00e1k", "NOUN", [42, 48]], [",", ",", "PUNCT", [48, 49]], ["kter\u00fd", "kter\u00fd", "DET", [50, 55]], ["trochu", "trochu", "ADV", [56, 62]], ["v\u00edce", "v\u00edce", "ADV", [63, 67]], ["bojuje", "bojovat", "VERB", [68, 74]], ["a", "a", "CCONJ", [75, 76]], ["navij\u00e1k", "navij\u00e1k", "NOUN", [77, 84]], ["prokluzuje", "prokluzovat", "VERB", [85, 95]], ["v\u00edce", "v\u00edce", "ADV", [96, 100]], ["ne\u017e", "ne\u017e", "SCONJ", [101, 104]], ["je", "b\u00fdt", "AUX", [105, 107]], ["zdr\u00e1vo", "zdrav\u00fd", "ADV", [108, 114]], [",", ",", "PUNCT", [114, 115]], ["se", "se", "PRON", [116, 118]], ["pokus\u00edm", "pokusit", "VERB", [119, 126]], ["s\u00e1hnout", "s\u00e1hnout", "VERB", [127, 134]], ["na", "na", "ADP", [135, 137]], ["brzdu", "brzda", "NOUN", [138, 143]], [",", ",", "PUNCT", [143, 144]], ["ale", "ale", "CCONJ", [145, 148]], ["Mark", "Mark", "PROPN", [149, 153]], ["je", "b\u00fdt", "AUX", [154, 156]], ["ve", "v", "ADP", [157, 159]], ["st\u0159ehu", "st\u0159eh", "NOUN", [160, 166]], ["a", "a", "CCONJ", [167, 168]], ["dosti", "dost", "ADV", [169, 174]], ["ne\u0161etrn\u011b", "\u0161etrn\u011b", "ADV", [175, 183]], ["mi", "j\u00e1", "PRON", [184, 186]], ["odstr\u010d\u00ed", "odstr\u010dit", "VERB", [187, 194]], ["ruku", "ruka", "NOUN", [195, 199]], ["a", "a", "CCONJ", [200, 201]], ["ud\u011bl\u00e1", "ud\u011blat", "VERB", [202, 207]], ["to", "ten", "DET", [208, 210]], ["s\u00e1m", "sam\u00fd", "DET", [211, 214]], [".", ".", "PUNCT", [214, 215]]]], ["calgarske-listy_2003_unor_ocr.txt", "Div m\u011b p\u0159es n\u00ed nepl\u00e1cne.", [["Div", "div", "NOUN", [0, 3]], ["m\u011b", "j\u00e1", "PRON", [4, 6]], ["p\u0159es", "p\u0159es", "ADP", [7, 11]], ["n\u00ed", "on", "PRON", [12, 14]], ["nepl\u00e1cne", "pl\u00e1cnout", "VERB", [15, 23]], [".", ".", "PUNCT", [23, 24]]]], ["calgarske-listy_2003_unor_ocr.txt", "Kdy\u017e to ud\u011bl\u00e1m pot\u0159et\u00ed, tak nav\u00edc zavr\u010d\u00ed, abych rad\u011bji na nic nesahal.", [["Kdy\u017e", "kdy\u017e", "SCONJ", [0, 4]], ["to", "ten", "DET", [5, 7]], ["ud\u011bl\u00e1m", "ud\u011blat", "VERB", [8, 14]], ["pot\u0159et\u00ed", "pot\u0159et\u00ed", "ADV", [15, 22]], [",", ",", "PUNCT", [22, 23]], ["tak", "tak", "ADV", [24, 27]], ["nav\u00edc", "nav\u00edc", "ADV", [28, 33]], ["zavr\u010d\u00ed", "zavr\u010det", "VERB", [34, 40]], [",", ",", "PUNCT", [40, 41]], ["aby", "aby", "SCONJ", [-13480, -13480]], ["bych", "b\u00fdt", "AUX", [-13480, -13480]], ["rad\u011bji", "r\u00e1d", "ADV", [48, 54]], ["na", "na", "ADP", [55, 57]], ["nic", "nic", "PRON", [58, 61]], ["nesahal", "sahat", "VERB", [62, 69]], [".", ".", "PUNCT", [69, 70]]]], ["calgarske-listy_2003_unor_ocr.txt", "N\u00e1vazku s vlascem, na kter\u00e9 je n\u00e1vnada se nemohu ani dotknout, asi abych se nep\u00edchl o h\u00e1\u010dek.", [["N\u00e1vazku", "N\u00e1vazek", "PROPN", [0, 7]], ["s", "s", "ADP", [8, 9]], ["vlascem", "vlasec", "NOUN", [10, 17]], [",", ",", "PUNCT", [17, 18]], ["na", "na", "ADP", [19, 21]], ["kter\u00e9", "kter\u00fd", "DET", [22, 27]], ["je", "b\u00fdt", "AUX", [28, 30]], ["n\u00e1vnada", "n\u00e1vnada", "NOUN", [31, 38]], ["se", "se", "PRON", [39, 41]], ["nemohu", "moci", "VERB", [42, 48]], ["ani", "ani", "CCONJ", [49, 52]], ["dotknout", "dotknout", "VERB", [53, 61]], [",", ",", "PUNCT", [61, 62]], ["asi", "asi", "PART", [63, 66]], ["aby", "aby", "SCONJ", [-13551, -13551]], ["bych", "b\u00fdt", "AUX", [-13551, -13551]], ["se", "se", "PRON", [73, 75]], ["nep\u00edchl", "p\u00edchnout", "VERB", [76, 83]], ["o", "o", "ADP", [84, 85]], ["h\u00e1\u010dek", "h\u00e1\u010dek", "NOUN", [86, 91]], [".", ".", "PUNCT", [91, 92]]]], ["calgarske-listy_2003_unor_ocr.txt", "Tento zp\u016fsob tak\u00e9rybolovu zn\u00e1m z vypr\u00e1v\u011bn\u00ed.", [["Tento", "tento", "DET", [0, 5]], ["zp\u016fsob", "zp\u016fsob", "NOUN", [6, 12]], ["tak\u00e9rybolovu", "tak\u00e9rybolov", "NOUN", [13, 25]], ["zn\u00e1m", "zn\u00e1m\u00fd", "ADJ", [26, 30]], ["z", "z", "ADP", [31, 32]], ["vypr\u00e1v\u011bn\u00ed", "vypr\u00e1v\u011bn\u00ed", "NOUN", [33, 42]], [".", ".", "PUNCT", [42, 43]]]], ["calgarske-listy_2003_unor_ocr.txt", "H\u00e1z\u00edm tento z\u00e1\u017eitek do stejn\u00e9ho pytle jako byl lov na kance v obo\u0159e v Ji\u017en\u00edch \u010cech\u00e1ch, kde jsem m\u011bl dojem, \u017ee mi k\u0148oura vysypali z bedni\u010dky p\u0159\u00edmo p\u0159ed mu\u0161ku.", [["H\u00e1z\u00edm", "h\u00e1zet", "VERB", [0, 5]], ["tento", "tento", "DET", [6, 11]], ["z\u00e1\u017eitek", "z\u00e1\u017eitek", "NOUN", [12, 19]], ["do", "do", "ADP", [20, 22]], ["stejn\u00e9ho", "stejn\u00fd", "ADJ", [23, 31]], ["pytle", "pytel", "NOUN", [32, 37]], ["jako", "jako", "SCONJ", [38, 42]], ["byl", "b\u00fdt", "AUX", [43, 46]], ["lov", "lov", "NOUN", [47, 50]], ["na", "na", "ADP", [51, 53]], ["kance", "kanec", "NOUN", [54, 59]], ["v", "v", "ADP", [60, 61]], ["obo\u0159e", "obora", "NOUN", [62, 67]], ["v", "v", "ADP", [68, 69]], ["Ji\u017en\u00edch", "ji\u017en\u00ed", "ADJ", [70, 77]], ["\u010cech\u00e1ch", "\u010cechy", "PROPN", [78, 85]], [",", ",", "PUNCT", [85, 86]], ["kde", "kde", "ADV", [87, 90]], ["jsem", "b\u00fdt", "AUX", [91, 95]], ["m\u011bl", "m\u00edt", "VERB", [96, 99]], ["dojem", "dojem", "NOUN", [100, 105]], [",", ",", "PUNCT", [105, 106]], ["\u017ee", "\u017ee", "SCONJ", [107, 109]], ["mi", "j\u00e1", "PRON", [110, 112]], ["k\u0148oura", "k\u0148oura", "NOUN", [113, 119]], ["vysypali", "vysypat", "VERB", [120, 128]], ["z", "z", "ADP", [129, 130]], ["bedni\u010dky", "bedni\u010dka", "NOUN", [131, 139]], ["p\u0159\u00edmo", "p\u0159\u00edmo", "ADV", [140, 145]], ["p\u0159ed", "p\u0159ed", "ADP", [146, 150]], ["mu\u0161ku", "mu\u0161ka", "NOUN", [151, 156]], [".", ".", "PUNCT", [156, 157]]]], ["calgarske-listy_2003_unor_ocr.txt", "Na Pacifick\u00e9m pob\u0159e\u017e\u00ed Vancouver Island, kde tr\u00e1v\u00edm posledn\u00ed l\u00e9ta drtivou \u010d\u00e1st sv\u00fdch ryb\u00e1\u0159sk\u00fdch kratochv\u00edl\u00ed, jsou zvyklosti zpravidla jin\u00e9.", [["Na", "na", "ADP", [0, 2]], ["Pacifick\u00e9m", "pacifick\u00fd", "ADJ", [3, 13]], ["pob\u0159e\u017e\u00ed", "pob\u0159e\u017e\u00ed", "NOUN", [14, 21]], ["Vancouver", "Vancouver", "PROPN", [22, 31]], ["Island", "Island", "PROPN", [32, 38]], [",", ",", "PUNCT", [38, 39]], ["kde", "kde", "ADV", [40, 43]], ["tr\u00e1v\u00edm", "tr\u00e1vit", "VERB", [44, 50]], ["posledn\u00ed", "posledn\u00ed", "ADJ", [51, 59]], ["l\u00e9ta", "l\u00e9ta", "NOUN", [60, 64]], ["drtivou", "drtiv\u00fd", "ADJ", [65, 72]], ["\u010d\u00e1st", "\u010d\u00e1st", "NOUN", [73, 77]], ["sv\u00fdch", "sv\u016fj", "DET", [78, 83]], ["ryb\u00e1\u0159sk\u00fdch", "ryb\u00e1\u0159sk\u00fd", "ADJ", [84, 94]], ["kratochv\u00edl\u00ed", "kratochv\u00edle", "NOUN", [95, 106]], [",", ",", "PUNCT", [106, 107]], ["jsou", "b\u00fdt", "AUX", [108, 112]], ["zvyklosti", "zvyklost", "NOUN", [113, 122]], ["zpravidla", "zpravidla", "ADV", [123, 132]], ["jin\u00e9", "jin\u00fd", "ADJ", [133, 137]], [".", ".", "PUNCT", [137, 138]]]], ["calgarske-listy_2003_unor_ocr.txt", "Je to ov\u0161em d\u00e1no t\u00edm, \u017ee v ur\u010dit\u00e9 sestav\u011b ryba\u0159\u00edme u\u017e l\u00e9ta, tak\u017ee nap\u0159\u00edklad n\u00e1\u0161 skipper Nick, se kter\u00fdm se plav\u00edm od roku 1997 v\u00ed, \u017ee leccos um\u00edme a nech\u00e1v\u00e1 n\u00e1m pom\u011brn\u011b volnou ruku.", [["Je", "b\u00fdt", "AUX", [0, 2]], ["to", "ten", "DET", [3, 5]], ["ov\u0161em", "ov\u0161em", "PART", [6, 11]], ["d\u00e1no", "dan\u00fd", "ADJ", [12, 16]], ["t\u00edm", "ten", "DET", [17, 20]], [",", ",", "PUNCT", [20, 21]], ["\u017ee", "\u017ee", "SCONJ", [22, 24]], ["v", "v", "ADP", [25, 26]], ["ur\u010dit\u00e9", "ur\u010dit\u00fd", "ADJ", [27, 33]], ["sestav\u011b", "sestava", "NOUN", [34, 41]], ["ryba\u0159\u00edme", "ryba\u0159it", "VERB", [42, 50]], ["u\u017e", "u\u017e", "ADV", [51, 53]], ["l\u00e9ta", "l\u00e9ta", "NOUN", [54, 58]], [",", ",", "PUNCT", [58, 59]], ["tak\u017ee", "tak\u017ee", "SCONJ", [60, 65]], ["nap\u0159\u00edklad", "nap\u0159\u00edklad", "PART", [66, 75]], ["n\u00e1\u0161", "n\u00e1\u0161", "DET", [76, 79]], ["skipper", "skipper", "NOUN", [80, 87]], ["Nick", "Nick", "PROPN", [88, 92]], [",", ",", "PUNCT", [92, 93]], ["se", "s", "ADP", [94, 96]], ["kter\u00fdm", "kter\u00fd", "DET", [97, 103]], ["se", "s", "ADP", [104, 106]], ["plav\u00edm", "plavit", "VERB", [107, 113]], ["od", "od", "ADP", [114, 116]], ["roku", "rok", "NOUN", [117, 121]], ["1997", "1997", "NUM", [122, 126]], ["v\u00ed", "v\u011bd\u011bt", "VERB", [127, 129]], [",", ",", "PUNCT", [129, 130]], ["\u017ee", "\u017ee", "SCONJ", [131, 133]], ["leccos", "leccos", "PRON", [134, 140]], ["um\u00edme", "um\u011bt", "VERB", [141, 146]], ["a", "a", "CCONJ", [147, 148]], ["nech\u00e1v\u00e1", "nech\u00e1vat", "VERB", [149, 156]], ["n\u00e1m", "my", "PRON", [157, 160]], ["pom\u011brn\u011b", "pom\u011brn\u011b", "ADV", [161, 168]], ["volnou", "voln\u00fd", "ADJ", [169, 175]], ["ruku", "ruka", "NOUN", [176, 180]], [".", ".", "PUNCT", [180, 181]]]], ["calgarske-listy_2003_unor_ocr.txt", "Nick n\u00e1s ov\u0161em zn\u00e1, m\u016f\u017eete nam\u00edtnout.", [["Nick", "Nick", "PROPN", [0, 4]], ["n\u00e1s", "my", "PRON", [5, 8]], ["ov\u0161em", "ov\u0161em", "PART", [9, 14]], ["zn\u00e1", "zn\u00e1t", "VERB", [15, 18]], [",", ",", "PUNCT", [18, 19]], ["m\u016f\u017eete", "moci", "VERB", [20, 26]], ["nam\u00edtnout", "nam\u00edtnout", "VERB", [27, 36]], [".", ".", "PUNCT", [36, 37]]]], ["calgarske-listy_2003_unor_ocr.txt", "Letos v l\u00e9t\u011b jsem ale byl na rodinn\u00e9 dovolen\u00e9 v Tof\u00ednu, v jednom z Kanadsk\u00fdch n\u00e1rodn\u00edch park\u016f, Pacific Rim Park.", [["Letos", "letos", "ADV", [0, 5]], ["v", "v", "ADP", [6, 7]], ["l\u00e9t\u011b", "l\u00e9to", "NOUN", [8, 12]], ["jsem", "b\u00fdt", "AUX", [13, 17]], ["ale", "ale", "CCONJ", [18, 21]], ["byl", "b\u00fdt", "AUX", [22, 25]], ["na", "na", "ADP", [26, 28]], ["rodinn\u00e9", "rodinn\u00fd", "ADJ", [29, 36]], ["dovolen\u00e9", "dovolen\u00e1", "NOUN", [37, 45]], ["v", "v", "ADP", [46, 47]], ["Tof\u00ednu", "Tof\u00edn", "PROPN", [48, 54]], [",", ",", "PUNCT", [54, 55]], ["v", "v", "ADP", [56, 57]], ["jednom", "jeden", "NUM", [58, 64]], ["z", "z", "ADP", [65, 66]], ["Kanadsk\u00fdch", "kanadsk\u00fd", "ADJ", [67, 77]], ["n\u00e1rodn\u00edch", "n\u00e1rodn\u00ed", "ADJ", [78, 87]], ["park\u016f", "park", "NOUN", [88, 93]], [",", ",", "PUNCT", [93, 94]], ["Pacific", "Pacific", "X", [95, 102]], ["Rim", "Rim", "X", [103, 106]], ["Park", "Park", "X", [107, 111]], [".", ".", "PUNCT", [111, 112]]]], ["calgarske-listy_2003_unor_ocr.txt", "Najal jsem si \u010dlun na cel\u00fd den a vzal sebou Irenu a Kl\u00e1ru.", [["Najal", "najmout", "VERB", [0, 5]], ["jsem", "b\u00fdt", "AUX", [6, 10]], ["si", "se", "PRON", [11, 13]], ["\u010dlun", "\u010dlun", "NOUN", [14, 18]], ["na", "na", "ADP", [19, 21]], ["cel\u00fd", "cel\u00fd", "ADJ", [22, 26]], ["den", "den", "NOUN", [27, 30]], ["a", "a", "CCONJ", [31, 32]], ["vzal", "vz\u00edt", "VERB", [33, 37]], ["sebou", "se", "PRON", [38, 43]], ["Irenu", "Irena", "PROPN", [44, 49]], ["a", "a", "CCONJ", [50, 51]], ["Kl\u00e1ru", "Kl\u00e1r", "PROPN", [52, 57]], [".", ".", "PUNCT", [57, 58]]]], ["calgarske-listy_2003_unor_ocr.txt", "Kv\u016fli mo\u0159sk\u00e9 nemoci nemohli chytat, tak\u017ee jsem m\u011bl cel\u00fd \u010dlun pro sebe a chytal na dva pruty, skoro jako rusk\u00e1 tkadlena Voroblikovov\u00e1, kter\u00e1 pracovala na t\u0159ech stavech a trhala normy..", [["Kv\u016fli", "kv\u016fli", "ADP", [0, 5]], ["mo\u0159sk\u00e9", "mo\u0159sk\u00fd", "ADJ", [6, 12]], ["nemoci", "nemoc", "NOUN", [13, 19]], ["nemohli", "moci", "VERB", [20, 27]], ["chytat", "chytat", "VERB", [28, 34]], [",", ",", "PUNCT", [34, 35]], ["tak\u017ee", "tak\u017ee", "SCONJ", [36, 41]], ["jsem", "b\u00fdt", "AUX", [42, 46]], ["m\u011bl", "m\u00edt", "VERB", [47, 50]], ["cel\u00fd", "cel\u00fd", "ADJ", [51, 55]], ["\u010dlun", "\u010dlun", "NOUN", [56, 60]], ["pro", "pro", "ADP", [61, 64]], ["sebe", "se", "PRON", [65, 69]], ["a", "a", "CCONJ", [70, 71]], ["chytal", "chytat", "VERB", [72, 78]], ["na", "na", "ADP", [79, 81]], ["dva", "dva", "NUM", [82, 85]], ["pruty", "prut", "NOUN", [86, 91]], [",", ",", "PUNCT", [91, 92]], ["skoro", "skoro", "ADV", [93, 98]], ["jako", "jako", "SCONJ", [99, 103]], ["rusk\u00e1", "rusk\u00fd", "ADJ", [104, 109]], ["tkadlena", "tkadlen\u00fd", "ADJ", [110, 118]], ["Voroblikovov\u00e1", "Voroblikovov\u00e1", "PROPN", [119, 132]], [",", ",", "PUNCT", [132, 133]], ["kter\u00e1", "kter\u00fd", "DET", [134, 139]], ["pracovala", "pracovat", "VERB", [140, 149]], ["na", "na", "ADP", [150, 152]], ["t\u0159ech", "t\u0159i", "NUM", [153, 158]], ["stavech", "stav", "NOUN", [159, 166]], ["a", "a", "CCONJ", [167, 168]], ["trhala", "trhat", "VERB", [169, 175]], ["normy", "norma", "NOUN", [176, 181]], [".", ".", "PUNCT", [181, 182]], [".", ".", "PUNCT", [182, 183]]]], ["calgarske-listy_2003_unor_ocr.txt", "Z\u00e1\u017eitek to byl fantastick\u00fd, ale d\u016fvod pro\u010d se o tomto zmi\u0148uji byl p\u0159\u00edstup skippera Dicka.", [["Z\u00e1\u017eitek", "z\u00e1\u017eitek", "NOUN", [0, 7]], ["to", "ten", "DET", [8, 10]], ["byl", "b\u00fdt", "AUX", [11, 14]], ["fantastick\u00fd", "fantastick\u00fd", "ADJ", [15, 26]], [",", ",", "PUNCT", [26, 27]], ["ale", "ale", "CCONJ", [28, 31]], ["d\u016fvod", "d\u016fvod", "NOUN", [32, 37]], ["pro\u010d", "pro\u010d", "ADV", [38, 42]], ["se", "se", "PRON", [43, 45]], ["o", "o", "ADP", [46, 47]], ["tomto", "tento", "DET", [48, 53]], ["zmi\u0148uji", "zmi\u0148ovat", "VERB", [54, 61]], ["byl", "b\u00fdt", "AUX", [62, 65]], ["p\u0159\u00edstup", "p\u0159\u00edstup", "NOUN", [66, 73]], ["skippera", "skipper", "PROPN", [74, 82]], ["Dicka", "Dick", "PROPN", [83, 88]], [".", ".", "PUNCT", [88, 89]]]], ["calgarske-listy_2003_unor_ocr.txt", "Za p\u016fl hodinky poznal, \u017ee m\u011b m\u016f\u017ee z\u00e1\u010f lodi zcela sv\u011b\u0159it a pak u\u017e se v\u011bnoval jenom \u0159\u00edzen\u00ed \u010dlunu.", [["Za", "za", "ADP", [0, 2]], ["p\u016fl", "p\u016fl", "NUM", [3, 6]], ["hodinky", "hodinky", "NOUN", [7, 14]], ["poznal", "poznat", "VERB", [15, 21]], [",", ",", "PUNCT", [21, 22]], ["\u017ee", "\u017ee", "SCONJ", [23, 25]], ["m\u011b", "j\u00e1", "PRON", [26, 28]], ["m\u016f\u017ee", "moci", "VERB", [29, 33]], ["z\u00e1\u010f", "z\u00e1\u010f", "NOUN", [34, 37]], ["lodi", "lo\u010f", "NOUN", [38, 42]], ["zcela", "zcela", "ADV", [43, 48]], ["sv\u011b\u0159it", "sv\u011b\u0159it", "VERB", [49, 55]], ["a", "a", "CCONJ", [56, 57]], ["pak", "pak", "ADV", [58, 61]], ["u\u017e", "u\u017e", "ADV", [62, 64]], ["se", "se", "PRON", [65, 67]], ["v\u011bnoval", "v\u011bnovat", "VERB", [68, 75]], ["jenom", "jenom", "PART", [76, 81]], ["\u0159\u00edzen\u00ed", "\u0159\u00edzen\u00ed", "NOUN", [82, 88]], ["\u010dlunu", "\u010dlun", "NOUN", [89, 94]], [".", ".", "PUNCT", [94, 95]]]], ["calgarske-listy_2003_unor_ocr.txt", "4", [["4", "4", "NUM", [0, 1]]]], ["calgarske-listy_2003_unor_ocr.txt", "Oba zm\u00edn\u011bn\u00ed skippe\u0159i Nick a Dick a v\u0161ichni ostatn\u00ed, a\u0165 je zn\u00e1m \u010di nezn\u00e1m ale tak\u00e9 v\u00ed, \u017ee jejich ameri\u010dt\u00ed z\u00e1kazn\u00edci, kter\u00fdch je nepom\u011brn\u011b v\u00edce ne\u017e kanadsk\u00fdch, velmi \u010dasto (ale ne ve v\u0161ech p\u0159\u00edpadech) tento zp\u016fsob ryba\u0159en\u00ed s naserv\u00edrov\u00e1n\u00edm a\u017e pod nos p\u0159\u00edmo vy\u017eaduj\u00ed.", [["Oba", "oba", "NUM", [0, 3]], ["zm\u00edn\u011bn\u00ed", "zm\u00edn\u011bn\u00fd", "ADJ", [4, 11]], ["skippe\u0159i", "skipper", "NOUN", [12, 20]], ["Nick", "Nick", "PROPN", [21, 25]], ["a", "a", "CCONJ", [26, 27]], ["Dick", "Dick", "PROPN", [28, 32]], ["a", "a", "CCONJ", [33, 34]], ["v\u0161ichni", "v\u0161echen", "DET", [35, 42]], ["ostatn\u00ed", "ostatn\u00ed", "ADJ", [43, 50]], [",", ",", "PUNCT", [50, 51]], ["a\u0165", "a\u0165", "SCONJ", [52, 54]], ["je", "b\u00fdt", "AUX", [55, 57]], ["zn\u00e1m", "zn\u00e1m\u00fd", "ADJ", [58, 62]], ["\u010di", "\u010di", "CCONJ", [63, 65]], ["nezn\u00e1m", "zn\u00e1t", "VERB", [66, 72]], ["ale", "ale", "CCONJ", [73, 76]], ["tak\u00e9", "tak\u00e9", "ADV", [77, 81]], ["v\u00ed", "v\u011bd\u011bt", "VERB", [82, 84]], [",", ",", "PUNCT", [84, 85]], ["\u017ee", "\u017ee", "SCONJ", [86, 88]], ["jejich", "jeho", "DET", [89, 95]], ["ameri\u010dt\u00ed", "americk\u00fd", "ADJ", [96, 104]], ["z\u00e1kazn\u00edci", "z\u00e1kazn\u00edk", "NOUN", [105, 114]], [",", ",", "PUNCT", [114, 115]], ["kter\u00fdch", "kter\u00fd", "DET", [116, 123]], ["je", "b\u00fdt", "AUX", [124, 126]], ["nepom\u011brn\u011b", "pom\u011brn\u011b", "ADV", [127, 136]], ["v\u00edce", "v\u00edce", "ADV", [137, 141]], ["ne\u017e", "ne\u017e", "SCONJ", [142, 145]], ["kanadsk\u00fdch", "kanadsk\u00fd", "ADJ", [146, 156]], [",", ",", "PUNCT", [156, 157]], ["velmi", "velmi", "ADV", [158, 163]], ["\u010dasto", "\u010dasto", "ADV", [164, 169]], ["(", "(", "PUNCT", [170, 171]], ["ale", "ale", "CCONJ", [171, 174]], ["ne", "ne", "PART", [175, 177]], ["ve", "v", "ADP", [178, 180]], ["v\u0161ech", "v\u0161echen", "DET", [181, 186]], ["p\u0159\u00edpadech", "p\u0159\u00edpad", "NOUN", [187, 196]], [")", ")", "PUNCT", [196, 197]], ["tento", "tento", "DET", [198, 203]], ["zp\u016fsob", "zp\u016fsob", "NOUN", [204, 210]], ["ryba\u0159en\u00ed", "ryba\u0159en\u00ed", "NOUN", [211, 219]], ["s", "s", "ADP", [220, 221]], ["naserv\u00edrov\u00e1n\u00edm", "naserv\u00edrov\u00e1n\u00ed", "NOUN", [222, 236]], ["a\u017e", "a\u017e", "PART", [237, 239]], ["pod", "pod", "ADP", [240, 243]], ["nos", "nos", "NOUN", [244, 247]], ["p\u0159\u00edmo", "p\u0159\u00edmo", "ADV", [248, 253]], ["vy\u017eaduj\u00ed", "vy\u017eadovat", "VERB", [254, 262]], [".", ".", "PUNCT", [262, 263]]]], ["calgarske-listy_2003_unor_ocr.txt", "O tom, jestli byla d\u0159\u00edve slepice nebo vejce se sv\u00fdmi p\u0159\u00e1teli debatujeme o ka\u017ed\u00e9m v\u00fdlet\u011b na Pacifick\u00e9 pob\u0159e\u017e\u00ed.", [["O", "o", "ADP", [0, 1]], ["tom", "ten", "DET", [2, 5]], [",", ",", "PUNCT", [5, 6]], ["jestli", "jestli", "SCONJ", [7, 13]], ["byla", "b\u00fdt", "AUX", [14, 18]], ["d\u0159\u00edve", "d\u0159\u00edve", "ADV", [19, 24]], ["slepice", "slepice", "NOUN", [25, 32]], ["nebo", "nebo", "CCONJ", [33, 37]], ["vejce", "vejce", "NOUN", [38, 43]], ["se", "s", "ADP", [44, 46]], ["sv\u00fdmi", "sv\u016fj", "DET", [47, 52]], ["p\u0159\u00e1teli", "p\u0159\u00edtel", "NOUN", [53, 60]], ["debatujeme", "debatovat", "VERB", [61, 71]], ["o", "o", "ADP", [72, 73]], ["ka\u017ed\u00e9m", "ka\u017ed\u00fd", "DET", [74, 80]], ["v\u00fdlet\u011b", "v\u00fdlet", "NOUN", [81, 87]], ["na", "na", "ADP", [88, 90]], ["Pacifick\u00e9", "pacifick\u00fd", "ADJ", [91, 100]], ["pob\u0159e\u017e\u00ed", "pob\u0159e\u017e\u00ed", "NOUN", [101, 108]], [".", ".", "PUNCT", [108, 109]]]], ["calgarske-listy_2003_unor_ocr.txt", "Je tento zp\u016fsob zaveden\u00fd proto, \u017ee se majitel\u00e9 chartern boj\u00ed o sv\u00e9 n\u00e1dob\u00ed\u010dko a aby co nejv\u00edc p\u0159ede\u0161li mo\u017en\u00e9mu zran\u011bn\u00ed, co\u017e souvis\u00ed tak\u00e9 s americkou posedlost\u00ed se o ka\u017edou blbost soudit?", [["Je", "b\u00fdt", "AUX", [0, 2]], ["tento", "tento", "DET", [3, 8]], ["zp\u016fsob", "zp\u016fsob", "NOUN", [9, 15]], ["zaveden\u00fd", "zaveden\u00fd", "ADJ", [16, 24]], ["proto", "proto", "ADV", [25, 30]], [",", ",", "PUNCT", [30, 31]], ["\u017ee", "\u017ee", "SCONJ", [32, 34]], ["se", "se", "PRON", [35, 37]], ["majitel\u00e9", "majitel", "NOUN", [38, 46]], ["chartern", "chartern", "NOUN", [47, 55]], ["boj\u00ed", "b\u00e1t", "VERB", [56, 60]], ["o", "o", "ADP", [61, 62]], ["sv\u00e9", "sv\u016fj", "DET", [63, 66]], ["n\u00e1dob\u00ed\u010dko", "n\u00e1dob\u00ed\u010dko", "NOUN", [67, 76]], ["a", "a", "CCONJ", [77, 78]], ["aby", "aby", "SCONJ", [-15124, -15124]], ["by", "b\u00fdt", "AUX", [-15124, -15124]], ["co", "co", "PRON", [83, 85]], ["nejv\u00edc", "v\u00edce", "ADV", [86, 92]], ["p\u0159ede\u0161li", "p\u0159edej\u00edt", "VERB", [93, 101]], ["mo\u017en\u00e9mu", "mo\u017en\u00fd", "ADJ", [102, 109]], ["zran\u011bn\u00ed", "zran\u011bn\u00ed", "NOUN", [110, 117]], [",", ",", "PUNCT", [117, 118]], ["co\u017e", "co\u017e", "PRON", [119, 122]], ["souvis\u00ed", "souviset", "VERB", [123, 130]], ["tak\u00e9", "tak\u00e9", "ADV", [131, 135]], ["s", "s", "ADP", [136, 137]], ["americkou", "americk\u00fd", "ADJ", [138, 147]], ["posedlost\u00ed", "posedlost", "NOUN", [148, 158]], ["se", "se", "PRON", [159, 161]], ["o", "o", "ADP", [162, 163]], ["ka\u017edou", "ka\u017ed\u00fd", "DET", [164, 170]], ["blbost", "blbost", "NOUN", [171, 177]], ["soudit", "soudit", "VERB", [178, 184]], ["?", "?", "PUNCT", [184, 185]]]], ["calgarske-listy_2003_unor_ocr.txt", "Anebo je to proto, \u017ee drtiv\u00e1 v\u011bt\u0161ina z\u00e1kazn\u00edk\u016f nejsou vlastn\u011b ani tak sportovn\u00ed ryb\u00e1\u0159i, jako sp\u00ed\u0161e v\u00fdletn\u00edci, kte\u0159\u00ed to cht\u011bj\u00ed zkusit t\u0159eba jen proto, \u017ee cht\u011bj\u00ed m\u00edt fotku s par\u00e1dn\u00ed rybou.", [["Anebo", "anebo", "CCONJ", [0, 5]], ["je", "b\u00fdt", "AUX", [6, 8]], ["to", "ten", "DET", [9, 11]], ["proto", "proto", "ADV", [12, 17]], [",", ",", "PUNCT", [17, 18]], ["\u017ee", "\u017ee", "SCONJ", [19, 21]], ["drtiv\u00e1", "drtiv\u00fd", "ADJ", [22, 28]], ["v\u011bt\u0161ina", "v\u011bt\u0161ina", "NOUN", [29, 36]], ["z\u00e1kazn\u00edk\u016f", "z\u00e1kazn\u00edk", "NOUN", [37, 46]], ["nejsou", "b\u00fdt", "AUX", [47, 53]], ["vlastn\u011b", "vlastn\u011b", "ADV", [54, 61]], ["ani", "ani", "CCONJ", [62, 65]], ["tak", "tak", "ADV", [66, 69]], ["sportovn\u00ed", "sportovn\u00ed", "ADJ", [70, 79]], ["ryb\u00e1\u0159i", "ryb\u00e1\u0159", "NOUN", [80, 86]], [",", ",", "PUNCT", [86, 87]], ["jako", "jako", "SCONJ", [88, 92]], ["sp\u00ed\u0161e", "sp\u00ed\u0161", "PART", [93, 98]], ["v\u00fdletn\u00edci", "v\u00fdletn\u00edk", "NOUN", [99, 108]], [",", ",", "PUNCT", [108, 109]], ["kte\u0159\u00ed", "kter\u00fd", "DET", [110, 115]], ["to", "ten", "DET", [116, 118]], ["cht\u011bj\u00ed", "cht\u00edt", "VERB", [119, 125]], ["zkusit", "zkusit", "VERB", [126, 132]], ["t\u0159eba", "t\u0159eba", "PART", [133, 138]], ["jen", "jen", "PART", [139, 142]], ["proto", "proto", "ADV", [143, 148]], [",", ",", "PUNCT", [148, 149]], ["\u017ee", "\u017ee", "SCONJ", [150, 152]], ["cht\u011bj\u00ed", "cht\u00edt", "VERB", [153, 159]], ["m\u00edt", "m\u00edt", "VERB", [160, 163]], ["fotku", "fotka", "NOUN", [164, 169]], ["s", "s", "ADP", [170, 171]], ["par\u00e1dn\u00ed", "par\u00e1dn\u00ed", "ADJ", [172, 179]], ["rybou", "ryba", "NOUN", [180, 185]], [".", ".", "PUNCT", [185, 186]]]], ["calgarske-listy_2003_unor_ocr.txt", "Nemaj\u00ed pak ani zbla p\u0159edstavu tom, jak by skute\u010dn\u00fd rybolov m\u011bl vypadat a nechaj\u00ed si snadno neserv\u00edrovat tuto p\u0159e\u017ev\u00fdkanou verzi pseudorybolovu.", [["Nemaj\u00ed", "m\u00edt", "VERB", [0, 6]], ["pak", "pak", "ADV", [7, 10]], ["ani", "ani", "CCONJ", [11, 14]], ["zbla", "zbel", "NOUN", [15, 19]], ["p\u0159edstavu", "p\u0159edstava", "NOUN", [20, 29]], ["tom", "ten", "DET", [30, 33]], [",", ",", "PUNCT", [33, 34]], ["jak", "jak", "ADV", [35, 38]], ["by", "b\u00fdt", "AUX", [39, 41]], ["skute\u010dn\u00fd", "skute\u010dn\u00fd", "ADJ", [42, 50]], ["rybolov", "rybolov", "NOUN", [51, 58]], ["m\u011bl", "m\u00edt", "VERB", [59, 62]], ["vypadat", "vypadat", "VERB", [63, 70]], ["a", "a", "CCONJ", [71, 72]], ["nechaj\u00ed", "nechat", "VERB", [73, 80]], ["si", "se", "PRON", [81, 83]], ["snadno", "snadno", "ADV", [84, 90]], ["neserv\u00edrovat", "serv\u00edrovat", "VERB", [91, 103]], ["tuto", "tento", "DET", [104, 108]], ["p\u0159e\u017ev\u00fdkanou", "p\u0159e\u017ev\u00fdkan\u00fd", "ADJ", [109, 120]], ["verzi", "verze", "NOUN", [121, 126]], ["pseudorybolovu", "pseudorybolov", "NOUN", [127, 141]], [".", ".", "PUNCT", [141, 142]]]], ["calgarske-listy_2003_unor_ocr.txt", "B\u016fh su\u010f, s\u00e1m nev\u00edm a p\u0159i tom jsem o tom p\u0159em\u00fd\u0161lel mnohokr\u00e1tT \u017daryba\u0159ili bychom si asi dob\u0159e, ale ryby odm\u00edtaly br\u00e1t.", [["B\u016fh", "b\u016fh", "NOUN", [0, 3]], ["su\u010f", "su\u010f", "NOUN", [4, 7]], [",", ",", "PUNCT", [7, 8]], ["s\u00e1m", "sam\u00fd", "DET", [9, 12]], ["nev\u00edm", "v\u011bd\u011bt", "VERB", [13, 18]], ["a", "a", "CCONJ", [19, 20]], ["p\u0159i", "p\u0159i", "ADP", [21, 24]], ["tom", "ten", "DET", [25, 28]], ["jsem", "b\u00fdt", "AUX", [29, 33]], ["o", "o", "ADP", [34, 35]], ["tom", "ten", "DET", [36, 39]], ["p\u0159em\u00fd\u0161lel", "p\u0159em\u00fd\u0161let", "VERB", [40, 49]], ["mnohokr\u00e1tT", "mnohokr\u00e1tT", "ADV", [50, 60]], ["\u017daryba\u0159ili", "\u017earyba\u0159it", "VERB", [61, 71]], ["bychom", "b\u00fdt", "AUX", [72, 78]], ["si", "se", "PRON", [79, 81]], ["asi", "asi", "PART", [82, 85]], ["dob\u0159e", "dob\u0159e", "ADV", [86, 91]], [",", ",", "PUNCT", [91, 92]], ["ale", "ale", "CCONJ", [93, 96]], ["ryby", "ryba", "NOUN", [97, 101]], ["odm\u00edtaly", "odm\u00edtat", "VERB", [102, 110]], ["br\u00e1t", "br\u00e1t", "VERB", [111, 115]], [".", ".", "PUNCT", [115, 116]]]], ["calgarske-listy_2003_unor_ocr.txt", "To ka\u017ed\u00fd ryb\u00e1\u0159 zn\u00e1, i kdy\u017e na mo\u0159i se to zase a\u017e tak moc \u010dasto nest\u00e1v\u00e1.", [["To", "ten", "DET", [0, 2]], ["ka\u017ed\u00fd", "ka\u017ed\u00fd", "DET", [3, 8]], ["ryb\u00e1\u0159", "ryb\u00e1\u0159", "NOUN", [9, 14]], ["zn\u00e1", "zn\u00e1t", "VERB", [15, 18]], [",", ",", "PUNCT", [18, 19]], ["i", "i", "CCONJ", [20, 21]], ["kdy\u017e", "kdy\u017e", "SCONJ", [22, 26]], ["na", "na", "ADP", [27, 29]], ["mo\u0159i", "mo\u0159e", "NOUN", [30, 34]], ["se", "se", "PRON", [35, 37]], ["to", "ten", "DET", [38, 40]], ["zase", "zase", "ADV", [41, 45]], ["a\u017e", "a\u017e", "PART", [46, 48]], ["tak", "tak", "ADV", [49, 52]], ["moc", "moc", "ADV", [53, 56]], ["\u010dasto", "\u010dasto", "ADV", [57, 62]], ["nest\u00e1v\u00e1", "st\u00e1vat", "VERB", [63, 70]], [".", ".", "PUNCT", [70, 71]]]], ["calgarske-listy_2003_unor_ocr.txt", "Mark sKevinem aby zachr\u00e1nili situaci nakonec zam\u00ed\u0159ili do oblasti, kde se zdr\u017euj\u00ed obrovsk\u00e1 hejna mal\u00fdch Ahi.", [["Mark", "Mark", "PROPN", [0, 4]], ["sKevinem", "sKevin", "PROPN", [5, 13]], ["aby", "aby", "SCONJ", [-15829, -15829]], ["by", "b\u00fdt", "AUX", [-15829, -15829]], ["zachr\u00e1nili", "zachr\u00e1nit", "VERB", [18, 28]], ["situaci", "situace", "NOUN", [29, 36]], ["nakonec", "nakonec", "ADV", [37, 44]], ["zam\u00ed\u0159ili", "zam\u00ed\u0159it", "VERB", [45, 53]], ["do", "do", "ADP", [54, 56]], ["oblasti", "oblast", "NOUN", [57, 64]], [",", ",", "PUNCT", [64, 65]], ["kde", "kde", "ADV", [66, 69]], ["se", "se", "PRON", [70, 72]], ["zdr\u017euj\u00ed", "zdr\u017eovat", "VERB", [73, 80]], ["obrovsk\u00e1", "obrovsk\u00fd", "ADJ", [81, 89]], ["hejna", "hejno", "NOUN", [90, 95]], ["mal\u00fdch", "mal\u00fd", "ADJ", [96, 102]], ["Ahi", "Ahi", "PROPN", [103, 106]], [".", ".", "PUNCT", [106, 107]]]], ["calgarske-listy_2003_unor_ocr.txt", "To byla jedin\u00e1 chv\u00edle, kdy jsme si \u017earyba\u0159ili, za slabou hodinku a p\u016fl jsme t\u011bchto mal\u00fdch \u017elutoploutv\u00fdch tu\u0148\u00e1k\u016f vyt\u00e1hli ve t\u0159ech na t\u0159i tucty.", [["To", "ten", "DET", [0, 2]], ["byla", "b\u00fdt", "AUX", [3, 7]], ["jedin\u00e1", "jedin\u00fd", "ADJ", [8, 14]], ["chv\u00edle", "chv\u00edle", "NOUN", [15, 21]], [",", ",", "PUNCT", [21, 22]], ["kdy", "kdy", "ADV", [23, 26]], ["jsme", "b\u00fdt", "AUX", [27, 31]], ["si", "se", "PRON", [32, 34]], ["\u017earyba\u0159ili", "\u017earyba\u0159it", "VERB", [35, 45]], [",", ",", "PUNCT", [45, 46]], ["za", "za", "ADP", [47, 49]], ["slabou", "slab\u00fd", "ADJ", [50, 56]], ["hodinku", "hodinka", "NOUN", [57, 64]], ["a", "a", "CCONJ", [65, 66]], ["p\u016fl", "p\u016fl", "NUM", [67, 70]], ["jsme", "b\u00fdt", "AUX", [71, 75]], ["t\u011bchto", "tento", "DET", [76, 82]], ["mal\u00fdch", "mal\u00fd", "ADJ", [83, 89]], ["\u017elutoploutv\u00fdch", "\u017elutoploutv\u00fd", "ADJ", [90, 104]], ["tu\u0148\u00e1k\u016f", "tu\u0148\u00e1k", "NOUN", [105, 111]], ["vyt\u00e1hli", "vyt\u00e1hnout", "VERB", [112, 119]], ["ve", "v", "ADP", [120, 122]], ["t\u0159ech", "t\u0159i", "NUM", [123, 128]], ["na", "na", "ADP", [129, 131]], ["t\u0159i", "t\u0159i", "NUM", [132, 135]], ["tucty", "tuct", "NOUN", [136, 141]], [".", ".", "PUNCT", [141, 142]]]], ["calgarske-listy_2003_unor_ocr.txt", "Trolovac\u00ed rychlost se sni\u017euje na 5 uzl\u016f v hodin\u011b, po\u0159\u00e1d trochu vysok\u00e1, ale tu\u0148\u00e1ci jsou dravci a berou jako vztekl\u00ed.", [["Trolovac\u00ed", "trolovac\u00ed", "ADJ", [0, 9]], ["rychlost", "rychlost", "NOUN", [10, 18]], ["se", "se", "PRON", [19, 21]], ["sni\u017euje", "sni\u017eovat", "VERB", [22, 29]], ["na", "na", "ADP", [30, 32]], ["5", "5", "NUM", [33, 34]], ["uzl\u016f", "uzel", "NOUN", [35, 39]], ["v", "v", "ADP", [40, 41]], ["hodin\u011b", "hodina", "NOUN", [42, 48]], [",", ",", "PUNCT", [48, 49]], ["po\u0159\u00e1d", "po\u0159\u00e1d", "ADV", [50, 55]], ["trochu", "trochu", "ADV", [56, 62]], ["vysok\u00e1", "vysok\u00fd", "ADJ", [63, 69]], [",", ",", "PUNCT", [69, 70]], ["ale", "ale", "CCONJ", [71, 74]], ["tu\u0148\u00e1ci", "tu\u0148\u00e1k", "NOUN", [75, 81]], ["jsou", "b\u00fdt", "AUX", [82, 86]], ["dravci", "dravec", "NOUN", [87, 93]], ["a", "a", "CCONJ", [94, 95]], ["berou", "br\u00e1t", "VERB", [96, 101]], ["jako", "jako", "SCONJ", [102, 106]], ["vztekl\u00ed", "vztekl\u00fd", "ADJ", [107, 114]], [".", ".", "PUNCT", [114, 115]]]], ["calgarske-listy_2003_unor_ocr.txt", "Marn\u00e1 sl\u00e1va, jsou ale mal\u00ed, tak\u017ee boj se vede sp\u00ed\u0161e v n\u00e1znaku.", [["Marn\u00e1", "marn\u00fd", "ADJ", [0, 5]], ["sl\u00e1va", "sl\u00e1va", "NOUN", [6, 11]], [",", ",", "PUNCT", [11, 12]], ["jsou", "b\u00fdt", "AUX", [13, 17]], ["ale", "ale", "CCONJ", [18, 21]], ["mal\u00ed", "mal\u00fd", "ADJ", [22, 26]], [",", ",", "PUNCT", [26, 27]], ["tak\u017ee", "tak\u017ee", "SCONJ", [28, 33]], ["boj", "boj", "NOUN", [34, 37]], ["se", "se", "PRON", [38, 40]], ["vede", "v\u00e9st", "VERB", [41, 45]], ["sp\u00ed\u0161e", "sp\u00ed\u0161", "PART", [46, 51]], ["v", "v", "ADP", [52, 53]], ["n\u00e1znaku", "n\u00e1znak", "NOUN", [54, 61]], [".", ".", "PUNCT", [61, 62]]]], ["calgarske-listy_2003_unor_ocr.txt", "P\u0159i tomto lovu jsme samoz\u0159ejm\u011b pou\u017e\u00edvali pruty a dopl\u0148ky norm\u00e1ln\u00edch dimenz\u00ed.", [["P\u0159i", "p\u0159i", "ADP", [0, 3]], ["tomto", "tento", "DET", [4, 9]], ["lovu", "lov", "NOUN", [10, 14]], ["jsme", "b\u00fdt", "AUX", [15, 19]], ["samoz\u0159ejm\u011b", "samoz\u0159ejm\u011b", "ADV", [20, 30]], ["pou\u017e\u00edvali", "pou\u017e\u00edvat", "VERB", [31, 40]], ["pruty", "prut", "NOUN", [41, 46]], ["a", "a", "CCONJ", [47, 48]], ["dopl\u0148ky", "dopln\u011bk", "NOUN", [49, 56]], ["norm\u00e1ln\u00edch", "norm\u00e1ln\u00ed", "ADJ", [57, 67]], ["dimenz\u00ed", "dimenze", "NOUN", [68, 75]], [".", ".", "PUNCT", [75, 76]]]], ["calgarske-listy_2003_unor_ocr.txt", "Nic v\u011bt\u0161\u00edho n\u00e1m nezabralo.", [["Nic", "nic", "PRON", [0, 3]], ["v\u011bt\u0161\u00edho", "velk\u00fd", "ADJ", [4, 11]], ["n\u00e1m", "my", "PRON", [12, 15]], ["nezabralo", "zabrat", "VERB", [16, 25]], [".", ".", "PUNCT", [25, 26]]]], ["calgarske-listy_2003_unor_ocr.txt", "Mark sice asi t\u0159ikr\u00e1t vym\u011bnil n\u00e1vnady, ale jinak jsem p\u0159\u00edli\u0161nou iniciativu ze strany pos\u00e1dky nezaznamenal.", [["Mark", "Mark", "PROPN", [0, 4]], ["sice", "sice", "CCONJ", [5, 9]], ["asi", "asi", "PART", [10, 13]], ["t\u0159ikr\u00e1t", "t\u0159ikr\u00e1t", "ADV", [14, 21]], ["vym\u011bnil", "vym\u011bnit", "VERB", [22, 29]], ["n\u00e1vnady", "n\u00e1vnada", "NOUN", [30, 37]], [",", ",", "PUNCT", [37, 38]], ["ale", "ale", "CCONJ", [39, 42]], ["jinak", "jinak", "ADV", [43, 48]], ["jsem", "b\u00fdt", "AUX", [49, 53]], ["p\u0159\u00edli\u0161nou", "p\u0159\u00edli\u0161n\u00fd", "ADJ", [54, 63]], ["iniciativu", "iniciativa", "NOUN", [64, 74]], ["ze", "z", "ADP", [75, 77]], ["strany", "strana", "NOUN", [78, 84]], ["pos\u00e1dky", "pos\u00e1dka", "NOUN", [85, 92]], ["nezaznamenal", "zaznamenat", "VERB", [93, 105]], [".", ".", "PUNCT", [105, 106]]]], ["calgarske-listy_2003_unor_ocr.txt", "Sna\u017e\u00edm se na toto t\u00e9ma zav\u00e9st \u0159e\u010d s pos\u00e1dkou, ale moc se nedov\u00edd\u00e1m.", [["Sna\u017e\u00edm", "sna\u017eit", "VERB", [0, 6]], ["se", "se", "PRON", [7, 9]], ["na", "na", "ADP", [10, 12]], ["toto", "tento", "DET", [13, 17]], ["t\u00e9ma", "t\u00e9ma", "NOUN", [18, 22]], ["zav\u00e9st", "zav\u00e9st", "VERB", [23, 29]], ["\u0159e\u010d", "\u0159e\u010d", "NOUN", [30, 33]], ["s", "s", "ADP", [34, 35]], ["pos\u00e1dkou", "pos\u00e1dka", "NOUN", [36, 44]], [",", ",", "PUNCT", [44, 45]], ["ale", "ale", "CCONJ", [46, 49]], ["moc", "moc", "ADV", [50, 53]], ["se", "se", "PRON", [54, 56]], ["nedov\u00edd\u00e1m", "dov\u00eddat", "VERB", [57, 66]], [".", ".", "PUNCT", [66, 67]]]], ["calgarske-listy_2003_unor_ocr.txt", "Chyt\u00e1 se prost\u011b na povrchu a rychlost osmi V\u00e1noce na Yukonu.", [["Chyt\u00e1", "chytat", "VERB", [0, 5]], ["se", "se", "PRON", [6, 8]], ["prost\u011b", "prost\u011b", "ADV", [9, 15]], ["na", "na", "ADP", [16, 18]], ["povrchu", "povrch", "NOUN", [19, 26]], ["a", "a", "CCONJ", [27, 28]], ["rychlost", "rychlost", "NOUN", [29, 37]], ["osmi", "osm", "NUM", [38, 42]], ["V\u00e1noce", "V\u00e1noce", "NOUN", [43, 49]], ["na", "na", "ADP", [50, 52]], ["Yukonu", "Yukon", "PROPN", [53, 59]], [".", ".", "PUNCT", [59, 60]]]], ["calgarske-listy_2003_unor_ocr.txt", "Trampsk\u00e1 osada TUL\u00c1CI SEVERU : napsala M\u00cdVALA.", [["Trampsk\u00e1", "trampsk\u00fd", "ADJ", [0, 8]], ["osada", "osada", "NOUN", [9, 14]], ["TUL\u00c1CI", "tul\u00e1k", "NOUN", [15, 21]], ["SEVERU", "sever", "NOUN", [22, 28]], [":", ":", "PUNCT", [29, 30]], ["napsala", "napsat", "VERB", [31, 38]], ["M\u00cdVALA", "m\u00edvat", "VERB", [39, 45]], [".", ".", "PUNCT", [45, 46]]]], ["calgarske-listy_2003_unor_ocr.txt", "Byl \u0161t\u011bdr\u00fd den roku 1897.", [["Byl", "b\u00fdt", "AUX", [0, 3]], ["\u0161t\u011bdr\u00fd", "\u0161t\u011bdr\u00fd", "ADJ", [4, 10]], ["den", "den", "NOUN", [11, 14]], ["roku", "rok", "NOUN", [15, 19]], ["1897", "1897", "NUM", [20, 24]], [".", ".", "PUNCT", [24, 25]]]], ["calgarske-listy_2003_unor_ocr.txt", "V \u00fa\u017easn\u00e9m b\u00edl\u00e9m tichu bylo sly\u0161et jen oddechov\u00e1n\u00ed ps\u016f a \u0161ust\u011bn\u00ed skluznic po such\u00e9m krystalov\u00e9m sn\u011bhu.", [["V", "v", "ADP", [0, 1]], ["\u00fa\u017easn\u00e9m", "\u00fa\u017easn\u00fd", "ADJ", [2, 9]], ["b\u00edl\u00e9m", "b\u00edl\u00fd", "ADJ", [10, 15]], ["tichu", "ticho", "NOUN", [16, 21]], ["bylo", "b\u00fdt", "AUX", [22, 26]], ["sly\u0161et", "sly\u0161et", "VERB", [27, 33]], ["jen", "jen", "PART", [34, 37]], ["oddechov\u00e1n\u00ed", "oddechov\u00e1n\u00ed", "NOUN", [38, 49]], ["ps\u016f", "pes", "NOUN", [50, 53]], ["a", "a", "CCONJ", [54, 55]], ["\u0161ust\u011bn\u00ed", "\u0161ust\u011bn\u00ed", "NOUN", [56, 63]], ["skluznic", "skluznice", "NOUN", [64, 72]], ["po", "po", "ADP", [73, 75]], ["such\u00e9m", "such\u00fd", "ADJ", [76, 82]], ["krystalov\u00e9m", "krystalov\u00fd", "ADJ", [83, 94]], ["sn\u011bhu", "sn\u00edh", "NOUN", [95, 100]], [".", ".", "PUNCT", [100, 101]]]], ["calgarske-listy_2003_unor_ocr.txt", "Pol\u00e1rn\u00ed z\u00e1\u0159 spou\u0161t\u011bla na zmrzlou zemi zelenav\u00e9 z\u00e1clony a ve sn\u011bhu se t\u0159pitily drobn\u00e9 st\u0159\u00edbrn\u00e9 krystalky.", [["Pol\u00e1rn\u00ed", "pol\u00e1rn\u00ed", "ADJ", [0, 7]], ["z\u00e1\u0159", "z\u00e1\u0159", "NOUN", [8, 11]], ["spou\u0161t\u011bla", "spou\u0161t\u011bt", "VERB", [12, 21]], ["na", "na", "ADP", [22, 24]], ["zmrzlou", "zmrzl\u00fd", "ADJ", [25, 32]], ["zemi", "zem\u011b", "NOUN", [33, 37]], ["zelenav\u00e9", "zelenav\u00fd", "ADJ", [38, 46]], ["z\u00e1clony", "z\u00e1clona", "NOUN", [47, 54]], ["a", "a", "CCONJ", [55, 56]], ["ve", "v", "ADP", [57, 59]], ["sn\u011bhu", "sn\u00edh", "NOUN", [60, 65]], ["se", "se", "PRON", [66, 68]], ["t\u0159pitily", "t\u0159pitit", "VERB", [69, 77]], ["drobn\u00e9", "drobn\u00fd", "ADJ", [78, 84]], ["st\u0159\u00edbrn\u00e9", "st\u0159\u00edbrn\u00fd", "ADJ", [85, 93]], ["krystalky", "krystalka", "NOUN", [94, 103]], [".", ".", "PUNCT", [103, 104]]]], ["calgarske-listy_2003_unor_ocr.txt", "T\u0159i mlad\u00ed zlatokopov\u00e9 tuhle severskou kr\u00e1su nevn\u00edmali.", [["T\u0159i", "t\u0159i", "NUM", [0, 3]], ["mlad\u00ed", "mlad\u00fd", "ADJ", [4, 9]], ["zlatokopov\u00e9", "zlatokop", "NOUN", [10, 21]], ["tuhle", "tenhle", "DET", [22, 27]], ["severskou", "seversk\u00fd", "ADJ", [28, 37]], ["kr\u00e1su", "kr\u00e1sa", "NOUN", [38, 43]], ["nevn\u00edmali", "vn\u00edmat", "VERB", [44, 53]], [".", ".", "PUNCT", [53, 54]]]], ["calgarske-listy_2003_unor_ocr.txt", "M\u011bli ten den za sebou u\u017e t\u0159icet m\u00edl\u00ed, byli promrzl\u00ed, unaven\u00ed a sklesl\u00ed.", [["M\u011bli", "m\u00edt", "VERB", [0, 4]], ["ten", "ten", "DET", [5, 8]], ["den", "den", "NOUN", [9, 12]], ["za", "za", "ADP", [13, 15]], ["sebou", "se", "PRON", [16, 21]], ["u\u017e", "u\u017e", "ADV", [22, 24]], ["t\u0159icet", "t\u0159icet", "NUM", [25, 31]], ["m\u00edl\u00ed", "m\u00edle", "NOUN", [32, 36]], [",", ",", "PUNCT", [36, 37]], ["byli", "b\u00fdt", "AUX", [38, 42]], ["promrzl\u00ed", "promrzl\u00fd", "ADJ", [43, 51]], [",", ",", "PUNCT", [51, 52]], ["unaven\u00ed", "unaven\u00fd", "ADJ", [53, 60]], ["a", "a", "CCONJ", [61, 62]], ["sklesl\u00ed", "sklesl\u00fd", "ADJ", [63, 70]], [".", ".", "PUNCT", [70, 71]]]], ["calgarske-listy_2003_unor_ocr.txt", "\u0160t\u011bdr\u00fd den....jak jin\u00e9 to b\u00fdvalo v jejich domovech dole na jihu!", [["\u0160t\u011bdr\u00fd", "\u0161t\u011bdr\u00fd", "ADJ", [0, 6]], ["den", "den", "NOUN", [7, 10]], [".", ".", "PUNCT", [10, 11]], [".", ".", "PUNCT", [11, 12]], [".", ".", "PUNCT", [12, 13]], [".", ".", "PUNCT", [13, 14]], ["jak", "jak", "ADV", [14, 17]], ["jin\u00e9", "jin\u00fd", "ADJ", [18, 22]], ["to", "ten", "DET", [23, 25]], ["b\u00fdvalo", "b\u00fdvat", "AUX", [26, 32]], ["v", "v", "ADP", [33, 34]], ["jejich", "jeho", "DET", [35, 41]], ["domovech", "domov", "NOUN", [42, 50]], ["dole", "d\u016fl", "NOUN", [51, 55]], ["na", "na", "ADP", [56, 58]], ["jihu", "jih", "NOUN", [59, 63]], ["!", "!", "PUNCT", [63, 64]]]], ["calgarske-listy_2003_unor_ocr.txt", "Johny Lind, nejstar\u0161\u00ed z trojice ve sv\u00fdch dvaadvaceti letech p\u0159em\u00fd\u0161lel, jestli Grace Sommerton je\u0161t\u011b na n\u011bj \u010dek\u00e1 - pro\u010d by vlastn\u011b m\u011bla?", [["Johny", "Johny", "PROPN", [0, 5]], ["Lind", "Lind", "PROPN", [6, 10]], [",", ",", "PUNCT", [10, 11]], ["nejstar\u0161\u00ed", "star\u00fd", "ADJ", [12, 21]], ["z", "z", "ADP", [22, 23]], ["trojice", "trojice", "NOUN", [24, 31]], ["ve", "v", "ADP", [32, 34]], ["sv\u00fdch", "sv\u016fj", "DET", [35, 40]], ["dvaadvaceti", "dvaadvacet", "NUM", [41, 52]], ["letech", "l\u00e9ta", "NOUN", [53, 59]], ["p\u0159em\u00fd\u0161lel", "p\u0159em\u00fd\u0161let", "VERB", [60, 69]], [",", ",", "PUNCT", [69, 70]], ["jestli", "jestli", "SCONJ", [71, 77]], ["Grace", "Grace", "PROPN", [78, 83]], ["Sommerton", "Sommerton", "PROPN", [84, 93]], ["je\u0161t\u011b", "je\u0161t\u011b", "ADV", [94, 99]], ["na", "na", "ADP", [100, 102]], ["n\u011bj", "on", "PRON", [103, 106]], ["\u010dek\u00e1", "\u010dekat", "VERB", [107, 111]], ["-", "-", "PUNCT", [112, 113]], ["pro\u010d", "pro\u010d", "ADV", [114, 118]], ["by", "b\u00fdt", "AUX", [119, 121]], ["vlastn\u011b", "vlastn\u011b", "ADV", [122, 129]], ["m\u011bla", "m\u00edt", "VERB", [130, 134]], ["?", "?", "PUNCT", [134, 135]]]], ["calgarske-listy_2003_unor_ocr.txt", "Odjel tak narychlo a na dopisy odtud se ned\u00e1 spol\u00e9hat.", [["Odjel", "odjet", "VERB", [0, 5]], ["tak", "tak", "ADV", [6, 9]], ["narychlo", "narychlo", "ADV", [10, 18]], ["a", "a", "CCONJ", [19, 20]], ["na", "na", "ADP", [21, 23]], ["dopisy", "dopis", "NOUN", [24, 30]], ["odtud", "odtud", "ADV", [31, 36]], ["se", "se", "PRON", [37, 39]], ["ned\u00e1", "d\u00e1t", "VERB", [40, 44]], ["spol\u00e9hat", "spol\u00e9hat", "VERB", [45, 53]], [".", ".", "PUNCT", [53, 54]]]], ["calgarske-listy_2003_unor_ocr.txt", "Bill Wilkinson myslel na svou m\u00e1mu, po t\u00e1tov\u011b smrti z\u016fstala sama, nev\u00ed ani jestli je on na \u017eivu - ta asi nem\u00e1 p\u011bkn\u00e9 v\u00e1noce.", [["Bill", "Bill", "PROPN", [0, 4]], ["Wilkinson", "Wilkinson", "PROPN", [5, 14]], ["myslel", "myslit", "VERB", [15, 21]], ["na", "na", "ADP", [22, 24]], ["svou", "sv\u016fj", "DET", [25, 29]], ["m\u00e1mu", "m\u00e1ma", "NOUN", [30, 34]], [",", ",", "PUNCT", [34, 35]], ["po", "po", "ADP", [36, 38]], ["t\u00e1tov\u011b", "t\u00e1tov", "NOUN", [39, 45]], ["smrti", "smrt", "NOUN", [46, 51]], ["z\u016fstala", "z\u016fstat", "VERB", [52, 59]], ["sama", "sam\u00fd", "DET", [60, 64]], [",", ",", "PUNCT", [64, 65]], ["nev\u00ed", "v\u011bd\u011bt", "VERB", [66, 70]], ["ani", "ani", "CCONJ", [71, 74]], ["jestli", "jestli", "SCONJ", [75, 81]], ["je", "b\u00fdt", "AUX", [82, 84]], ["on", "on", "PRON", [85, 87]], ["na", "na", "ADP", [88, 90]], ["\u017eivu", "\u017eivo", "NOUN", [91, 95]], ["-", "-", "PUNCT", [96, 97]], ["ta", "ten", "DET", [98, 100]], ["asi", "asi", "PART", [101, 104]], ["nem\u00e1", "m\u00edt", "VERB", [105, 109]], ["p\u011bkn\u00e9", "p\u011bkn\u00fd", "ADJ", [110, 115]], ["v\u00e1noce", "v\u00e1noce", "NOUN", [116, 122]], [".", ".", "PUNCT", [122, 123]]]], ["calgarske-listy_2003_unor_ocr.txt", "Dave Mittchel byl v duchu tak\u00e9 doma v uzl\u016f je ta optim\u00e1ln\u00ed a basta.", [["Dave", "Dave", "PROPN", [0, 4]], ["Mittchel", "Mittchel", "PROPN", [5, 13]], ["byl", "b\u00fdt", "AUX", [14, 17]], ["v", "v", "ADP", [18, 19]], ["duchu", "duch", "NOUN", [20, 25]], ["tak\u00e9", "tak\u00e9", "ADV", [26, 30]], ["doma", "doma", "ADV", [31, 35]], ["v", "v", "ADP", [36, 37]], ["uzl\u016f", "uzel", "NOUN", [38, 42]], ["je", "b\u00fdt", "AUX", [43, 45]], ["ta", "ten", "DET", [46, 48]], ["optim\u00e1ln\u00ed", "optim\u00e1ln\u00ed", "ADJ", [49, 58]], ["a", "a", "CCONJ", [59, 60]], ["basta", "basta", "NOUN", [61, 66]], [".", ".", "PUNCT", [66, 67]]]], ["calgarske-listy_2003_unor_ocr.txt", "Je to vyzkou\u0161en\u00e9 a zpravidla to funguje dob\u0159e.", [["Je", "b\u00fdt", "AUX", [0, 2]], ["to", "ten", "DET", [3, 5]], ["vyzkou\u0161en\u00e9", "vyzkou\u0161en\u00fd", "ADJ", [6, 16]], ["a", "a", "CCONJ", [17, 18]], ["zpravidla", "zpravidla", "ADV", [19, 28]], ["to", "ten", "DET", [29, 31]], ["funguje", "fungovat", "VERB", [32, 39]], ["dob\u0159e", "dob\u0159e", "ADV", [40, 45]], [".", ".", "PUNCT", [45, 46]]]], ["calgarske-listy_2003_unor_ocr.txt", "Holt m\u00e1me dnes sm\u016flu.", [["Holt", "holt", "ADV", [0, 4]], ["m\u00e1me", "m\u00edt", "VERB", [5, 9]], ["dnes", "dnes", "ADV", [10, 14]], ["sm\u016flu", "sm\u016fla", "NOUN", [15, 20]], [".", ".", "PUNCT", [20, 21]]]], ["calgarske-listy_2003_unor_ocr.txt", "V\u00edm, \u017ee se pohybujeme nad hlubinou okolo 600-900 metr\u016f a \u017ee ryby se vyskytuj\u00ed tak do sto metr\u016f.", [["V\u00edm", "v\u011bd\u011bt", "VERB", [0, 3]], [",", ",", "PUNCT", [3, 4]], ["\u017ee", "\u017ee", "SCONJ", [5, 7]], ["se", "se", "PRON", [8, 10]], ["pohybujeme", "pohybovat", "VERB", [11, 21]], ["nad", "nad", "ADP", [22, 25]], ["hlubinou", "hlubina", "NOUN", [26, 34]], ["okolo", "okolo", "ADP", [35, 40]], ["600", "600", "NUM", [41, 44]], ["-", "-", "PUNCT", [44, 45]], ["900", "900", "NUM", [45, 48]], ["metr\u016f", "metr", "NOUN", [49, 54]], ["a", "a", "CCONJ", [55, 56]], ["\u017ee", "\u017ee", "SCONJ", [57, 59]], ["ryby", "ryba", "NOUN", [60, 64]], ["se", "se", "PRON", [65, 67]], ["vyskytuj\u00ed", "vyskytovat", "VERB", [68, 77]], ["tak", "tak", "ADV", [78, 81]], ["do", "do", "ADP", [82, 84]], ["sto", "sto", "NUM", [85, 88]], ["metr\u016f", "metr", "NOUN", [89, 94]], [".", ".", "PUNCT", [94, 95]]]], ["calgarske-listy_2003_unor_ocr.txt", "V\u00edm, \u017ee p\u0159i lovu losos\u016f zkou\u0161\u00edme r\u016fznou hloubku, a nakonec vol\u00edme tu, kde m\u00e1me nejv\u011bt\u0161\u00ed po\u010det z\u00e1b\u011br\u016f.", [["V\u00edm", "v\u011bd\u011bt", "VERB", [0, 3]], [",", ",", "PUNCT", [3, 4]], ["\u017ee", "\u017ee", "SCONJ", [5, 7]], ["p\u0159i", "p\u0159i", "ADP", [8, 11]], ["lovu", "lov", "NOUN", [12, 16]], ["losos\u016f", "losos", "NOUN", [17, 23]], ["zkou\u0161\u00edme", "zkou\u0161et", "VERB", [24, 32]], ["r\u016fznou", "r\u016fzn\u00fd", "ADJ", [33, 39]], ["hloubku", "hloubka", "NOUN", [40, 47]], [",", ",", "PUNCT", [47, 48]], ["a", "a", "CCONJ", [49, 50]], ["nakonec", "nakonec", "ADV", [51, 58]], ["vol\u00edme", "volit", "VERB", [59, 65]], ["tu", "tu", "ADV", [66, 68]], [",", ",", "PUNCT", [68, 69]], ["kde", "kde", "ADV", [70, 73]], ["m\u00e1me", "m\u00edt", "VERB", [74, 78]], ["nejv\u011bt\u0161\u00ed", "velk\u00fd", "ADJ", [79, 87]], ["po\u010det", "po\u010det", "NOUN", [88, 93]], ["z\u00e1b\u011br\u016f", "z\u00e1b\u011br", "NOUN", [94, 100]], [".", ".", "PUNCT", [100, 101]]]], ["calgarske-listy_2003_unor_ocr.txt", "To se m\u016f\u017ee m\u011bnit b\u011bhem hodiny n\u011bkolikr\u00e1t.", [["To", "ten", "DET", [0, 2]], ["se", "se", "PRON", [3, 5]], ["m\u016f\u017ee", "moci", "VERB", [6, 10]], ["m\u011bnit", "m\u011bnit", "VERB", [11, 16]], ["b\u011bhem", "b\u011bhem", "ADP", [17, 22]], ["hodiny", "hodina", "NOUN", [23, 29]], ["n\u011bkolikr\u00e1t", "n\u011bkolikr\u00e1t", "ADV", [30, 40]], [".", ".", "PUNCT", [40, 41]]]], ["calgarske-listy_2003_unor_ocr.txt", "Ka\u017edop\u00e1dn\u011b chytat na t\u0159i pruty ve stejn\u00e9 hloubce, v tomto p\u0159\u00edpad\u011b na povrchu a nezkusit t\u0159eba m\u00edrnou hloubku, je mi trochu podez\u0159el\u00e9.", [["Ka\u017edop\u00e1dn\u011b", "ka\u017edop\u00e1dn\u011b", "ADV", [0, 10]], ["chytat", "chytat", "VERB", [11, 17]], ["na", "na", "ADP", [18, 20]], ["t\u0159i", "t\u0159i", "NUM", [21, 24]], ["pruty", "prut", "NOUN", [25, 30]], ["ve", "v", "ADP", [31, 33]], ["stejn\u00e9", "stejn\u00fd", "ADJ", [34, 40]], ["hloubce", "hloubka", "NOUN", [41, 48]], [",", ",", "PUNCT", [48, 49]], ["v", "v", "ADP", [50, 51]], ["tomto", "tento", "DET", [52, 57]], ["p\u0159\u00edpad\u011b", "p\u0159\u00edpad", "NOUN", [58, 65]], ["na", "na", "ADP", [66, 68]], ["povrchu", "povrch", "NOUN", [69, 76]], ["a", "a", "CCONJ", [77, 78]], ["nezkusit", "zkusit", "VERB", [79, 87]], ["t\u0159eba", "t\u0159eba", "PART", [88, 93]], ["m\u00edrnou", "m\u00edrn\u00fd", "ADJ", [94, 100]], ["hloubku", "hloubka", "NOUN", [101, 108]], [",", ",", "PUNCT", [108, 109]], ["je", "b\u00fdt", "AUX", [110, 112]], ["mi", "j\u00e1", "PRON", [113, 115]], ["trochu", "trochu", "ADV", [116, 122]], ["podez\u0159el\u00e9", "podez\u0159el\u00fd", "ADJ", [123, 132]], [".", ".", "PUNCT", [132, 133]]]], ["calgarske-listy_2003_unor_ocr.txt", "Lo\u010f samoz\u0159ejm\u011b mus\u00ed b\u00fdt vybavena sonografem, schopn\u00fdm identifikovat jednotliv\u00e9 ryby i jejich hejna a\u017e do hloubky 200 m, ale na ten nevid\u00edm, proto\u017ee lo\u010f je patrov\u00e1 a m\u016fstek je naho\u0159e, p\u0159\u00edstupn\u00fd jen pos\u00e1dce.", [["Lo\u010f", "lo\u010f", "NOUN", [0, 3]], ["samoz\u0159ejm\u011b", "samoz\u0159ejm\u011b", "ADV", [4, 14]], ["mus\u00ed", "muset", "VERB", [15, 19]], ["b\u00fdt", "b\u00fdt", "AUX", [20, 23]], ["vybavena", "vybaven\u00fd", "ADJ", [24, 32]], ["sonografem", "sonograf", "NOUN", [33, 43]], [",", ",", "PUNCT", [43, 44]], ["schopn\u00fdm", "schopn\u00fd", "ADJ", [45, 53]], ["identifikovat", "identifikovat", "VERB", [54, 67]], ["jednotliv\u00e9", "jednotliv\u00fd", "ADJ", [68, 78]], ["ryby", "ryba", "NOUN", [79, 83]], ["i", "i", "CCONJ", [84, 85]], ["jejich", "jeho", "DET", [86, 92]], ["hejna", "hejno", "NOUN", [93, 98]], ["a\u017e", "a\u017e", "PART", [99, 101]], ["do", "do", "ADP", [102, 104]], ["hloubky", "hloubka", "NOUN", [105, 112]], ["200", "200", "NUM", [113, 116]], ["m", "metr", "NOUN", [117, 118]], [",", ",", "PUNCT", [118, 119]], ["ale", "ale", "CCONJ", [120, 123]], ["na", "na", "ADP", [124, 126]], ["ten", "ten", "DET", [127, 130]], ["nevid\u00edm", "vid\u011bt", "VERB", [131, 138]], [",", ",", "PUNCT", [138, 139]], ["proto\u017ee", "proto\u017ee", "SCONJ", [140, 147]], ["lo\u010f", "lo\u010f", "NOUN", [148, 151]], ["je", "b\u00fdt", "AUX", [152, 154]], ["patrov\u00e1", "patrov\u00fd", "ADJ", [155, 162]], ["a", "a", "CCONJ", [163, 164]], ["m\u016fstek", "m\u016fstek", "NOUN", [165, 171]], ["je", "b\u00fdt", "AUX", [172, 174]], ["naho\u0159e", "naho\u0159e", "ADV", [175, 181]], [",", ",", "PUNCT", [181, 182]], ["p\u0159\u00edstupn\u00fd", "p\u0159\u00edstupn\u00fd", "ADJ", [183, 192]], ["jen", "jen", "ADV", [193, 196]], ["pos\u00e1dce", "pos\u00e1dka", "NOUN", [197, 204]], [".", ".", "PUNCT", [204, 205]]]], ["calgarske-listy_2003_unor_ocr.txt", "Dal\u0161\u00ed podivnost oproti kanadsk\u00fdm zvyklostem.", [["Dal\u0161\u00ed", "dal\u0161\u00ed", "ADJ", [0, 5]], ["podivnost", "podivnost", "NOUN", [6, 15]], ["oproti", "oproti", "ADP", [16, 22]], ["kanadsk\u00fdm", "kanadsk\u00fd", "ADJ", [23, 32]], ["zvyklostem", "zvyklost", "NOUN", [33, 43]], [".", ".", "PUNCT", [43, 44]]]], ["calgarske-listy_2003_unor_ocr.txt", "M\u00e1m z toho pocity v\u00edce ne\u017e sm\u00ed\u0161en\u00e9 a proto nakonec p\u00ed\u0161i toto pov\u00edd\u00e1n\u00ed.", [["M\u00e1m", "m\u00edt", "VERB", [0, 3]], ["z", "z", "ADP", [4, 5]], ["toho", "ten", "DET", [6, 10]], ["pocity", "pocit", "NOUN", [11, 17]], ["v\u00edce", "v\u00edce", "ADV", [18, 22]], ["ne\u017e", "ne\u017e", "SCONJ", [23, 26]], ["sm\u00ed\u0161en\u00e9", "sm\u00ed\u0161en\u00fd", "ADJ", [27, 34]], ["a", "a", "CCONJ", [35, 36]], ["proto", "proto", "CCONJ", [37, 42]], ["nakonec", "nakonec", "ADV", [43, 50]], ["p\u00ed\u0161i", "ps\u00e1t", "VERB", [51, 55]], ["toto", "tento", "DET", [56, 60]], ["pov\u00edd\u00e1n\u00ed", "pov\u00edd\u00e1n\u00ed", "NOUN", [61, 69]], [".", ".", "PUNCT", [69, 70]]]], ["calgarske-listy_2003_unor_ocr.txt", "Ne abych p\u0159\u00edpadn\u00e9 z\u00e1jemce o tento druh kratochv\u00edle odradil, ale abych je p\u0159inutil myslet dvakr\u00e1t.", [["Ne", "ne", "PART", [0, 2]], ["aby", "aby", "SCONJ", [-18218, -18218]], ["bych", "b\u00fdt", "AUX", [-18218, -18218]], ["p\u0159\u00edpadn\u00e9", "p\u0159\u00edpadn\u00fd", "ADJ", [9, 17]], ["z\u00e1jemce", "z\u00e1jemce", "NOUN", [18, 25]], ["o", "o", "ADP", [26, 27]], ["tento", "tento", "DET", [28, 33]], ["druh", "druh", "NOUN", [34, 38]], ["kratochv\u00edle", "kratochv\u00edle", "NOUN", [39, 50]], ["odradil", "odradit", "VERB", [51, 58]], [",", ",", "PUNCT", [58, 59]], ["ale", "ale", "CCONJ", [60, 63]], ["aby", "aby", "SCONJ", [-18218, -18218]], ["bych", "b\u00fdt", "AUX", [-18218, -18218]], ["je", "on", "PRON", [70, 72]], ["p\u0159inutil", "p\u0159inutit", "VERB", [73, 81]], ["myslet", "myslit", "VERB", [82, 88]], ["dvakr\u00e1t", "dvakr\u00e1t", "ADV", [89, 96]], [".", ".", "PUNCT", [96, 97]]]], ["calgarske-listy_2003_unor_ocr.txt", "Moji dva souputn\u00edci jsou viditeln\u011b otr\u00e1veni je\u0161t\u011b v\u00edce ne\u017e j\u00e1, ale lou\u010den\u00ed s m\u00edrn\u011b omluvn\u011b se tv\u00e1\u0159\u00edc\u00ed pos\u00e1dkou prob\u00edh\u00e1 nakonec v kulturn\u00edm stylu.", [["Moji", "m\u016fj", "DET", [0, 4]], ["dva", "dva", "NUM", [5, 8]], ["souputn\u00edci", "souputn\u00edk", "NOUN", [9, 19]], ["jsou", "b\u00fdt", "AUX", [20, 24]], ["viditeln\u011b", "viditeln\u011b", "ADV", [25, 34]], ["otr\u00e1veni", "otr\u00e1ven\u00fd", "ADJ", [35, 43]], ["je\u0161t\u011b", "je\u0161t\u011b", "ADV", [44, 49]], ["v\u00edce", "v\u00edce", "ADV", [50, 54]], ["ne\u017e", "ne\u017e", "SCONJ", [55, 58]], ["j\u00e1", "j\u00e1", "PRON", [59, 61]], [",", ",", "PUNCT", [61, 62]], ["ale", "ale", "CCONJ", [63, 66]], ["lou\u010den\u00ed", "lou\u010den\u00ed", "NOUN", [67, 74]], ["s", "s", "ADP", [75, 76]], ["m\u00edrn\u011b", "m\u00edrn\u011b", "ADV", [77, 82]], ["omluvn\u011b", "omluvn\u011b", "ADV", [83, 90]], ["se", "s", "ADP", [91, 93]], ["tv\u00e1\u0159\u00edc\u00ed", "tv\u00e1\u0159\u00edc\u00ed", "ADJ", [94, 101]], ["pos\u00e1dkou", "pos\u00e1dka", "NOUN", [102, 110]], ["prob\u00edh\u00e1", "prob\u00edhat", "VERB", [111, 118]], ["nakonec", "nakonec", "ADV", [119, 126]], ["v", "v", "ADP", [127, 128]], ["kulturn\u00edm", "kulturn\u00ed", "ADJ", [129, 138]], ["stylu", "styl", "NOUN", [139, 144]], [".", ".", "PUNCT", [144, 145]]]], ["calgarske-listy_2003_unor_ocr.txt", "T\u011bch p\u016fltuctu \u017elutoploutv\u00fdch tu\u0148\u00e1k\u016f, kter\u00e9 jsem nakonec dom\u016f p\u0159inesl se uk\u00e1zalo b\u00fdt velmi chutn\u00fdmi, co\u017e nakonec nebylo pro mne \u017e\u00e1dnou novinkou, nebo\u0165 jsem je m\u011bl opakovan\u011b zde v m\u00edstn\u00ed restauraci.", [["T\u011bch", "ten", "DET", [0, 4]], ["p\u016fltuctu", "p\u016fltuct", "NOUN", [5, 13]], ["\u017elutoploutv\u00fdch", "\u017elutoploutv\u00fd", "ADJ", [14, 28]], ["tu\u0148\u00e1k\u016f", "tu\u0148\u00e1k", "NOUN", [29, 35]], [",", ",", "PUNCT", [35, 36]], ["kter\u00e9", "kter\u00fd", "DET", [37, 42]], ["jsem", "b\u00fdt", "AUX", [43, 47]], ["nakonec", "nakonec", "ADV", [48, 55]], ["dom\u016f", "dom\u016f", "ADV", [56, 60]], ["p\u0159inesl", "p\u0159in\u00e9st", "VERB", [61, 68]], ["se", "se", "PRON", [69, 71]], ["uk\u00e1zalo", "uk\u00e1zat", "VERB", [72, 79]], ["b\u00fdt", "b\u00fdt", "AUX", [80, 83]], ["velmi", "velmi", "ADV", [84, 89]], ["chutn\u00fdmi", "chutn\u00fd", "ADJ", [90, 98]], [",", ",", "PUNCT", [98, 99]], ["co\u017e", "co\u017e", "PRON", [100, 103]], ["nakonec", "nakonec", "ADV", [104, 111]], ["nebylo", "b\u00fdt", "AUX", [112, 118]], ["pro", "pro", "ADP", [119, 122]], ["mne", "j\u00e1", "PRON", [123, 126]], ["\u017e\u00e1dnou", "\u017e\u00e1dn\u00fd", "DET", [127, 133]], ["novinkou", "novinka", "NOUN", [134, 142]], [",", ",", "PUNCT", [142, 143]], ["nebo\u0165", "nebo\u0165", "CCONJ", [144, 149]], ["jsem", "b\u00fdt", "AUX", [150, 154]], ["je", "on", "PRON", [155, 157]], ["m\u011bl", "m\u00edt", "VERB", [158, 161]], ["opakovan\u011b", "opakovan\u011b", "ADV", [162, 171]], ["zde", "zde", "ADV", [172, 175]], ["v", "v", "ADP", [176, 177]], ["m\u00edstn\u00ed", "m\u00edstn\u00ed", "ADJ", [178, 184]], ["restauraci", "restaurace", "NOUN", [185, 195]], [".", ".", "PUNCT", [195, 196]]]], ["calgarske-listy_2003_unor_ocr.txt", "Nav\u00edc \u010derstv\u00e1 ryba je \u010derstv\u00e1 ryba.", [["Nav\u00edc", "nav\u00edc", "ADV", [0, 5]], ["\u010derstv\u00e1", "\u010derstv\u00fd", "ADJ", [6, 13]], ["ryba", "ryba", "NOUN", [14, 18]], ["je", "b\u00fdt", "AUX", [19, 21]], ["\u010derstv\u00e1", "\u010derstv\u00fd", "ADJ", [22, 29]], ["ryba", "ryba", "NOUN", [30, 34]], [".", ".", "PUNCT", [34, 35]]]], ["calgarske-listy_2003_unor_ocr.txt", "P\u0159esto, \u017ee byli mal\u00ed, byli docela masit\u00ed (tmav\u011b \u010derven\u00e9 maso, skoro jako hov\u011bz\u00ed) m\u011bli m\u00e1lo kost\u00ed a vysta\u010dili nejen na \u0161t\u011bdrove\u010dern\u00ed ve\u010de\u0159i, ale je\u0161t\u011b jsme z nich m\u011bli dv\u011b j\u00eddla.", [["P\u0159esto", "p\u0159esto", "ADV", [0, 6]], [",", ",", "PUNCT", [6, 7]], ["\u017ee", "\u017ee", "SCONJ", [8, 10]], ["byli", "b\u00fdt", "AUX", [11, 15]], ["mal\u00ed", "mal\u00fd", "ADJ", [16, 20]], [",", ",", "PUNCT", [20, 21]], ["byli", "b\u00fdt", "AUX", [22, 26]], ["docela", "docela", "ADV", [27, 33]], ["masit\u00ed", "masit\u00fd", "ADJ", [34, 40]], ["(", "(", "PUNCT", [41, 42]], ["tmav\u011b", "tmav\u011b", "ADV", [42, 47]], ["\u010derven\u00e9", "\u010derven\u00fd", "ADJ", [48, 55]], ["maso", "maso", "NOUN", [56, 60]], [",", ",", "PUNCT", [60, 61]], ["skoro", "skoro", "ADV", [62, 67]], ["jako", "jako", "SCONJ", [68, 72]], ["hov\u011bz\u00ed", "hov\u011bz\u00ed", "ADJ", [73, 79]], [")", ")", "PUNCT", [79, 80]], ["m\u011bli", "m\u00edt", "VERB", [81, 85]], ["m\u00e1lo", "m\u00e1lo", "DET", [86, 90]], ["kost\u00ed", "kost", "NOUN", [91, 96]], ["a", "a", "CCONJ", [97, 98]], ["vysta\u010dili", "vysta\u010dit", "VERB", [99, 108]], ["nejen", "nejen", "ADV", [109, 114]], ["na", "na", "ADP", [115, 117]], ["\u0161t\u011bdrove\u010dern\u00ed", "\u0161t\u011bdrove\u010dern\u00ed", "ADJ", [118, 131]], ["ve\u010de\u0159i", "ve\u010de\u0159e", "NOUN", [132, 138]], [",", ",", "PUNCT", [138, 139]], ["ale", "ale", "CCONJ", [140, 143]], ["je\u0161t\u011b", "je\u0161t\u011b", "ADV", [144, 149]], ["jsme", "b\u00fdt", "AUX", [150, 154]], ["z", "z", "ADP", [155, 156]], ["nich", "on", "PRON", [157, 161]], ["m\u011bli", "m\u00edt", "VERB", [162, 166]], ["dv\u011b", "dva", "NUM", [167, 170]], ["j\u00eddla", "j\u00eddlo", "NOUN", [171, 176]], [".", ".", "PUNCT", [176, 177]]]], ["calgarske-listy_2003_unor_ocr.txt", "Tak\u017ee tu \u0160t\u011bdrove\u010dern\u00ed rybu jsem si nakonec chytil, i kdy\u017e zp\u016fsobem na hony vzd\u00e1len\u00fdm m\u00fdm p\u016fvodn\u00edm p\u0159edstav\u00e1m.", [["Tak\u017ee", "tak\u017ee", "SCONJ", [0, 5]], ["tu", "ten", "DET", [6, 8]], ["\u0160t\u011bdrove\u010dern\u00ed", "\u0161t\u011bdrove\u010dern\u00ed", "ADJ", [9, 22]], ["rybu", "ryba", "NOUN", [23, 27]], ["jsem", "b\u00fdt", "AUX", [28, 32]], ["si", "se", "PRON", [33, 35]], ["nakonec", "nakonec", "ADV", [36, 43]], ["chytil", "chytit", "VERB", [44, 50]], [",", ",", "PUNCT", [50, 51]], ["i", "i", "CCONJ", [52, 53]], ["kdy\u017e", "kdy\u017e", "SCONJ", [54, 58]], ["zp\u016fsobem", "zp\u016fsob", "NOUN", [59, 67]], ["na", "na", "ADP", [68, 70]], ["hony", "hon", "NOUN", [71, 75]], ["vzd\u00e1len\u00fdm", "vzd\u00e1len\u00fd", "ADJ", [76, 85]], ["m\u00fdm", "m\u016fj", "DET", [86, 89]], ["p\u016fvodn\u00edm", "p\u016fvodn\u00ed", "ADJ", [90, 98]], ["p\u0159edstav\u00e1m", "p\u0159edstava", "NOUN", [99, 109]], [".", ".", "PUNCT", [109, 110]]]], ["calgarske-listy_2003_unor_ocr.txt", "Tak u\u017e to holt leckdy v \u017eivot\u011b chod\u00ed.", [["Tak", "tak", "ADV", [0, 3]], ["u\u017e", "u\u017e", "ADV", [4, 6]], ["to", "ten", "DET", [7, 9]], ["holt", "holt", "ADV", [10, 14]], ["leckdy", "leckdy", "ADV", [15, 21]], ["v", "v", "ADP", [22, 23]], ["\u017eivot\u011b", "\u017eivot", "NOUN", [24, 30]], ["chod\u00ed", "chodit", "VERB", [31, 36]], [".", ".", "PUNCT", [36, 37]]]], ["calgarske-listy_2003_unor_ocr.txt", "Pov\u0161imn\u011bte si pros\u00edm, \u017ee tato pov\u00eddka je vlastn\u011b o \u0161esti \u010dudl\u00e1ch.", [["Pov\u0161imn\u011bte", "pov\u0161imnout", "VERB", [0, 10]], ["si", "se", "PRON", [11, 13]], ["pros\u00edm", "prosit", "VERB", [14, 20]], [",", ",", "PUNCT", [20, 21]], ["\u017ee", "\u017ee", "SCONJ", [22, 24]], ["tato", "tento", "DET", [25, 29]], ["pov\u00eddka", "pov\u00eddka", "NOUN", [30, 37]], ["je", "b\u00fdt", "AUX", [38, 40]], ["vlastn\u011b", "vlastn\u011b", "ADV", [41, 48]], ["o", "o", "ADP", [49, 50]], ["\u0161esti", "\u0161est", "NUM", [51, 56]], ["\u010dudl\u00e1ch", "\u010dudla", "NOUN", [57, 64]], [".", ".", "PUNCT", [64, 65]]]], ["calgarske-listy_2003_unor_ocr.txt", "A pak \u017ee z hovna bi\u010d neuplete\u0161.", [["A", "a", "CCONJ", [0, 1]], ["pak", "pak", "ADV", [2, 5]], ["\u017ee", "\u017ee", "SCONJ", [6, 8]], ["z", "z", "ADP", [9, 10]], ["hovna", "hovna", "NOUN", [11, 16]], ["bi\u010d", "bi\u010d", "NOUN", [17, 20]], ["neuplete\u0161", "upl\u00e9st", "VERB", [21, 30]], [".", ".", "PUNCT", [30, 31]]]], ["calgarske-listy_2003_unor_ocr.txt", "Ale moc jsem si nezapraskal....", [["Ale", "ale", "CCONJ", [0, 3]], ["moc", "moc", "ADV", [4, 7]], ["jsem", "b\u00fdt", "AUX", [8, 12]], ["si", "se", "PRON", [13, 15]], ["nezapraskal", "zapraskat", "VERB", [16, 27]], [".", ".", "PUNCT", [27, 28]], [".", ".", "PUNCT", [28, 29]], [".", ".", "PUNCT", [29, 30]], [".", ".", "PUNCT", [30, 31]]]], ["calgarske-listy_2003_unor_ocr.txt", "Maui, Hawaii, prosinec 2002.", [["Maui", "Maui", "PROPN", [0, 4]], [",", ",", "PUNCT", [4, 5]], ["Hawaii", "Hawaii", "PROPN", [6, 12]], [",", ",", "PUNCT", [12, 13]], ["prosinec", "prosinec", "NOUN", [14, 22]], ["2002", "2002", "NUM", [23, 27]], [".", ".", "PUNCT", [27, 28]]]], ["calgarske-listy_2003_unor_ocr.txt", "Texasu.", [["Texasu", "Texas", "PROPN", [0, 6]], [".", ".", "PUNCT", [6, 7]]]], ["calgarske-listy_2003_unor_ocr.txt", "P\u011bt pod nulou u nich byla zima!!!", [["P\u011bt", "p\u011bt", "NUM", [0, 3]], ["pod", "pod", "ADP", [4, 7]], ["nulou", "nula", "NOUN", [8, 13]], ["u", "u", "ADP", [14, 15]], ["nich", "on", "PRON", [16, 20]], ["byla", "b\u00fdt", "AUX", [21, 25]], ["zima", "zima", "NOUN", [26, 30]], ["!", "!", "PUNCT", [30, 31]], ["!", "!", "PUNCT", [31, 32]], ["!", "!", "PUNCT", [32, 33]]]], ["calgarske-listy_2003_unor_ocr.txt", "Co by \u0159ekli tomuhle?", [["Co", "co", "PRON", [0, 2]], ["by", "b\u00fdt", "AUX", [3, 5]], ["\u0159ekli", "\u0159\u00edci", "VERB", [6, 11]], ["tomuhle", "tenhuhl", "DET", [12, 19]], ["?", "?", "PUNCT", [19, 20]]]], ["calgarske-listy_2003_unor_ocr.txt", "Je\u0161t\u011b t\u0159i m\u00edle jim zb\u00fdvaly k jejich srubu na Eldor\u00e1du.", [["Je\u0161t\u011b", "je\u0161t\u011b", "ADV", [0, 5]], ["t\u0159i", "t\u0159i", "NUM", [6, 9]], ["m\u00edle", "m\u00edl", "NOUN", [10, 14]], ["jim", "on", "PRON", [15, 18]], ["zb\u00fdvaly", "zb\u00fdvat", "VERB", [19, 26]], ["k", "k", "ADP", [27, 28]], ["jejich", "jeho", "DET", [29, 35]], ["srubu", "srub", "NOUN", [36, 41]], ["na", "na", "ADP", [42, 44]], ["Eldor\u00e1du", "Eldor\u00e1d", "PROPN", [45, 53]], [".", ".", "PUNCT", [53, 54]]]], ["calgarske-listy_2003_unor_ocr.txt", "Tu najednou v pravo u cesty spat\u0159ili osam\u011bl\u00fd srub.", [["Tu", "tu", "ADV", [0, 2]], ["najednou", "najednou", "ADV", [3, 11]], ["v", "v", "ADP", [12, 13]], ["pravo", "pravo", "NOUN", [14, 19]], ["u", "u", "ADP", [20, 21]], ["cesty", "cesta", "NOUN", [22, 27]], ["spat\u0159ili", "spat\u0159it", "VERB", [28, 36]], ["osam\u011bl\u00fd", "osam\u011bl\u00fd", "ADJ", [37, 44]], ["srub", "srub", "NOUN", [45, 49]], [".", ".", "PUNCT", [49, 50]]]], ["calgarske-listy_2003_unor_ocr.txt", "Tenounk\u00fd prou\u017eek d\u00fdmu stoupal z kom\u00edna.", [["Tenounk\u00fd", "tenounk\u00fd", "ADJ", [0, 8]], ["prou\u017eek", "prou\u017eek", "NOUN", [9, 16]], ["d\u00fdmu", "d\u00fdm", "NOUN", [17, 21]], ["stoupal", "stoupat", "VERB", [22, 29]], ["z", "z", "ADP", [30, 31]], ["kom\u00edna", "kom\u00edn", "NOUN", [32, 38]], [".", ".", "PUNCT", [38, 39]]]], ["calgarske-listy_2003_unor_ocr.txt", "\"Poj\u010fme dovnit\u0159 se oh\u0159\u00e1t\" navrhl Johny.", [["\"", "\"", "PUNCT", [0, 1]], ["Poj\u010fme", "j\u00edt", "VERB", [1, 7]], ["dovnit\u0159", "dovnit\u0159", "ADV", [8, 15]], ["se", "se", "PRON", [16, 18]], ["oh\u0159\u00e1t", "oh\u0159\u00e1t", "VERB", [19, 24]], ["\"", "\"", "PUNCT", [24, 25]], ["navrhl", "navrhnout", "VERB", [26, 32]], ["Johny", "Johny", "PROPN", [33, 38]], [".", ".", "PUNCT", [38, 39]]]], ["calgarske-listy_2003_unor_ocr.txt", "\"Asi jeli na \u0160t\u011bdr\u00fd den do Dawsonu, aspo\u0148 jim roztop\u00edme ohe\u0148!", [["\"", "\"", "PUNCT", [0, 1]], ["Asi", "asi", "PART", [1, 4]], ["jeli", "jet", "VERB", [5, 9]], ["na", "na", "ADP", [10, 12]], ["\u0160t\u011bdr\u00fd", "\u0161t\u011bdr\u00fd", "ADJ", [13, 19]], ["den", "den", "NOUN", [20, 23]], ["do", "do", "ADP", [24, 26]], ["Dawsonu", "Dawson", "PROPN", [27, 34]], [",", ",", "PUNCT", [34, 35]], ["aspo\u0148", "aspo\u0148", "ADV", [36, 41]], ["jim", "on", "PRON", [42, 45]], ["roztop\u00edme", "roztopit", "VERB", [46, 55]], ["ohe\u0148", "ohe\u0148", "NOUN", [56, 60]], ["!", "!", "PUNCT", [60, 61]]]], ["calgarske-listy_2003_unor_ocr.txt", "\"Otev\u0159eli dve\u0159e a ve\u0161li dovnit\u0159.", [["\"", "\"", "PUNCT", [0, 1]], ["Otev\u0159eli", "otev\u0159\u00edt", "VERB", [1, 9]], ["dve\u0159e", "dve\u0159e", "NOUN", [10, 15]], ["a", "a", "CCONJ", [16, 17]], ["ve\u0161li", "vej\u00edt", "VERB", [18, 23]], ["dovnit\u0159", "dovnit\u0159", "ADV", [24, 31]], [".", ".", "PUNCT", [31, 32]]]], ["calgarske-listy_2003_unor_ocr.txt", "Usly\u0161eli tich\u00e9 vzlyk\u00e1n\u00ed a vzdych\u00e1n\u00ed z rohu m\u00edstnosti, kde st\u00e1la postel.", [["Usly\u0161eli", "usly\u0161et", "VERB", [0, 8]], ["tich\u00e9", "tich\u00fd", "ADJ", [9, 14]], ["vzlyk\u00e1n\u00ed", "vzlyk\u00e1n\u00ed", "NOUN", [15, 23]], ["a", "a", "CCONJ", [24, 25]], ["vzdych\u00e1n\u00ed", "vzdych\u00e1n\u00ed", "NOUN", [26, 35]], ["z", "z", "ADP", [36, 37]], ["rohu", "roh", "NOUN", [38, 42]], ["m\u00edstnosti", "m\u00edstnost", "NOUN", [43, 52]], [",", ",", "PUNCT", [52, 53]], ["kde", "kde", "ADV", [54, 57]], ["st\u00e1la", "st\u00e1t", "VERB", [58, 63]], ["postel", "postel", "NOUN", [64, 70]], [".", ".", "PUNCT", [70, 71]]]], ["calgarske-listy_2003_unor_ocr.txt", "Dave nahmatal v kapse sv\u00ed\u010dku a zap\u00e1lil ji.", [["Dave", "Dave", "PROPN", [0, 4]], ["nahmatal", "nahmatat", "VERB", [5, 13]], ["v", "v", "ADP", [14, 15]], ["kapse", "kapsa", "NOUN", [16, 21]], ["sv\u00ed\u010dku", "sv\u00ed\u010dek", "NOUN", [22, 28]], ["a", "a", "CCONJ", [29, 30]], ["zap\u00e1lil", "zap\u00e1lit", "VERB", [31, 38]], ["ji", "on", "PRON", [39, 41]], [".", ".", "PUNCT", [41, 42]]]], ["calgarske-listy_2003_unor_ocr.txt", "V blikotav\u00e9m sv\u011btle uvid\u011bli mladou \u017eenu, le\u017e\u00edc\u00ed v tratoli\u0161ti krve s novorozen\u00fdm d\u00edt\u011btem p\u0159itisknut\u00fdm k prs\u016fm.", [["V", "v", "ADP", [0, 1]], ["blikotav\u00e9m", "blikotav\u00fd", "ADJ", [2, 12]], ["sv\u011btle", "sv\u011btlo", "NOUN", [13, 19]], ["uvid\u011bli", "uvid\u011bt", "VERB", [20, 27]], ["mladou", "mlad\u00fd", "ADJ", [28, 34]], ["\u017eenu", "\u017eena", "NOUN", [35, 39]], [",", ",", "PUNCT", [39, 40]], ["le\u017e\u00edc\u00ed", "le\u017e\u00edc\u00ed", "ADJ", [41, 47]], ["v", "v", "ADP", [48, 49]], ["tratoli\u0161ti", "tratoli\u0161t\u011b", "NOUN", [50, 60]], ["krve", "krev", "NOUN", [61, 65]], ["s", "s", "ADP", [66, 67]], ["novorozen\u00fdm", "novorozen\u00fd", "ADJ", [68, 79]], ["d\u00edt\u011btem", "d\u00edt\u011b", "NOUN", [80, 87]], ["p\u0159itisknut\u00fdm", "p\u0159itisknut\u00fd", "ADJ", [88, 100]], ["k", "k", "ADP", [101, 102]], ["prs\u016fm", "prs", "NOUN", [103, 108]], [".", ".", "PUNCT", [108, 109]]]], ["calgarske-listy_2003_unor_ocr.txt", "P\u0159estala na\u0159\u00edkat a lehce se usm\u00e1la na Davyho, kter\u00fd rychle p\u0159iklekl k jej\u00ed posteli.", [["P\u0159estala", "p\u0159estat", "VERB", [0, 8]], ["na\u0159\u00edkat", "na\u0159\u00edkat", "VERB", [9, 16]], ["a", "a", "CCONJ", [17, 18]], ["lehce", "lehce", "ADV", [19, 24]], ["se", "se", "PRON", [25, 27]], ["usm\u00e1la", "usm\u00e1t", "VERB", [28, 34]], ["na", "na", "ADP", [35, 37]], ["Davyho", "Davy", "PROPN", [38, 44]], [",", ",", "PUNCT", [44, 45]], ["kter\u00fd", "kter\u00fd", "DET", [46, 51]], ["rychle", "rychle", "ADV", [52, 58]], ["p\u0159iklekl", "p\u0159ikleknout", "VERB", [59, 67]], ["k", "k", "ADP", [68, 69]], ["jej\u00ed", "jeho", "DET", [70, 74]], ["posteli", "postel", "NOUN", [75, 82]], [".", ".", "PUNCT", [82, 83]]]], ["calgarske-listy_2003_unor_ocr.txt", "Pak o\u010di zav\u0159ela a z tv\u00e1\u0159e j\u00ed mizel v\u00fdraz bolesti.", [["Pak", "pak", "ADV", [0, 3]], ["o\u010di", "oko", "NOUN", [4, 7]], ["zav\u0159ela", "zav\u0159\u00edt", "VERB", [8, 15]], ["a", "a", "CCONJ", [16, 17]], ["z", "z", "ADP", [18, 19]], ["tv\u00e1\u0159e", "tv\u00e1\u0159", "NOUN", [20, 25]], ["j\u00ed", "on", "PRON", [26, 28]], ["mizel", "mizet", "VERB", [29, 34]], ["v\u00fdraz", "v\u00fdraz", "NOUN", [35, 40]], ["bolesti", "bolest", "NOUN", [41, 48]], [".", ".", "PUNCT", [48, 49]]]], ["calgarske-listy_2003_unor_ocr.txt", "Dave ji chytil za ruku.", [["Dave", "Dave", "PROPN", [0, 4]], ["ji", "on", "PRON", [5, 7]], ["chytil", "chytit", "VERB", [8, 14]], ["za", "za", "ADP", [15, 17]], ["ruku", "ruka", "NOUN", [18, 22]], [".", ".", "PUNCT", [22, 23]]]], ["calgarske-listy_2003_unor_ocr.txt", "Byla bezvl\u00e1dn\u00e1.", [["Byla", "b\u00fdt", "AUX", [0, 4]], ["bezvl\u00e1dn\u00e1", "bezvl\u00e1dn\u00fd", "ADJ", [5, 14]], [".", ".", "PUNCT", [14, 15]]]], ["calgarske-listy_2003_unor_ocr.txt", "Pod\u00edval se vyd\u011b\u0161en\u011b na svoje dva kamar\u00e1dy: \"Je mrtv\u00e1 - ona um\u0159ela!\"", [["Pod\u00edval", "pod\u00edvat", "VERB", [0, 7]], ["se", "se", "PRON", [8, 10]], ["vyd\u011b\u0161en\u011b", "vyd\u011b\u0161en\u011b", "ADV", [11, 19]], ["na", "na", "ADP", [20, 22]], ["svoje", "sv\u016fj", "DET", [23, 28]], ["dva", "dva", "NUM", [29, 32]], ["kamar\u00e1dy", "kamar\u00e1d", "NOUN", [33, 41]], [":", ":", "PUNCT", [41, 42]], ["\"", "\"", "PUNCT", [43, 44]], ["Je", "b\u00fdt", "AUX", [44, 46]], ["mrtv\u00e1", "mrtv\u00fd", "ADJ", [47, 52]], ["-", "-", "PUNCT", [53, 54]], ["ona", "on", "PRON", [55, 58]], ["um\u0159ela", "um\u0159\u00edt", "VERB", [59, 65]], ["!", "!", "PUNCT", [65, 66]], ["\"", "\"", "PUNCT", [66, 67]]]], ["calgarske-listy_2003_unor_ocr.txt", "T\u0159i mlad\u00ed mu\u017ei se v \u0161oku d\u00edvali jeden na druh\u00e9ho.", [["T\u0159i", "t\u0159i", "NUM", [0, 3]], ["mlad\u00ed", "mlad\u00fd", "ADJ", [4, 9]], ["mu\u017ei", "mu\u017e", "NOUN", [10, 14]], ["se", "se", "PRON", [15, 17]], ["v", "v", "ADP", [18, 19]], ["\u0161oku", "\u0161ok", "NOUN", [20, 24]], ["d\u00edvali", "d\u00edvat", "VERB", [25, 31]], ["jeden", "jeden", "NUM", [32, 37]], ["na", "na", "ADP", [38, 40]], ["druh\u00e9ho", "druh\u00fd", "ADJ", [41, 48]], [".", ".", "PUNCT", [48, 49]]]], ["calgarske-listy_2003_unor_ocr.txt", "Ticho p\u0159eru\u0161ilo d\u00edt\u011b, kter\u00e9 za\u010dalo plakat.", [["Ticho", "ticho", "NOUN", [0, 5]], ["p\u0159eru\u0161ilo", "p\u0159eru\u0161it", "VERB", [6, 15]], ["d\u00edt\u011b", "d\u00edt\u011b", "NOUN", [16, 20]], [",", ",", "PUNCT", [20, 21]], ["kter\u00e9", "kter\u00fd", "DET", [22, 27]], ["za\u010dalo", "za\u010d\u00edt", "VERB", [28, 34]], ["plakat", "plakat", "VERB", [35, 41]], [".", ".", "PUNCT", [41, 42]]]], ["calgarske-listy_2003_unor_ocr.txt", "Pak si teprve uv\u011bdomili, \u017ee je 5  tu \u017eivot, pr\u00e1v\u011b zapo\u010dat\u00fd a neschopn\u00fd se starat s\u00e1m o sebe.", [["Pak", "pak", "ADV", [0, 3]], ["si", "se", "PRON", [4, 6]], ["teprve", "teprve", "ADV", [7, 13]], ["uv\u011bdomili", "uv\u011bdomit", "VERB", [14, 23]], [",", ",", "PUNCT", [23, 24]], ["\u017ee", "\u017ee", "SCONJ", [25, 27]], ["je", "b\u00fdt", "AUX", [28, 30]], ["5", "5", "NUM", [31, 32]], ["tu", "tu", "ADV", [34, 36]], ["\u017eivot", "\u017eivot", "NOUN", [37, 42]], [",", ",", "PUNCT", [42, 43]], ["pr\u00e1v\u011b", "pr\u00e1v\u011b", "ADV", [44, 49]], ["zapo\u010dat\u00fd", "zapo\u010dat\u00fd", "ADJ", [50, 58]], ["a", "a", "CCONJ", [59, 60]], ["neschopn\u00fd", "schopn\u00fd", "ADJ", [61, 70]], ["se", "se", "PRON", [71, 73]], ["starat", "starat", "VERB", [74, 80]], ["s\u00e1m", "sam\u00fd", "DET", [81, 84]], ["o", "o", "ADP", [85, 86]], ["sebe", "se", "PRON", [87, 91]], [".", ".", "PUNCT", [91, 92]]]], ["calgarske-listy_2003_unor_ocr.txt", "Johny rozdmychal ohe\u0148 v kamnech a Bili si vysvl\u00e9kl parku a novorozenou hol\u010di\u010dku do n\u00ed zabalil.", [["Johny", "Johny", "PROPN", [0, 5]], ["rozdmychal", "rozdmychat", "VERB", [6, 16]], ["ohe\u0148", "ohe\u0148", "NOUN", [17, 21]], ["v", "v", "ADP", [22, 23]], ["kamnech", "kamna", "NOUN", [24, 31]], ["a", "a", "CCONJ", [32, 33]], ["Bili", "b\u00edt", "VERB", [34, 38]], ["si", "se", "PRON", [39, 41]], ["vysvl\u00e9kl", "vysvl\u00e9knout", "VERB", [42, 50]], ["parku", "park", "NOUN", [51, 56]], ["a", "a", "CCONJ", [57, 58]], ["novorozenou", "novorozen\u00fd", "ADJ", [59, 70]], ["hol\u010di\u010dku", "hol\u010di\u010dka", "NOUN", [71, 79]], ["do", "do", "ADP", [80, 82]], ["n\u00ed", "on", "PRON", [83, 85]], ["zabalil", "zabalit", "VERB", [86, 93]], [".", ".", "PUNCT", [93, 94]]]], ["calgarske-listy_2003_unor_ocr.txt", "V tom okam\u017eiku se otev\u0159ely dve\u0159e a v oblaku p\u00e1ry dovnit\u0159 vrazil mlad\u00fd mu\u017e.", [["V", "v", "ADP", [0, 1]], ["tom", "ten", "DET", [2, 5]], ["okam\u017eiku", "okam\u017eik", "NOUN", [6, 14]], ["se", "se", "PRON", [15, 17]], ["otev\u0159ely", "otev\u0159\u00edt", "VERB", [18, 26]], ["dve\u0159e", "dve\u0159e", "NOUN", [27, 32]], ["a", "a", "CCONJ", [33, 34]], ["v", "v", "ADP", [35, 36]], ["oblaku", "oblak", "NOUN", [37, 43]], ["p\u00e1ry", "p\u00e1r", "NOUN", [44, 48]], ["dovnit\u0159", "dovnit\u0159", "ADV", [49, 56]], ["vrazil", "vrazit", "VERB", [57, 63]], ["mlad\u00fd", "mlad\u00fd", "ADJ", [64, 69]], ["mu\u017e", "mu\u017e", "NOUN", [70, 73]], [".", ".", "PUNCT", [73, 74]]]], ["calgarske-listy_2003_unor_ocr.txt", "\"Jenny, Jenny,sehnal jsem doktora!\"", [["\"", "\"", "PUNCT", [0, 1]], ["Jenny", "Jenny", "PROPN", [1, 6]], [",", ",", "PUNCT", [6, 7]], ["Jenny", "Jenny", "PROPN", [8, 13]], [",", ",", "PUNCT", [13, 14]], ["sehnal", "sehnat", "VERB", [14, 20]], ["jsem", "b\u00fdt", "AUX", [21, 25]], ["doktora", "doktor", "NOUN", [26, 33]], ["!", "!", "PUNCT", [33, 34]], ["\"", "\"", "PUNCT", [34, 35]]]], ["calgarske-listy_2003_unor_ocr.txt", "Zas\u00edpal a sklesl na podlahu vedle postele.", [["Zas\u00edpal", "zas\u00edpat", "VERB", [0, 7]], ["a", "a", "CCONJ", [8, 9]], ["sklesl", "sklesnout", "VERB", [10, 16]], ["na", "na", "ADP", [17, 19]], ["podlahu", "podlaha", "NOUN", [20, 27]], ["vedle", "vedle", "ADP", [28, 33]], ["postele", "postel", "NOUN", [34, 41]], [".", ".", "PUNCT", [41, 42]]]], ["calgarske-listy_2003_unor_ocr.txt", "To u\u017e doktor vch\u00e1zel dovnit\u0159.", [["To", "ten", "DET", [0, 2]], ["u\u017e", "u\u017e", "ADV", [3, 5]], ["doktor", "doktor", "NOUN", [6, 12]], ["vch\u00e1zel", "vch\u00e1zet", "VERB", [13, 20]], ["dovnit\u0159", "dovnit\u0159", "ADV", [21, 28]], [".", ".", "PUNCT", [28, 29]]]], ["calgarske-listy_2003_unor_ocr.txt", "Pod\u00edval se na \u017eenu na posteli a potom na mu\u017ee na zemi.", [["Pod\u00edval", "pod\u00edvat", "VERB", [0, 7]], ["se", "se", "PRON", [8, 10]], ["na", "na", "ADP", [11, 13]], ["\u017eenu", "\u017eena", "NOUN", [14, 18]], ["na", "na", "ADP", [19, 21]], ["posteli", "postel", "NOUN", [22, 29]], ["a", "a", "CCONJ", [30, 31]], ["potom", "potom", "ADV", [32, 37]], ["na", "na", "ADP", [38, 40]], ["mu\u017ee", "mu\u017e", "NOUN", [41, 45]], ["na", "na", "ADP", [46, 48]], ["zemi", "zem\u011b", "NOUN", [49, 53]], [".", ".", "PUNCT", [53, 54]]]], ["calgarske-listy_2003_unor_ocr.txt", "\"Oba jsou mrtvi.", [["\"", "\"", "PUNCT", [0, 1]], ["Oba", "oba", "NUM", [1, 4]], ["jsou", "b\u00fdt", "AUX", [5, 9]], ["mrtvi", "mrtev", "NOUN", [10, 15]], [".", ".", "PUNCT", [15, 16]]]], ["calgarske-listy_2003_unor_ocr.txt", "Namrzly mu pl\u00edce, nen\u00ed divu, b\u011b\u017eel a\u017e do Grand Forks a je -45C.", [["Namrzly", "namrzla", "NOUN", [0, 7]], ["mu", "on", "PRON", [8, 10]], ["pl\u00edce", "pl\u00edce", "NOUN", [11, 16]], [",", ",", "PUNCT", [16, 17]], ["nen\u00ed", "b\u00fdt", "AUX", [18, 22]], ["divu", "div", "NOUN", [23, 27]], [",", ",", "PUNCT", [27, 28]], ["b\u011b\u017eel", "b\u011b\u017eet", "VERB", [29, 34]], ["a\u017e", "a\u017e", "PART", [35, 37]], ["do", "do", "ADP", [38, 40]], ["Grand", "Grand", "X", [41, 46]], ["Forks", "Forks", "X", [47, 52]], ["a", "a", "CCONJ", [53, 54]], ["je", "b\u00fdt", "AUX", [55, 57]], ["-45C", "-45C", "NUM", [58, 62]], [".", ".", "PUNCT", [62, 63]]]], ["calgarske-listy_2003_unor_ocr.txt", "A matka.....k \u010dertu tihle lid\u00e9 nem\u011bli nikdy p\u0159ij\u00edt na sever!", [["A", "a", "CCONJ", [0, 1]], ["matka", "matka", "NOUN", [2, 7]], [".", ".", "PUNCT", [7, 8]], [".", ".", "PUNCT", [8, 9]], [".", ".", "PUNCT", [9, 10]], [".", ".", "PUNCT", [10, 11]], [".", ".", "PUNCT", [11, 12]], ["k", "k", "ADP", [12, 13]], ["\u010dertu", "\u010dert", "NOUN", [14, 19]], ["tihle", "tenhle", "DET", [20, 25]], ["lid\u00e9", "lid\u00e9", "NOUN", [26, 30]], ["nem\u011bli", "m\u00edt", "VERB", [31, 37]], ["nikdy", "nikdy", "ADV", [38, 43]], ["p\u0159ij\u00edt", "p\u0159ij\u00edt", "VERB", [44, 50]], ["na", "na", "ADP", [51, 53]], ["sever", "sever", "NOUN", [54, 59]], ["!", "!", "PUNCT", [59, 60]]]], ["calgarske-listy_2003_unor_ocr.txt", "Je tu n\u011bjak\u00e1 \u017eena ke kter\u00e9 m\u016f\u017eete vz\u00edt to d\u00edt\u011b?\"", [["Je", "b\u00fdt", "AUX", [0, 2]], ["tu", "tu", "ADV", [3, 5]], ["n\u011bjak\u00e1", "n\u011bjak\u00fd", "DET", [6, 12]], ["\u017eena", "\u017eena", "NOUN", [13, 17]], ["ke", "k", "ADP", [18, 20]], ["kter\u00e9", "kter\u00fd", "DET", [21, 26]], ["m\u016f\u017eete", "moci", "VERB", [27, 33]], ["vz\u00edt", "vz\u00edt", "VERB", [34, 38]], ["to", "ten", "DET", [39, 41]], ["d\u00edt\u011b", "d\u00edt\u011b", "NOUN", [42, 46]], ["?", "?", "PUNCT", [46, 47]], ["\"", "\"", "PUNCT", [47, 48]]]], ["calgarske-listy_2003_unor_ocr.txt", "\"Ne\" \u0159ekl Bili, kter\u00fd st\u00e1le dr\u017eel hol\u010di\u010dku v obrovsk\u00fdch pa\u017e\u00edch.", [["\"", "\"", "PUNCT", [0, 1]], ["Ne", "ne", "PART", [1, 3]], ["\"", "\"", "PUNCT", [3, 4]], ["\u0159ekl", "\u0159\u00edci", "VERB", [5, 9]], ["Bili", "b\u00edt", "VERB", [10, 14]], [",", ",", "PUNCT", [14, 15]], ["kter\u00fd", "kter\u00fd", "DET", [16, 21]], ["st\u00e1le", "st\u00e1le", "ADV", [22, 27]], ["dr\u017eel", "dr\u017eet", "VERB", [28, 33]], ["hol\u010di\u010dku", "hol\u010di\u010dka", "NOUN", [34, 42]], ["v", "v", "ADP", [43, 44]], ["obrovsk\u00fdch", "obrovsk\u00fd", "ADJ", [45, 55]], ["pa\u017e\u00edch", "pa\u017e", "NOUN", [56, 62]], [".", ".", "PUNCT", [62, 63]]]], ["calgarske-listy_2003_unor_ocr.txt", "\"Hm,hm\" \u0159ekl doktor \"u\u017e abych tedy \u0161el.", [["\"", "\"", "PUNCT", [0, 1]], ["Hm", "hcis", "NOUN", [1, 3]], [",", ",", "PUNCT", [3, 4]], ["hm", "hm", "NOUN", [4, 6]], ["\"", "\"", "PUNCT", [6, 7]], ["\u0159ekl", "\u0159\u00edci", "VERB", [8, 12]], ["doktor", "doktor", "NOUN", [13, 19]], ["\"", "\"", "PUNCT", [20, 21]], ["u\u017e", "u\u017e", "ADV", [21, 23]], ["aby", "aby", "SCONJ", [-20764, -20764]], ["bych", "b\u00fdt", "AUX", [-20764, -20764]], ["tedy", "tedy", "CCONJ", [30, 34]], ["\u0161el", "j\u00edt", "VERB", [35, 38]], [".", ".", "PUNCT", [38, 39]]]], ["calgarske-listy_2003_unor_ocr.txt", "Mus\u00edte se o ni n\u011bjak postarat!\"", [["Mus\u00edte", "muset", "VERB", [0, 6]], ["se", "se", "PRON", [7, 9]], ["o", "o", "ADP", [10, 11]], ["ni", "on", "PRON", [12, 14]], ["n\u011bjak", "n\u011bjak", "ADV", [15, 20]], ["postarat", "postarat", "VERB", [21, 29]], ["!", "!", "PUNCT", [29, 30]], ["\"", "\"", "PUNCT", [30, 31]]]], ["calgarske-listy_2003_unor_ocr.txt", "Zapadly za n\u00edm dve\u0159e a mlad\u00ed zlatokopov\u00e9 z\u016fstali sami s novorozen\u011btem a dv\u011bma mrtv\u00fdmi.", [["Zapadly", "zapadnout", "VERB", [0, 7]], ["za", "za", "ADP", [8, 10]], ["n\u00edm", "on", "PRON", [11, 14]], ["dve\u0159e", "dve\u0159e", "NOUN", [15, 20]], ["a", "a", "CCONJ", [21, 22]], ["mlad\u00ed", "mlad\u00fd", "ADJ", [23, 28]], ["zlatokopov\u00e9", "zlatokop", "NOUN", [29, 40]], ["z\u016fstali", "z\u016fstat", "VERB", [41, 48]], ["sami", "sam\u00fd", "DET", [49, 53]], ["s", "s", "ADP", [54, 55]], ["novorozen\u011btem", "novorozen\u011bt", "NOUN", [56, 69]], ["a", "a", "CCONJ", [70, 71]], ["dv\u011bma", "dva", "NUM", [72, 77]], ["mrtv\u00fdmi", "mrtv\u00fd", "ADJ", [78, 85]], [".", ".", "PUNCT", [85, 86]]]], ["calgarske-listy_2003_unor_ocr.txt", "\"Nemysl\u00edm \u017ee bych tu cht\u011bl z\u016fstat\" \u0159ekl Dave a ostatn\u00ed s n\u00edm souhlasili.", [["\"", "\"", "PUNCT", [0, 1]], ["Nemysl\u00edm", "myslit", "VERB", [1, 9]], ["\u017ee", "\u017ee", "SCONJ", [10, 12]], ["bych", "b\u00fdt", "AUX", [13, 17]], ["tu", "tu", "ADV", [18, 20]], ["cht\u011bl", "cht\u00edt", "VERB", [21, 26]], ["z\u016fstat", "z\u016fstat", "VERB", [27, 33]], ["\"", "\"", "PUNCT", [33, 34]], ["\u0159ekl", "\u0159\u00edci", "VERB", [35, 39]], ["Dave", "Dave", "PROPN", [40, 44]], ["a", "a", "CCONJ", [45, 46]], ["ostatn\u00ed", "ostatn\u00ed", "ADJ", [47, 54]], ["s", "s", "ADP", [55, 56]], ["n\u00edm", "on", "PRON", [57, 60]], ["souhlasili", "souhlasit", "VERB", [61, 71]], [".", ".", "PUNCT", [71, 72]]]], ["calgarske-listy_2003_unor_ocr.txt", "\"Do na\u0161eho srubu je to jen t\u0159i m\u00edle, ale jak tam dopravit to mimino?\"", [["\"", "\"", "PUNCT", [0, 1]], ["Do", "do", "ADP", [1, 3]], ["na\u0161eho", "n\u00e1\u0161", "DET", [4, 10]], ["srubu", "srub", "NOUN", [11, 16]], ["je", "b\u00fdt", "AUX", [17, 19]], ["to", "ten", "DET", [20, 22]], ["jen", "jen", "ADV", [23, 26]], ["t\u0159i", "t\u0159i", "NUM", [27, 30]], ["m\u00edle", "m\u00edl", "NOUN", [31, 35]], [",", ",", "PUNCT", [35, 36]], ["ale", "ale", "CCONJ", [37, 40]], ["jak", "jak", "ADV", [41, 44]], ["tam", "tam", "ADV", [45, 48]], ["dopravit", "dopravit", "VERB", [49, 57]], ["to", "ten", "DET", [58, 60]], ["mimino", "mimino", "NOUN", [61, 67]], ["?", "?", "PUNCT", [67, 68]], ["\"", "\"", "PUNCT", [68, 69]]]], ["calgarske-listy_2003_unor_ocr.txt", "\"Sp\u0159\u00e1hneme dva t\u00fdmy dohromady\" navrhl Bili \"j\u00e1 si sednu na san\u011b a d\u00e1m si ji pod parku\".", [["\"", "\"", "PUNCT", [0, 1]], ["Sp\u0159\u00e1hneme", "sp\u0159\u00e1hnout", "VERB", [1, 10]], ["dva", "dva", "NUM", [11, 14]], ["t\u00fdmy", "t\u00fdm", "NOUN", [15, 19]], ["dohromady", "dohromady", "ADV", [20, 29]], ["\"", "\"", "PUNCT", [29, 30]], ["navrhl", "navrhnout", "VERB", [31, 37]], ["Bili", "b\u00edt", "VERB", [38, 42]], ["\"", "\"", "PUNCT", [43, 44]], ["j\u00e1", "j\u00e1", "PRON", [44, 46]], ["si", "se", "PRON", [47, 49]], ["sednu", "sednout", "VERB", [50, 55]], ["na", "na", "ADP", [56, 58]], ["san\u011b", "san\u011b", "NOUN", [59, 63]], ["a", "a", "CCONJ", [64, 65]], ["d\u00e1m", "d\u00e1t", "VERB", [66, 69]], ["si", "se", "PRON", [70, 72]], ["ji", "on", "PRON", [73, 75]], ["pod", "pod", "ADP", [76, 79]], ["parku", "park", "NOUN", [80, 85]], ["\"", "\"", "PUNCT", [85, 86]], [".", ".", "PUNCT", [86, 87]]]], ["calgarske-listy_2003_unor_ocr.txt", "\"OK\" souhlasil Dave.", [["\"", "\"", "PUNCT", [0, 1]], ["OK", "OK", "NOUN", [1, 3]], ["\"", "\"", "PUNCT", [3, 4]], ["souhlasil", "souhlasit", "VERB", [5, 14]], ["Dave", "Dave", "PROPN", [15, 19]], [".", ".", "PUNCT", [19, 20]]]], ["calgarske-listy_2003_unor_ocr.txt", "Johny za\u010dal prohled\u00e1vat srub.", [["Johny", "Johny", "PROPN", [0, 5]], ["za\u010dal", "za\u010d\u00edt", "VERB", [6, 11]], ["prohled\u00e1vat", "prohled\u00e1vat", "VERB", [12, 23]], ["srub", "srub", "NOUN", [24, 28]], [".", ".", "PUNCT", [28, 29]]]], ["calgarske-listy_2003_unor_ocr.txt", "\"Co hled\u00e1\u0161?\" zeptal se Dave.", [["\"", "\"", "PUNCT", [0, 1]], ["Co", "co", "PRON", [1, 3]], ["hled\u00e1\u0161", "hledat", "VERB", [4, 10]], ["?", "?", "PUNCT", [10, 11]], ["\"", "\"", "PUNCT", [11, 12]], ["zeptal", "zeptat", "VERB", [13, 19]], ["se", "se", "PRON", [20, 22]], ["Dave", "Dave", "PROPN", [23, 27]], [".", ".", "PUNCT", [27, 28]]]], ["calgarske-listy_2003_unor_ocr.txt", "\"Ale m\u011blo by tu b\u00fdt n\u011bjak\u00e9 oble\u010den\u00ed, ne?", [["\"", "\"", "PUNCT", [0, 1]], ["Ale", "ale", "CCONJ", [1, 4]], ["m\u011blo", "m\u00edt", "VERB", [5, 9]], ["by", "b\u00fdt", "AUX", [10, 12]], ["tu", "tu", "ADV", [13, 15]], ["b\u00fdt", "b\u00fdt", "AUX", [16, 19]], ["n\u011bjak\u00e9", "n\u011bjak\u00fd", "DET", [20, 26]], ["oble\u010den\u00ed", "oble\u010den\u00ed", "NOUN", [27, 35]], [",", ",", "PUNCT", [35, 36]], ["ne", "ne", "PART", [37, 39]], ["?", "?", "PUNCT", [39, 40]]]], ["calgarske-listy_2003_unor_ocr.txt", "P\u0159ece v\u011bd\u011bli ,\u017ee budou m\u00edt d\u00edt\u011b!\"", [["P\u0159ece", "p\u0159ece", "PART", [0, 5]], ["v\u011bd\u011bli", "v\u011bd\u011bt", "VERB", [6, 12]], [",", ",", "PUNCT", [13, 14]], ["\u017ee", "\u017ee", "SCONJ", [14, 16]], ["budou", "b\u00fdt", "AUX", [17, 22]], ["m\u00edt", "m\u00edt", "VERB", [23, 26]], ["d\u00edt\u011b", "d\u00edt\u011b", "NOUN", [27, 31]], ["!", "!", "PUNCT", [31, 32]], ["\"", "\"", "PUNCT", [32, 33]]]], ["calgarske-listy_2003_unor_ocr.txt", "\"To je fakt.", [["\"", "\"", "PUNCT", [0, 1]], ["To", "ten", "DET", [1, 3]], ["je", "b\u00fdt", "AUX", [4, 6]], ["fakt", "fakt", "NOUN", [7, 11]], [".", ".", "PUNCT", [11, 12]]]], ["calgarske-listy_2003_unor_ocr.txt", "Po\u010dkej pod\u00edv\u00e1m se pod postel.\"", [["Po\u010dkej", "po\u010dkat", "VERB", [0, 6]], ["pod\u00edv\u00e1m", "pod\u00edvat", "VERB", [7, 14]], ["se", "se", "PRON", [15, 17]], ["pod", "pod", "ADP", [18, 21]], ["postel", "postel", "NOUN", [22, 28]], [".", ".", "PUNCT", [28, 29]], ["\"", "\"", "PUNCT", [29, 30]]]], ["calgarske-listy_2003_unor_ocr.txt", "Dave vyt\u00e1hl z pod postele krabici.", [["Dave", "Dave", "PROPN", [0, 4]], ["vyt\u00e1hl", "vyt\u00e1hnout", "VERB", [5, 11]], ["z", "z", "ADP", [12, 13]], ["pod", "pod", "ADP", [14, 17]], ["postele", "postel", "NOUN", [18, 25]], ["krabici", "krabice", "NOUN", [26, 33]], [".", ".", "PUNCT", [33, 34]]]], ["calgarske-listy_2003_unor_ocr.txt", "\"Jo je to tady!", [["\"", "\"", "PUNCT", [0, 1]], ["Jo", "jo", "INTJ", [1, 3]], ["je", "b\u00fdt", "AUX", [4, 6]], ["to", "ten", "DET", [7, 9]], ["tady", "tady", "ADV", [10, 14]], ["!", "!", "PUNCT", [14, 15]]]], ["calgarske-listy_2003_unor_ocr.txt", "Fajn, m\u00e1me oble\u010den\u00ed a p\u00e1r plenek!\"", [["Fajn", "fajn", "INTJ", [0, 4]], [",", ",", "PUNCT", [4, 5]], ["m\u00e1me", "m\u00edt", "VERB", [6, 10]], ["oble\u010den\u00ed", "oble\u010den\u00ed", "NOUN", [11, 19]], ["a", "a", "CCONJ", [20, 21]], ["p\u00e1r", "p\u00e1r", "DET", [22, 25]], ["plenek", "plenka", "NOUN", [26, 32]], ["!", "!", "PUNCT", [32, 33]], ["\"", "\"", "PUNCT", [33, 34]]]], ["calgarske-listy_2003_unor_ocr.txt", "To jsem si oddechl\" \u0159ekl Johny \"Hrozn\u011b nerad bych sh\u00e1n\u011bl te\u010fka mech.\"", [["To", "ten", "DET", [0, 2]], ["jsem", "b\u00fdt", "AUX", [3, 7]], ["si", "se", "PRON", [8, 10]], ["oddechl", "oddechnout", "VERB", [11, 18]], ["\"", "\"", "PUNCT", [18, 19]], ["\u0159ekl", "\u0159\u00edci", "VERB", [20, 24]], ["Johny", "Johny", "PROPN", [25, 30]], ["\"", "\"", "PUNCT", [31, 32]], ["Hrozn\u011b", "hrozn\u011b", "ADV", [32, 38]], ["nerad", "r\u00e1d", "ADJ", [39, 44]], ["bych", "b\u00fdt", "AUX", [45, 49]], ["sh\u00e1n\u011bl", "sh\u00e1n\u011bt", "VERB", [50, 56]], ["te\u010fka", "te\u010fka", "ADV", [57, 62]], ["mech", "mech", "NOUN", [63, 67]], [".", ".", "PUNCT", [67, 68]], ["\"", "\"", "PUNCT", [68, 69]]]], ["calgarske-listy_2003_unor_ocr.txt", "\"Mech?", [["\"", "\"", "PUNCT", [0, 1]], ["Mech", "mech", "NOUN", [1, 5]], ["?", "?", "PUNCT", [5, 6]]]], ["calgarske-listy_2003_unor_ocr.txt", "A na co?", [["A", "a", "CCONJ", [0, 1]], ["na", "na", "ADP", [2, 4]], ["co", "co", "PRON", [5, 7]], ["?", "?", "PUNCT", [7, 8]]]], ["calgarske-listy_2003_unor_ocr.txt", "\"No, kdybychom nem\u011bli plenky, co by n\u00e1m zb\u00fdvalo?", [["\"", "\"", "PUNCT", [0, 1]], ["No", "no", "INTJ", [1, 3]], [",", ",", "PUNCT", [3, 4]], ["kdy\u017e", "kdy\u017e", "SCONJ", [-21524, -21524]], ["bychom", "b\u00fdt", "AUX", [-21524, -21524]], ["nem\u011bli", "m\u00edt", "VERB", [15, 21]], ["plenky", "plenka", "NOUN", [22, 28]], [",", ",", "PUNCT", [28, 29]], ["co", "co", "PRON", [30, 32]], ["by", "b\u00fdt", "AUX", [33, 35]], ["n\u00e1m", "my", "PRON", [36, 39]], ["zb\u00fdvalo", "zb\u00fdvat", "VERB", [40, 47]], ["?", "?", "PUNCT", [47, 48]]]], ["calgarske-listy_2003_unor_ocr.txt", "Ty nev\u00ed\u0161, jak to d\u011blaj\u00ed Indi\u00e1ni?\"", [["Ty", "ten", "DET", [0, 2]], ["nev\u00ed\u0161", "v\u011bd\u011bt", "VERB", [3, 8]], [",", ",", "PUNCT", [8, 9]], ["jak", "jak", "ADV", [10, 13]], ["to", "ten", "DET", [14, 16]], ["d\u011blaj\u00ed", "d\u011blat", "VERB", [17, 23]], ["Indi\u00e1ni", "Indi\u00e1n", "PROPN", [24, 31]], ["?", "?", "PUNCT", [31, 32]], ["\"", "\"", "PUNCT", [32, 33]]]], ["calgarske-listy_2003_unor_ocr.txt", "\"Ani ne.\"", [["\"", "\"", "PUNCT", [0, 1]], ["Ani", "ani", "CCONJ", [1, 4]], ["ne", "ne", "PART", [5, 7]], [".", ".", "PUNCT", [7, 8]], ["\"", "\"", "PUNCT", [8, 9]]]], ["calgarske-listy_2003_unor_ocr.txt", "\"Vezmou pytel, nacpou ho such\u00fdm mechem, a do toho zasad\u00ed d\u00edt\u011b.", [["\"", "\"", "PUNCT", [0, 1]], ["Vezmou", "vz\u00edt", "VERB", [1, 7]], ["pytel", "pytel", "NOUN", [8, 13]], [",", ",", "PUNCT", [13, 14]], ["nacpou", "nacpat", "VERB", [15, 21]], ["ho", "on", "PRON", [22, 24]], ["such\u00fdm", "such\u00fd", "ADJ", [25, 31]], ["mechem", "mech", "NOUN", [32, 38]], [",", ",", "PUNCT", [38, 39]], ["a", "a", "CCONJ", [40, 41]], ["do", "do", "ADP", [42, 44]], ["toho", "ten", "DET", [45, 49]], ["zasad\u00ed", "zasadit", "VERB", [50, 56]], ["d\u00edt\u011b", "d\u00edt\u011b", "NOUN", [57, 61]], [".", ".", "PUNCT", [61, 62]]]], ["calgarske-listy_2003_unor_ocr.txt", "A to \u010dur\u00e1 a kak\u00e1 - a a\u017e pytel prosakuje, tak mech vym\u011bn\u00ed.", [["A", "a", "CCONJ", [0, 1]], ["to", "to", "PART", [2, 4]], ["\u010dur\u00e1", "\u010durat", "VERB", [5, 9]], ["a", "a", "CCONJ", [10, 11]], ["kak\u00e1", "kak\u00e1", "NOUN", [12, 16]], ["-", "-", "PUNCT", [17, 18]], ["a", "a", "CCONJ", [19, 20]], ["a\u017e", "a\u017e", "PART", [21, 23]], ["pytel", "pytel", "NOUN", [24, 29]], ["prosakuje", "prosakovat", "VERB", [30, 39]], [",", ",", "PUNCT", [39, 40]], ["tak", "tak", "ADV", [41, 44]], ["mech", "mech", "NOUN", [45, 49]], ["vym\u011bn\u00ed", "vym\u011bnit", "VERB", [50, 56]], [".", ".", "PUNCT", [56, 57]]]], ["calgarske-listy_2003_unor_ocr.txt", "A poj\u010fte mi pomoct s t\u00edm mrtv\u00fdm!\"", [["A", "a", "CCONJ", [0, 1]], ["poj\u010fte", "jet", "VERB", [2, 8]], ["mi", "j\u00e1", "PRON", [9, 11]], ["pomoct", "pomoci", "VERB", [12, 18]], ["s", "s", "ADP", [19, 20]], ["t\u00edm", "ten", "DET", [21, 24]], ["mrtv\u00fdm", "mrtv\u00fd", "ADJ", [25, 31]], ["!", "!", "PUNCT", [31, 32]], ["\"", "\"", "PUNCT", [32, 33]]]], ["calgarske-listy_2003_unor_ocr.txt", "Spole\u010dn\u011b polo\u017eili mrtv\u00e9ho na postel vedle jeho \u017eeny.", [["Spole\u010dn\u011b", "spole\u010dn\u011b", "ADV", [0, 8]], ["polo\u017eili", "polo\u017eit", "VERB", [9, 17]], ["mrtv\u00e9ho", "mrtv\u00fd", "ADJ", [18, 25]], ["na", "na", "ADP", [26, 28]], ["postel", "postel", "NOUN", [29, 35]], ["vedle", "vedle", "ADP", [36, 41]], ["jeho", "jeho", "DET", [42, 46]], ["\u017eeny", "\u017eena", "NOUN", [47, 51]], [".", ".", "PUNCT", [51, 52]]]], ["calgarske-listy_2003_unor_ocr.txt", "\" Z jara je p\u0159ijdeme poh\u0159b\u00edt.", [["\"", "\"", "PUNCT", [0, 1]], ["Z", "z", "ADP", [2, 3]], ["jara", "jaro", "NOUN", [4, 8]], ["je", "on", "PRON", [9, 11]], ["p\u0159ijdeme", "p\u0159ij\u00edt", "VERB", [12, 20]], ["poh\u0159b\u00edt", "poh\u0159b\u00edt", "VERB", [21, 28]], [".", ".", "PUNCT", [28, 29]]]], ["calgarske-listy_2003_unor_ocr.txt", "\"Zat\u00edmco Johny a Dave pracovali na zaji\u0161t\u011bn\u00ed oken a dve\u0159\u00ed srubu, aby jimi nevnikla drav\u00e1 zv\u011b\u0159, Bili s d\u00edt\u011btem v n\u00e1ru\u010d\u00ed se zastavil nad lo\u017eem rodi\u010d\u016f.", [["\"", "\"", "PUNCT", [0, 1]], ["Zat\u00edmco", "zat\u00edmco", "SCONJ", [1, 8]], ["Johny", "Johny", "PROPN", [9, 14]], ["a", "a", "CCONJ", [15, 16]], ["Dave", "Dave", "PROPN", [17, 21]], ["pracovali", "pracovat", "VERB", [22, 31]], ["na", "na", "ADP", [32, 34]], ["zaji\u0161t\u011bn\u00ed", "zaji\u0161t\u011bn\u00ed", "NOUN", [35, 44]], ["oken", "okno", "NOUN", [45, 49]], ["a", "a", "CCONJ", [50, 51]], ["dve\u0159\u00ed", "dve\u0159e", "NOUN", [52, 57]], ["srubu", "srub", "NOUN", [58, 63]], [",", ",", "PUNCT", [63, 64]], ["aby", "aby", "SCONJ", [-21855, -21855]], ["by", "b\u00fdt", "AUX", [-21855, -21855]], ["jimi", "on", "PRON", [69, 73]], ["nevnikla", "vniknout", "VERB", [74, 82]], ["drav\u00e1", "drav\u00fd", "ADJ", [83, 88]], ["zv\u011b\u0159", "zv\u011b\u0159", "NOUN", [89, 93]], [",", ",", "PUNCT", [93, 94]], ["Bili", "b\u00edt", "VERB", [95, 99]], ["s", "s", "ADP", [100, 101]], ["d\u00edt\u011btem", "d\u00edt\u011b", "NOUN", [102, 109]], ["v", "v", "ADP", [110, 111]], ["n\u00e1ru\u010d\u00ed", "n\u00e1ru\u010d\u00ed", "NOUN", [112, 118]], ["se", "se", "PRON", [119, 121]], ["zastavil", "zastavit", "VERB", [122, 130]], ["nad", "nad", "ADP", [131, 134]], ["lo\u017eem", "lo\u017ee", "NOUN", [135, 140]], ["rodi\u010d\u016f", "rodi\u010d", "NOUN", [141, 147]], [".", ".", "PUNCT", [147, 148]]]], ["calgarske-listy_2003_unor_ocr.txt", "\"Bo\u017ee, pros\u00edme T\u011b, ochra\u0148uj du\u0161e t\u011bch dvou, kter\u00e9 jsi povolal k sob\u011b a dej n\u00e1m dost s\u00edly abychom byli schopni se postarat o tuto mali\u010dkou, kterou jsi sv\u011b\u0159il do na\u0161\u00ed p\u00e9\u010de pr\u00e1v\u011b dnes, v p\u0159edve\u010der zrozen\u00ed Tv\u00e9ho syna, Je\u017e\u00ed\u0161e Krista.", [["\"", "\"", "PUNCT", [0, 1]], ["Bo\u017ee", "b\u016fh", "INTJ", [1, 5]], [",", ",", "PUNCT", [5, 6]], ["pros\u00edme", "prosit", "VERB", [7, 14]], ["T\u011b", "ty", "PRON", [15, 17]], [",", ",", "PUNCT", [17, 18]], ["ochra\u0148uj", "ochra\u0148ovat", "VERB", [19, 27]], ["du\u0161e", "du\u0161e", "NOUN", [28, 32]], ["t\u011bch", "ten", "DET", [33, 37]], ["dvou", "dva", "NUM", [38, 42]], [",", ",", "PUNCT", [42, 43]], ["kter\u00e9", "kter\u00fd", "DET", [44, 49]], ["jsi", "b\u00fdt", "AUX", [50, 53]], ["povolal", "povolat", "VERB", [54, 61]], ["k", "k", "ADP", [62, 63]], ["sob\u011b", "se", "PRON", [64, 68]], ["a", "a", "CCONJ", [69, 70]], ["dej", "d\u00e1t", "VERB", [71, 74]], ["n\u00e1m", "my", "PRON", [75, 78]], ["dost", "dost", "ADV", [79, 83]], ["s\u00edly", "s\u00edla", "NOUN", [84, 88]], ["aby", "aby", "SCONJ", [-22004, -22004]], ["bychom", "b\u00fdt", "AUX", [-22004, -22004]], ["byli", "b\u00fdt", "AUX", [97, 101]], ["schopni", "schopn\u00fd", "ADJ", [102, 109]], ["se", "se", "PRON", [110, 112]], ["postarat", "postarat", "VERB", [113, 121]], ["o", "o", "ADP", [122, 123]], ["tuto", "tento", "DET", [124, 128]], ["mali\u010dkou", "mali\u010dk\u00fd", "ADJ", [129, 137]], [",", ",", "PUNCT", [137, 138]], ["kterou", "kter\u00fd", "DET", [139, 145]], ["jsi", "b\u00fdt", "AUX", [146, 149]], ["sv\u011b\u0159il", "sv\u011b\u0159it", "VERB", [150, 156]], ["do", "do", "ADP", [157, 159]], ["na\u0161\u00ed", "n\u00e1\u0161", "DET", [160, 164]], ["p\u00e9\u010de", "p\u00e9\u010de", "NOUN", [165, 169]], ["pr\u00e1v\u011b", "pr\u00e1v\u011b", "PART", [170, 175]], ["dnes", "dnes", "ADV", [176, 180]], [",", ",", "PUNCT", [180, 181]], ["v", "v", "ADP", [182, 183]], ["p\u0159edve\u010der", "p\u0159edve\u010der", "NOUN", [184, 193]], ["zrozen\u00ed", "zrozen\u00ed", "NOUN", [194, 201]], ["Tv\u00e9ho", "tv\u00fd", "ADJ", [202, 207]], ["syna", "syn", "NOUN", [208, 212]], [",", ",", "PUNCT", [212, 213]], ["Je\u017e\u00ed\u0161e", "Je\u017e\u00ed\u0161", "PROPN", [214, 220]], ["Krista", "Kristus", "PROPN", [221, 227]], [".", ".", "PUNCT", [227, 228]]]], ["calgarske-listy_2003_unor_ocr.txt", "Amen.\"", [["Amen", "amen", "INTJ", [0, 4]], [".", ".", "PUNCT", [4, 5]], ["\"", "\"", "PUNCT", [5, 6]]]], ["calgarske-listy_2003_unor_ocr.txt", "\"Tak a jedem\" prohl\u00e1sil Johny a zarazil je\u0161t\u011b posledn\u00ed h\u0159eb do tr\u00e1mu upev\u0148uj\u00edc\u00edho dve\u0159e.", [["\"", "\"", "PUNCT", [0, 1]], ["Tak", "tak", "ADV", [1, 4]], ["a", "a", "CCONJ", [5, 6]], ["jedem", "jed", "NOUN", [7, 12]], ["\"", "\"", "PUNCT", [12, 13]], ["prohl\u00e1sil", "prohl\u00e1sit", "VERB", [14, 23]], ["Johny", "Johny", "PROPN", [24, 29]], ["a", "a", "CCONJ", [30, 31]], ["zarazil", "zarazit", "VERB", [32, 39]], ["je\u0161t\u011b", "je\u0161t\u011b", "ADV", [40, 45]], ["posledn\u00ed", "posledn\u00ed", "ADJ", [46, 54]], ["h\u0159eb", "h\u0159eb", "NOUN", [55, 59]], ["do", "do", "ADP", [60, 62]], ["tr\u00e1mu", "tr\u00e1m", "NOUN", [63, 68]], ["upev\u0148uj\u00edc\u00edho", "upev\u0148uj\u00edc\u00ed", "ADJ", [69, 81]], ["dve\u0159e", "dve\u0159e", "NOUN", [82, 87]], [".", ".", "PUNCT", [87, 88]]]], ["calgarske-listy_2003_unor_ocr.txt", "V\u016fdci t\u00fdm\u016f, te\u010f u\u017e odpo\u010dinut\u00ed, ne\u010dekali ani na povel a vyrazili po zmrzl\u00e9m trailu k domovu.", [["V\u016fdci", "v\u016fdce", "NOUN", [0, 5]], ["t\u00fdm\u016f", "t\u00fdm", "NOUN", [6, 10]], [",", ",", "PUNCT", [10, 11]], ["te\u010f", "te\u010f", "ADV", [12, 15]], ["u\u017e", "u\u017e", "ADV", [16, 18]], ["odpo\u010dinut\u00ed", "odpo\u010dinut\u00ed", "NOUN", [19, 29]], [",", ",", "PUNCT", [29, 30]], ["ne\u010dekali", "\u010dekat", "VERB", [31, 39]], ["ani", "ani", "CCONJ", [40, 43]], ["na", "na", "ADP", [44, 46]], ["povel", "povel", "NOUN", [47, 52]], ["a", "a", "CCONJ", [53, 54]], ["vyrazili", "vyrazit", "VERB", [55, 63]], ["po", "po", "ADP", [64, 66]], ["zmrzl\u00e9m", "zmrzl\u00fd", "ADJ", [67, 74]], ["trailu", "trail", "NOUN", [75, 81]], ["k", "k", "ADP", [82, 83]], ["domovu", "domov", "NOUN", [84, 90]], [".", ".", "PUNCT", [90, 91]]]], ["calgarske-listy_2003_unor_ocr.txt", "Na obloze pl\u00e1la pol\u00e1rn\u00ed z\u00e1\u0159e jako posledn\u00ed sv\u00edce za zem\u0159el\u00e9.", [["Na", "na", "ADP", [0, 2]], ["obloze", "obloha", "NOUN", [3, 9]], ["pl\u00e1la", "pl\u00e1t", "VERB", [10, 15]], ["pol\u00e1rn\u00ed", "pol\u00e1rn\u00ed", "ADJ", [16, 23]], ["z\u00e1\u0159e", "z\u00e1\u0159e", "NOUN", [24, 28]], ["jako", "jako", "SCONJ", [29, 33]], ["posledn\u00ed", "posledn\u00ed", "ADJ", [34, 42]], ["sv\u00edce", "sv\u00edce", "NOUN", [43, 48]], ["za", "za", "ADP", [49, 51]], ["zem\u0159el\u00e9", "zem\u0159el\u00fd", "ADJ", [52, 59]], [".", ".", "PUNCT", [59, 60]]]], ["calgarske-listy_2003_unor_ocr.txt", "Za necelou p\u016flhodinu byli doma.", [["Za", "za", "ADP", [0, 2]], ["necelou", "cel\u00fd", "ADJ", [3, 10]], ["p\u016flhodinu", "p\u016flhodina", "NOUN", [11, 20]], ["byli", "b\u00fdt", "AUX", [21, 25]], ["doma", "doma", "ADV", [26, 30]], [".", ".", "PUNCT", [30, 31]]]], ["calgarske-listy_2003_unor_ocr.txt", "A\u010dkoliv v kamnech doutnalo je\u0161t\u011b p\u00e1r uhl\u00edk\u016f, do v\u00fd\u0161e dvou stop od zem\u011b se v\u0161e ji\u017e pokr\u00fdvalo jinovatkou.", [["A\u010dkoliv", "a\u010dkoliv", "SCONJ", [0, 7]], ["v", "v", "ADP", [8, 9]], ["kamnech", "kamna", "NOUN", [10, 17]], ["doutnalo", "doutnat", "VERB", [18, 26]], ["je\u0161t\u011b", "je\u0161t\u011b", "ADV", [27, 32]], ["p\u00e1r", "p\u00e1r", "DET", [33, 36]], ["uhl\u00edk\u016f", "uhl\u00edk", "NOUN", [37, 43]], [",", ",", "PUNCT", [43, 44]], ["do", "do", "ADP", [45, 47]], ["v\u00fd\u0161e", "v\u00fd\u0161e", "NOUN", [48, 52]], ["dvou", "dva", "NUM", [53, 57]], ["stop", "stopa", "NOUN", [58, 62]], ["od", "od", "ADP", [63, 65]], ["zem\u011b", "zem\u011b", "NOUN", [66, 70]], ["se", "se", "PRON", [71, 73]], ["v\u0161e", "v\u0161echen", "DET", [74, 77]], ["ji\u017e", "ji\u017e", "ADV", [78, 81]], ["pokr\u00fdvalo", "pokr\u00fdvat", "VERB", [82, 91]], ["jinovatkou", "jinovatka", "NOUN", [92, 102]], [".", ".", "PUNCT", [102, 103]]]], ["calgarske-listy_2003_unor_ocr.txt", "Dave hodil rychle do kamen p\u00e1r kus\u016f d\u0159eva.", [["Dave", "Dave", "PROPN", [0, 4]], ["hodil", "hodit", "VERB", [5, 10]], ["rychle", "rychle", "ADV", [11, 17]], ["do", "do", "ADP", [18, 20]], ["kamen", "kamna", "NOUN", [21, 26]], ["p\u00e1r", "p\u00e1r", "DET", [27, 30]], ["kus\u016f", "kus", "NOUN", [31, 35]], ["d\u0159eva", "d\u0159evo", "NOUN", [36, 41]], [".", ".", "PUNCT", [41, 42]]]], ["calgarske-listy_2003_unor_ocr.txt", "Johny venku vyp\u0159ahal psy a Bili si sedl na pry\u010dnu s hol\u010di\u010dkou v n\u00e1ru\u010d\u00ed.", [["Johny", "Johny", "PROPN", [0, 5]], ["venku", "venku", "ADV", [6, 11]], ["vyp\u0159ahal", "vyp\u0159ahat", "VERB", [12, 20]], ["psy", "pes", "NOUN", [21, 24]], ["a", "a", "CCONJ", [25, 26]], ["Bili", "b\u00edt", "VERB", [27, 31]], ["si", "se", "PRON", [32, 34]], ["sedl", "sednout", "VERB", [35, 39]], ["na", "na", "ADP", [40, 42]], ["pry\u010dnu", "pry\u010dna", "NOUN", [43, 49]], ["s", "s", "ADP", [50, 51]], ["hol\u010di\u010dkou", "hol\u010di\u010dka", "NOUN", [52, 61]], ["v", "v", "ADP", [62, 63]], ["n\u00e1ru\u010d\u00ed", "n\u00e1ru\u010d\u00ed", "NOUN", [64, 70]], [".", ".", "PUNCT", [70, 71]]]], ["calgarske-listy_2003_unor_ocr.txt", "Na san\u00edch v teple jeho t\u011bla spala ale te\u010f plakala a nebyla k uti\u0161en\u00ed.", [["Na", "na", "ADP", [0, 2]], ["san\u00edch", "sa\u0148", "NOUN", [3, 9]], ["v", "v", "ADP", [10, 11]], ["teple", "teplo", "NOUN", [12, 17]], ["jeho", "jeho", "DET", [18, 22]], ["t\u011bla", "t\u011blo", "NOUN", [23, 27]], ["spala", "sp\u00e1t", "VERB", [28, 33]], ["ale", "ale", "CCONJ", [34, 37]], ["te\u010f", "te\u010f", "ADV", [38, 41]], ["plakala", "plakat", "VERB", [42, 49]], ["a", "a", "CCONJ", [50, 51]], ["nebyla", "b\u00fdt", "AUX", [52, 58]], ["k", "k", "ADP", [59, 60]], ["uti\u0161en\u00ed", "uti\u0161en\u00ed", "NOUN", [61, 68]], [".", ".", "PUNCT", [68, 69]]]], ["calgarske-listy_2003_unor_ocr.txt", "Bili j\u00ed zp\u00edval, houpal a hladil, ale mimino \u0159valo \u010dim d\u00e1l v\u00edc.", [["Bili", "b\u00edt", "VERB", [0, 4]], ["j\u00ed", "on", "PRON", [5, 7]], ["zp\u00edval", "zp\u00edvat", "VERB", [8, 14]], [",", ",", "PUNCT", [14, 15]], ["houpal", "houpat", "VERB", [16, 22]], ["a", "a", "CCONJ", [23, 24]], ["hladil", "hladit", "VERB", [25, 31]], [",", ",", "PUNCT", [31, 32]], ["ale", "ale", "CCONJ", [33, 36]], ["mimino", "mimino", "NOUN", [37, 43]], ["\u0159valo", "\u0159v\u00e1t", "VERB", [44, 49]], ["\u010dim", "\u010dim", "INTJ", [50, 53]], ["d\u00e1l", "d\u00e1l", "ADV", [54, 57]], ["v\u00edc", "v\u00edce", "ADV", [58, 61]], [".", ".", "PUNCT", [61, 62]]]], ["calgarske-listy_2003_unor_ocr.txt", "Dave se zvedl od kamen.", [["Dave", "Dave", "PROPN", [0, 4]], ["se", "se", "PRON", [5, 7]], ["zvedl", "zvednout", "VERB", [8, 13]], ["od", "od", "ADP", [14, 16]], ["kamen", "kamna", "NOUN", [17, 22]], [".", ".", "PUNCT", [22, 23]]]], ["calgarske-listy_2003_unor_ocr.txt", "\"To se ti nepoda\u0159\u00ed ji takhle uklidnit.", [["\"", "\"", "PUNCT", [0, 1]], ["To", "ten", "DET", [1, 3]], ["se", "se", "PRON", [4, 6]], ["ti", "ten", "DET", [7, 9]], ["nepoda\u0159\u00ed", "poda\u0159it", "VERB", [10, 18]], ["ji", "on", "PRON", [19, 21]], ["takhle", "takhle", "ADV", [22, 28]], ["uklidnit", "uklidnit", "VERB", [29, 37]], [".", ".", "PUNCT", [37, 38]]]], ["calgarske-listy_2003_unor_ocr.txt", "M\u00e1 hlad!\"", [["M\u00e1", "m\u00edt", "VERB", [0, 2]], ["hlad", "hlad", "NOUN", [3, 7]], ["!", "!", "PUNCT", [7, 8]], ["\"", "\"", "PUNCT", [8, 9]]]], ["calgarske-listy_2003_unor_ocr.txt", "\"A co budeme d\u011blat?\"", [["\"", "\"", "PUNCT", [0, 1]], ["A", "a", "CCONJ", [1, 2]], ["co", "co", "PRON", [3, 5]], ["budeme", "b\u00fdt", "AUX", [6, 12]], ["d\u011blat", "d\u011blat", "VERB", [13, 18]], ["?", "?", "PUNCT", [18, 19]], ["\"", "\"", "PUNCT", [19, 20]]]], ["calgarske-listy_2003_unor_ocr.txt", "\"", [["\"", "\"", "PUNCT", [0, 1]]]], ["calgarske-listy_2003_unor_ocr.txt", "Mus\u00edme ji nakrmit!\"\"", [["Mus\u00edme", "muset", "VERB", [0, 6]], ["ji", "on", "PRON", [7, 9]], ["nakrmit", "nakrmit", "VERB", [10, 17]], ["!", "!", "PUNCT", [17, 18]], ["\"", "\"", "PUNCT", [18, 19]], ["\"", "\"", "PUNCT", [19, 20]]]], ["calgarske-listy_2003_unor_ocr.txt", "Nakrmit?", [["Nakrmit", "nakrmit", "VERB", [0, 7]], ["?", "?", "PUNCT", [7, 8]]]], ["calgarske-listy_2003_unor_ocr.txt", "Jak a \u010d\u00edm?", [["Jak", "jak", "ADV", [0, 3]], ["a", "a", "CCONJ", [4, 5]], ["\u010d\u00edm", "co", "PRON", [6, 9]], ["?", "?", "PUNCT", [9, 10]]]], ["calgarske-listy_2003_unor_ocr.txt", "Zvl\u00e1dnu ledacos, ale kojit teda neum\u00edm!\"", [["Zvl\u00e1dnu", "zvl\u00e1dnout", "VERB", [0, 7]], ["ledacos", "ledacos", "PRON", [8, 15]], [",", ",", "PUNCT", [15, 16]], ["ale", "ale", "CCONJ", [17, 20]], ["kojit", "kojit", "VERB", [21, 26]], ["teda", "teda", "INTJ", [27, 31]], ["neum\u00edm", "um\u011bt", "VERB", [32, 38]], ["!", "!", "PUNCT", [38, 39]], ["\"", "\"", "PUNCT", [39, 40]]]], ["calgarske-listy_2003_unor_ocr.txt", "\"To v\u011b\u0159\u00edm.", [["\"", "\"", "PUNCT", [0, 1]], ["To", "ten", "DET", [1, 3]], ["v\u011b\u0159\u00edm", "v\u011b\u0159it", "VERB", [4, 9]], [".", ".", "PUNCT", [9, 10]]]], ["calgarske-listy_2003_unor_ocr.txt", "Nev\u00ed\u0161 n\u00e1hodou, nem\u00e1me n\u011bkde n\u011bjakou konzervu ml\u00e9ka?\"", [["Nev\u00ed\u0161", "v\u011bd\u011bt", "VERB", [0, 5]], ["n\u00e1hodou", "n\u00e1hodou", "ADV", [6, 13]], [",", ",", "PUNCT", [13, 14]], ["nem\u00e1me", "m\u00edt", "VERB", [15, 21]], ["n\u011bkde", "n\u011bkde", "ADV", [22, 27]], ["n\u011bjakou", "n\u011bjak\u00fd", "DET", [28, 35]], ["konzervu", "konzerva", "NOUN", [36, 44]], ["ml\u00e9ka", "ml\u00e9ko", "NOUN", [45, 50]], ["?", "?", "PUNCT", [50, 51]], ["\"", "\"", "PUNCT", [51, 52]]]], ["calgarske-listy_2003_unor_ocr.txt", "\"Ml\u00e9ko?\"", [["\"", "\"", "PUNCT", [0, 1]], ["Ml\u00e9ko", "ml\u00e9ko", "NOUN", [1, 6]], ["?", "?", "PUNCT", [6, 7]], ["\"", "\"", "PUNCT", [7, 8]]]], ["calgarske-listy_2003_unor_ocr.txt", "Bili >se skoro vyd\u011bsil.", [["Bili", "b\u00edt", "VERB", [0, 4]], [">se", "b\u00fdt", "AUX", [5, 8]], ["skoro", "skoro", "ADV", [9, 14]], ["vyd\u011bsil", "vyd\u011bsit", "VERB", [15, 22]], [".", ".", "PUNCT", [22, 23]]]], ["calgarske-listy_2003_unor_ocr.txt", "\"To jsem u\u017e nevid\u011bl p\u016fl roku!", [["\"", "\"", "PUNCT", [0, 1]], ["To", "ten", "DET", [1, 3]], ["jsem", "b\u00fdt", "AUX", [4, 8]], ["u\u017e", "u\u017e", "ADV", [9, 11]], ["nevid\u011bl", "vid\u011bt", "VERB", [12, 19]], ["p\u016fl", "p\u016fl", "NUM", [20, 23]], ["roku", "rok", "NOUN", [24, 28]], ["!", "!", "PUNCT", [28, 29]]]], ["calgarske-listy_2003_unor_ocr.txt", "A co je tady?\"", [["A", "a", "CCONJ", [0, 1]], ["co", "co", "PRON", [2, 4]], ["je", "b\u00fdt", "AUX", [5, 7]], ["tady", "tady", "ADV", [8, 12]], ["?", "?", "PUNCT", [12, 13]], ["\"", "\"", "PUNCT", [13, 14]]]], ["calgarske-listy_2003_unor_ocr.txt", "\"No po\u010dkej.....brandy a whisky, ale u\u017e jenom na dn\u011b...", [["\"", "\"", "PUNCT", [0, 1]], ["No", "no", "INTJ", [1, 3]], ["po\u010dkej", "po\u010dkej", "INTJ", [4, 10]], [".", ".", "PUNCT", [10, 11]], [".", ".", "PUNCT", [11, 12]], [".", ".", "PUNCT", [12, 13]], [".", ".", "PUNCT", [13, 14]], [".", ".", "PUNCT", [14, 15]], ["brandy", "brandy", "NOUN", [15, 21]], ["a", "a", "CCONJ", [22, 23]], ["whisky", "whisky", "NOUN", [24, 30]], [",", ",", "PUNCT", [30, 31]], ["ale", "ale", "CCONJ", [32, 35]], ["u\u017e", "u\u017e", "ADV", [36, 38]], ["jenom", "jenom", "PART", [39, 44]], ["na", "na", "ADP", [45, 47]], ["dn\u011b", "dno", "NOUN", [48, 51]], [".", ".", "PUNCT", [51, 52]], [".", ".", "PUNCT", [52, 53]], [".", ".", "PUNCT", [53, 54]]]], ["calgarske-listy_2003_unor_ocr.txt", "Bille, v\u017edy\u0165 se dneska narodila!", [["Bille", "bille", "NOUN", [0, 5]], [",", ",", "PUNCT", [5, 6]], ["v\u017edy\u0165", "v\u017edy\u0165", "CCONJ", [7, 12]], ["se", "se", "PRON", [13, 15]], ["dneska", "dneska", "ADV", [16, 22]], ["narodila", "narodit", "VERB", [23, 31]], ["!", "!", "PUNCT", [31, 32]]]], ["calgarske-listy_2003_unor_ocr.txt", "No pt\u00e1\u0161 se co tady je.", [["No", "no", "INTJ", [0, 2]], ["pt\u00e1\u0161", "pt\u00e1t", "VERB", [3, 7]], ["se", "se", "PRON", [8, 10]], ["co", "co", "PRON", [11, 13]], ["tady", "tady", "ADV", [14, 18]], ["je", "b\u00fdt", "AUX", [19, 21]], [".", ".", "PUNCT", [21, 22]]]], ["calgarske-listy_2003_unor_ocr.txt", "Jo a ten va\u0159enej medv\u011bd od v\u010dera.\"", [["Jo", "jo", "INTJ", [0, 2]], ["a", "a", "CCONJ", [3, 4]], ["ten", "ten", "DET", [5, 8]], ["va\u0159enej", "va\u0159enej", "NOUN", [9, 16]], ["medv\u011bd", "medv\u011bd", "NOUN", [17, 23]], ["od", "od", "ADP", [24, 26]], ["v\u010dera", "v\u010dera", "ADV", [27, 32]], [".", ".", "PUNCT", [32, 33]], ["\"", "\"", "PUNCT", [33, 34]]]], ["calgarske-listy_2003_unor_ocr.txt", "Johny ve\u0161el dovnit\u0159 a nad kamnama si oh\u0159\u00edval ruce.", [["Johny", "Johny", "PROPN", [0, 5]], ["ve\u0161el", "vej\u00edt", "VERB", [6, 11]], ["dovnit\u0159", "dovnit\u0159", "ADV", [12, 19]], ["a", "a", "CCONJ", [20, 21]], ["nad", "nad", "ADP", [22, 25]], ["kamnama", "kamnam", "NOUN", [26, 33]], ["si", "se", "PRON", [34, 36]], ["oh\u0159\u00edval", "oh\u0159\u00edvat", "VERB", [37, 44]], ["ruce", "ruka", "NOUN", [45, 49]], [".", ".", "PUNCT", [49, 50]]]], ["calgarske-listy_2003_unor_ocr.txt", "\"Co se d\u011bje?", [["\"", "\"", "PUNCT", [0, 1]], ["Co", "co", "PRON", [1, 3]], ["se", "se", "PRON", [4, 6]], ["d\u011bje", "d\u00edt", "VERB", [7, 11]], ["?", "?", "PUNCT", [11, 12]]]], ["calgarske-listy_2003_unor_ocr.txt", "Pro\u010d v\u00e1m to d\u00edt\u011b tady tak \u0159ve?", [["Pro\u010d", "pro\u010d", "ADV", [0, 4]], ["v\u00e1m", "vy", "PRON", [5, 8]], ["to", "ten", "DET", [9, 11]], ["d\u00edt\u011b", "d\u00edt\u011b", "NOUN", [12, 16]], ["tady", "tady", "ADV", [17, 21]], ["tak", "tak", "ADV", [22, 25]], ["\u0159ve", "\u0159v\u00e1t", "VERB", [26, 29]], ["?", "?", "PUNCT", [29, 30]]]], ["calgarske-listy_2003_unor_ocr.txt", "M\u00e1 asi hlad.\" komentoval Bili.", [["M\u00e1", "m\u00edt", "VERB", [0, 2]], ["asi", "asi", "PART", [3, 6]], ["hlad", "hlad", "NOUN", [7, 11]], [".", ".", "PUNCT", [11, 12]], ["\"", "\"", "PUNCT", [12, 13]], ["komentoval", "komentovat", "VERB", [14, 24]], ["Bili", "b\u00edt", "VERB", [25, 29]], [".", ".", "PUNCT", [29, 30]]]], ["calgarske-listy_2003_unor_ocr.txt", "\"To je teda mal\u00e9r.", [["\"", "\"", "PUNCT", [0, 1]], ["To", "ten", "DET", [1, 3]], ["je", "b\u00fdt", "AUX", [4, 6]], ["teda", "teda", "INTJ", [7, 11]], ["mal\u00e9r", "mal\u00e9r", "NOUN", [12, 17]], [".", ".", "PUNCT", [17, 18]]]], ["calgarske-listy_2003_unor_ocr.txt", "Co j\u00ed d\u00e1me?", [["Co", "co", "PRON", [0, 2]], ["j\u00ed", "on", "PRON", [3, 5]], ["d\u00e1me", "d\u00e1t", "VERB", [6, 10]], ["?", "?", "PUNCT", [10, 11]]]], ["calgarske-listy_2003_unor_ocr.txt", "Nev\u00edm.", [["Nev\u00edm", "v\u011bd\u011bt", "VERB", [0, 5]], [".", ".", "PUNCT", [5, 6]]]], ["calgarske-listy_2003_unor_ocr.txt", "Zjistili jsme, \u017ee jedin\u00e9 co tu je, je medv\u011bd, brandy a whisky.", [["Zjistili", "zjistit", "VERB", [0, 8]], ["jsme", "b\u00fdt", "AUX", [9, 13]], [",", ",", "PUNCT", [13, 14]], ["\u017ee", "\u017ee", "SCONJ", [15, 17]], ["jedin\u00e9", "jedin\u00fd", "ADJ", [18, 24]], ["co", "co", "PRON", [25, 27]], ["tu", "tu", "ADV", [28, 30]], ["je", "b\u00fdt", "AUX", [31, 33]], [",", ",", "PUNCT", [33, 34]], ["je", "b\u00fdt", "AUX", [35, 37]], ["medv\u011bd", "medv\u011bd", "NOUN", [38, 44]], [",", ",", "PUNCT", [44, 45]], ["brandy", "brandy", "NOUN", [46, 52]], ["a", "a", "CCONJ", [53, 54]], ["whisky", "whisky", "NOUN", [55, 61]], [".", ".", "PUNCT", [61, 62]]]], ["calgarske-listy_2003_unor_ocr.txt", "\"Bili str\u010dil hol\u010di\u010dku do n\u00e1ru\u010de Davov\u00ed.", [["\"", "\"", "PUNCT", [0, 1]], ["Bili", "b\u00edt", "VERB", [1, 5]], ["str\u010dil", "str\u010dit", "VERB", [6, 12]], ["hol\u010di\u010dku", "hol\u010di\u010dka", "NOUN", [13, 21]], ["do", "do", "ADP", [22, 24]], ["n\u00e1ru\u010de", "n\u00e1ru\u010d", "NOUN", [25, 31]], ["Davov\u00ed", "Davov\u00ed", "PROPN", [32, 38]], [".", ".", "PUNCT", [38, 39]]]], ["calgarske-listy_2003_unor_ocr.txt", "\"Na, te\u010f to zkus ty!\"", [["\"", "\"", "PUNCT", [0, 1]], ["Na", "na", "ADP", [1, 3]], [",", ",", "PUNCT", [3, 4]], ["te\u010f", "te\u010f", "ADV", [5, 8]], ["to", "ten", "DET", [9, 11]], ["zkus", "zkus", "VERB", [12, 16]], ["ty", "ten", "DET", [17, 19]], ["!", "!", "PUNCT", [19, 20]], ["\"", "\"", "PUNCT", [20, 21]]]], ["calgarske-listy_2003_unor_ocr.txt", "Miminko m\u00edsto k\u0159iku u\u017e jen poplak\u00e1valo.", [["Miminko", "miminko", "NOUN", [0, 7]], ["m\u00edsto", "m\u00edsto", "ADP", [8, 13]], ["k\u0159iku", "k\u0159ik", "NOUN", [14, 19]], ["u\u017e", "u\u017e", "ADV", [20, 22]], ["jen", "jen", "PART", [23, 26]], ["poplak\u00e1valo", "poplak\u00e1vat", "VERB", [27, 38]], [".", ".", "PUNCT", [38, 39]]]], ["calgarske-listy_2003_unor_ocr.txt", "\"Jak dlouho vydr\u017e\u00ed bez j\u00eddla?", [["\"", "\"", "PUNCT", [0, 1]], ["Jak", "jak", "ADV", [1, 4]], ["dlouho", "dlouho", "ADV", [5, 11]], ["vydr\u017e\u00ed", "vydr\u017eet", "VERB", [12, 18]], ["bez", "bez", "ADP", [19, 22]], ["j\u00eddla", "j\u00eddlo", "NOUN", [23, 28]], ["?", "?", "PUNCT", [28, 29]]]], ["calgarske-listy_2003_unor_ocr.txt", "Co j\u00e1 v\u00edm?", [["Co", "co", "PRON", [0, 2]], ["j\u00e1", "j\u00e1", "PRON", [3, 5]], ["v\u00edm", "v\u011bd\u011bt", "VERB", [6, 9]], ["?", "?", "PUNCT", [9, 10]]]], ["calgarske-listy_2003_unor_ocr.txt", "J\u00e1 nev\u00edm o d\u011btech zhola nic.\"", [["J\u00e1", "j\u00e1", "PRON", [0, 2]], ["nev\u00edm", "v\u011bd\u011bt", "VERB", [3, 8]], ["o", "o", "ADP", [9, 10]], ["d\u011btech", "d\u00edt\u011b", "NOUN", [11, 17]], ["zhola", "zhola", "ADV", [18, 23]], ["nic", "nic", "PRON", [24, 27]], [".", ".", "PUNCT", [27, 28]], ["\"", "\"", "PUNCT", [28, 29]]]], ["calgarske-listy_2003_unor_ocr.txt", "Johny si dal hlt\u00e1 z l\u00e1hve whisky.", [["Johny", "Johny", "PROPN", [0, 5]], ["si", "se", "PRON", [6, 8]], ["dal", "d\u00e1t", "VERB", [9, 12]], ["hlt\u00e1", "hltat", "VERB", [13, 17]], ["z", "z", "ADP", [18, 19]], ["l\u00e1hve", "l\u00e1hev", "NOUN", [20, 25]], ["whisky", "whisky", "NOUN", [26, 32]], [".", ".", "PUNCT", [32, 33]]]], ["calgarske-listy_2003_unor_ocr.txt", "\"Co je hrozn\u00e9 je to, \u017ee tohle prvn\u00ed d\u00edt\u011b co m\u00e1me, nem\u00e1me s n\u011bjakou hezkou holkou, ale spolu.\u201d", [["\"", "\"", "PUNCT", [0, 1]], ["Co", "co", "PRON", [1, 3]], ["je", "b\u00fdt", "AUX", [4, 6]], ["hrozn\u00e9", "hrozn\u00fd", "ADJ", [7, 13]], ["je", "b\u00fdt", "AUX", [14, 16]], ["to", "ten", "DET", [17, 19]], [",", ",", "PUNCT", [19, 20]], ["\u017ee", "\u017ee", "SCONJ", [21, 23]], ["tohle", "tenhle", "DET", [24, 29]], ["prvn\u00ed", "prvn\u00ed", "ADJ", [30, 35]], ["d\u00edt\u011b", "d\u00edt\u011b", "NOUN", [36, 40]], ["co", "co", "PRON", [41, 43]], ["m\u00e1me", "m\u00edt", "VERB", [44, 48]], [",", ",", "PUNCT", [48, 49]], ["nem\u00e1me", "m\u00edt", "VERB", [50, 56]], ["s", "s", "ADP", [57, 58]], ["n\u011bjakou", "n\u011bjak\u00fd", "DET", [59, 66]], ["hezkou", "hezk\u00fd", "ADJ", [67, 73]], ["holkou", "holka", "NOUN", [74, 80]], [",", ",", "PUNCT", [80, 81]], ["ale", "ale", "CCONJ", [82, 85]], ["spolu", "spolu", "ADV", [86, 91]], [".", ".", "PUNCT", [91, 92]], ["\u201d", "\"", "PUNCT", [92, 93]]]], ["calgarske-listy_2003_unor_ocr.txt", "\u201cFuj, hele Johny, vynech legr\u00e1cky.", [["\u201c", "\"", "PUNCT", [0, 1]], ["Fuj", "fuj", "INTJ", [1, 4]], [",", ",", "PUNCT", [4, 5]], ["hele", "hele", "INTJ", [6, 10]], ["Johny", "Johny", "PROPN", [11, 16]], [",", ",", "PUNCT", [16, 17]], ["vynech", "vyn", "NOUN", [18, 24]], ["legr\u00e1cky", "legr\u00e1cka", "NOUN", [25, 33]], [".", ".", "PUNCT", [33, 34]]]], ["calgarske-listy_2003_unor_ocr.txt", "Co j\u00ed proboha d\u00e1me?", [["Co", "co", "PRON", [0, 2]], ["j\u00ed", "on", "PRON", [3, 5]], ["proboha", "proboha", "ADV", [6, 13]], ["d\u00e1me", "d\u00e1t", "VERB", [14, 18]], ["?", "?", "PUNCT", [18, 19]]]], ["calgarske-listy_2003_unor_ocr.txt", "\u201cNo co?", [["\u201c", "\"", "PUNCT", [0, 1]], ["No", "no", "INTJ", [1, 3]], ["co", "co", "PRON", [4, 6]], ["?", "?", "PUNCT", [6, 7]]]], ["calgarske-listy_2003_unor_ocr.txt", "M\u00e1me snad na v\u00fdb\u011br?", [["M\u00e1me", "m\u00edt", "VERB", [0, 4]], ["snad", "snad", "PART", [5, 9]], ["na", "na", "ADP", [10, 12]], ["v\u00fdb\u011br", "v\u00fdb\u011br", "NOUN", [13, 18]], ["?", "?", "PUNCT", [18, 19]]]], ["calgarske-listy_2003_unor_ocr.txt", "Trochu pol\u00edvky z toho medv\u011bda.", [["Trochu", "trochu", "ADV", [0, 6]], ["pol\u00edvky", "pol\u00edvka", "NOUN", [7, 14]], ["z", "z", "ADP", [15, 16]], ["toho", "ten", "DET", [17, 21]], ["medv\u011bda", "medv\u011bd", "NOUN", [22, 29]], [".", ".", "PUNCT", [29, 30]]]], ["calgarske-listy_2003_unor_ocr.txt", "Nic jin\u00e9ho tu nen\u00ed, tak nen\u00ed co \u0159e\u0161it.\u201d", [["Nic", "nic", "PRON", [0, 3]], ["jin\u00e9ho", "jin\u00fd", "ADJ", [4, 10]], ["tu", "tu", "ADV", [11, 13]], ["nen\u00ed", "b\u00fdt", "AUX", [14, 18]], [",", ",", "PUNCT", [18, 19]], ["tak", "tak", "ADV", [20, 23]], ["nen\u00ed", "b\u00fdt", "AUX", [24, 28]], ["co", "co", "PRON", [29, 31]], ["\u0159e\u0161it", "\u0159e\u0161it", "VERB", [32, 37]], [".", ".", "PUNCT", [37, 38]], ["\u201d", "\"", "PUNCT", [38, 39]]]], ["calgarske-listy_2003_unor_ocr.txt", "\u201cM\u00e1\u0161 pravdu.\u201d \u0159ekl Dave a Bili p\u0159isunul na kamna hrnec s medv\u011bdem va\u0159en\u00fdm ve vod\u011b.", [["\u201c", "\"", "PUNCT", [0, 1]], ["M\u00e1\u0161", "m\u00edt", "VERB", [1, 4]], ["pravdu", "pravda", "NOUN", [5, 11]], [".", ".", "PUNCT", [11, 12]], ["\u201d", "\"", "PUNCT", [12, 13]], ["\u0159ekl", "\u0159\u00edci", "VERB", [14, 18]], ["Dave", "Dave", "PROPN", [19, 23]], ["a", "a", "CCONJ", [24, 25]], ["Bili", "b\u00edt", "VERB", [26, 30]], ["p\u0159isunul", "p\u0159isunout", "VERB", [31, 39]], ["na", "na", "ADP", [40, 42]], ["kamna", "kamna", "NOUN", [43, 48]], ["hrnec", "hrnec", "NOUN", [49, 54]], ["s", "s", "ADP", [55, 56]], ["medv\u011bdem", "medv\u011bd", "NOUN", [57, 65]], ["va\u0159en\u00fdm", "va\u0159en\u00fd", "ADJ", [66, 73]], ["ve", "v", "ADP", [74, 76]], ["vod\u011b", "voda", "NOUN", [77, 81]], [".", ".", "PUNCT", [81, 82]]]], ["calgarske-listy_2003_unor_ocr.txt", "Po chv\u00edli d\u016fle\u017eit\u011b zkusil palcem, jestli je pol\u00e9vka u\u017e vhodn\u00e1 k pit\u00ed.", [["Po", "po", "ADP", [0, 2]], ["chv\u00edli", "chv\u00edle", "NOUN", [3, 9]], ["d\u016fle\u017eit\u011b", "d\u016fle\u017eit\u011b", "ADV", [10, 18]], ["zkusil", "zkusit", "VERB", [19, 25]], ["palcem", "palce", "NOUN", [26, 32]], [",", ",", "PUNCT", [32, 33]], ["jestli", "jestli", "SCONJ", [34, 40]], ["je", "b\u00fdt", "AUX", [41, 43]], ["pol\u00e9vka", "pol\u00e9vka", "NOUN", [44, 51]], ["u\u017e", "u\u017e", "ADV", [52, 54]], ["vhodn\u00e1", "vhodn\u00fd", "ADJ", [55, 61]], ["k", "k", "ADP", [62, 63]], ["pit\u00ed", "pit\u00ed", "NOUN", [64, 68]], [".", ".", "PUNCT", [68, 69]]]], ["calgarske-listy_2003_unor_ocr.txt", "Potom vzal l\u017e\u00edci a ochutnal.", [["Potom", "potom", "ADV", [0, 5]], ["vzal", "vz\u00edt", "VERB", [6, 10]], ["l\u017e\u00edci", "l\u017e\u00edce", "NOUN", [11, 16]], ["a", "a", "CCONJ", [17, 18]], ["ochutnal", "ochutnat", "VERB", [19, 27]], [".", ".", "PUNCT", [27, 28]]]], ["calgarske-listy_2003_unor_ocr.txt", "\"Nic moc to nen\u00ed, ale co se d\u00e1 d\u011blat!\"", [["\"", "\"", "PUNCT", [0, 1]], ["Nic", "nic", "PRON", [1, 4]], ["moc", "moc", "ADV", [5, 8]], ["to", "ten", "DET", [9, 11]], ["nen\u00ed", "b\u00fdt", "AUX", [12, 16]], [",", ",", "PUNCT", [16, 17]], ["ale", "ale", "CCONJ", [18, 21]], ["co", "co", "PRON", [22, 24]], ["se", "se", "PRON", [25, 27]], ["d\u00e1", "d\u00e1t", "VERB", [28, 30]], ["d\u011blat", "d\u011blat", "VERB", [31, 36]], ["!", "!", "PUNCT", [36, 37]], ["\"", "\"", "PUNCT", [37, 38]]]], ["calgarske-listy_2003_unor_ocr.txt", "\"Po\u010dkej, trochu to sprav\u00edm\" \u0159ekl Johny a cvrkl do hrnce tro\u0161ku brandy.", [["\"", "\"", "PUNCT", [0, 1]], ["Po\u010dkej", "po\u010dkat", "VERB", [1, 7]], [",", ",", "PUNCT", [7, 8]], ["trochu", "trochu", "ADV", [9, 15]], ["to", "ten", "DET", [16, 18]], ["sprav\u00edm", "spravit", "VERB", [19, 26]], ["\"", "\"", "PUNCT", [26, 27]], ["\u0159ekl", "\u0159\u00edci", "VERB", [28, 32]], ["Johny", "Johny", "PROPN", [33, 38]], ["a", "a", "CCONJ", [39, 40]], ["cvrkl", "cvrknout", "VERB", [41, 46]], ["do", "do", "ADP", [47, 49]], ["hrnce", "hrnec", "NOUN", [50, 55]], ["tro\u0161ku", "tro\u0161ku", "ADV", [56, 62]], ["brandy", "brandy", "NOUN", [63, 69]], [".", ".", "PUNCT", [69, 70]]]], ["calgarske-listy_2003_unor_ocr.txt", "\"Jo, u\u017e je to lep\u0161\u00ed\" znovu ochutnal Bill.", [["\"", "\"", "PUNCT", [0, 1]], ["Jo", "jo", "INTJ", [1, 3]], [",", ",", "PUNCT", [3, 4]], ["u\u017e", "u\u017e", "ADV", [5, 7]], ["je", "b\u00fdt", "AUX", [8, 10]], ["to", "ten", "DET", [11, 13]], ["lep\u0161\u00ed", "lep\u0161\u00ed", "ADJ", [14, 19]], ["\"", "\"", "PUNCT", [19, 20]], ["znovu", "znovu", "ADV", [21, 26]], ["ochutnal", "ochutnat", "VERB", [27, 35]], ["Bill", "Bill", "PROPN", [36, 40]], [".", ".", "PUNCT", [40, 41]]]], ["calgarske-listy_2003_unor_ocr.txt", "\"Kam se hrabe mate\u0159sk\u00fd ml\u00edko!", [["\"", "\"", "PUNCT", [0, 1]], ["Kam", "kam", "ADV", [1, 4]], ["se", "se", "PRON", [5, 7]], ["hrabe", "hr\u00e1bat", "VERB", [8, 13]], ["mate\u0159sk\u00fd", "mate\u0159sk\u00fd", "ADJ", [14, 22]], ["ml\u00edko", "ml\u00edko", "NOUN", [23, 28]], ["!", "!", "PUNCT", [28, 29]]]], ["calgarske-listy_2003_unor_ocr.txt", "M\u00e1\u0161 tam je\u0161t\u011b trochu t\u00fd brandy?\u201d \u201cSta\u010d\u00ed\u201d, rozhodl Johny.", [["M\u00e1\u0161", "m\u00edt", "VERB", [0, 3]], ["tam", "tam", "ADV", [4, 7]], ["je\u0161t\u011b", "je\u0161t\u011b", "ADV", [8, 13]], ["trochu", "trochu", "ADV", [14, 20]], ["t\u00fd", "t\u00fd", "ADP", [21, 23]], ["brandy", "brandy", "NOUN", [24, 30]], ["?", "?", "PUNCT", [30, 31]], ["\u201d", "\"", "PUNCT", [31, 32]], ["\u201c", "\"", "PUNCT", [33, 34]], ["Sta\u010d\u00ed", "sta\u010dit", "VERB", [34, 39]], ["\u201d", "\"", "PUNCT", [39, 40]], [",", ",", "PUNCT", [40, 41]], ["rozhodl", "rozhodnout", "VERB", [42, 49]], ["Johny", "Johny", "PROPN", [50, 55]], [".", ".", "PUNCT", [55, 56]]]], ["calgarske-listy_2003_unor_ocr.txt", "\"Je to p\u0159ece jen mimino!\"", [["\"", "\"", "PUNCT", [0, 1]], ["Je", "b\u00fdt", "AUX", [1, 3]], ["to", "ten", "DET", [4, 6]], ["p\u0159ece", "p\u0159ece", "PART", [7, 12]], ["jen", "jen", "ADV", [13, 16]], ["mimino", "mimino", "NOUN", [17, 23]], ["!", "!", "PUNCT", [23, 24]], ["\"", "\"", "PUNCT", [24, 25]]]], ["calgarske-listy_2003_unor_ocr.txt", "\"Tak uka\u017e, j\u00e1 ji podr\u017e\u00edm.\"", [["\"", "\"", "PUNCT", [0, 1]], ["Tak", "tak", "ADV", [1, 4]], ["uka\u017e", "uk\u00e1zat", "VERB", [5, 9]], [",", ",", "PUNCT", [9, 10]], ["j\u00e1", "j\u00e1", "PRON", [11, 13]], ["ji", "on", "PRON", [14, 16]], ["podr\u017e\u00edm", "podr\u017eet", "VERB", [17, 24]], [".", ".", "PUNCT", [24, 25]], ["\"", "\"", "PUNCT", [25, 26]]]], ["calgarske-listy_2003_unor_ocr.txt", "Zat\u00edm co Johny dr\u017eel hol\u010di\u010dku na kl\u00edn\u011b, Bili se sna\u017eil j\u00ed vpravit do pusy l\u017ei\u010dku s v\u00fdvarem.", [["Zat\u00edm", "zat\u00edm", "ADV", [0, 5]], ["co", "co", "PRON", [6, 8]], ["Johny", "Johny", "PROPN", [9, 14]], ["dr\u017eel", "dr\u017eet", "VERB", [15, 20]], ["hol\u010di\u010dku", "hol\u010di\u010dka", "NOUN", [21, 29]], ["na", "na", "ADP", [30, 32]], ["kl\u00edn\u011b", "kl\u00ed\u0148", "NOUN", [33, 38]], [",", ",", "PUNCT", [38, 39]], ["Bili", "b\u00edt", "VERB", [40, 44]], ["se", "se", "PRON", [45, 47]], ["sna\u017eil", "sna\u017eit", "VERB", [48, 54]], ["j\u00ed", "on", "PRON", [55, 57]], ["vpravit", "vpravit", "VERB", [58, 65]], ["do", "do", "ADP", [66, 68]], ["pusy", "pusa", "NOUN", [69, 73]], ["l\u017ei\u010dku", "l\u017ei\u010dka", "NOUN", [74, 80]], ["s", "s", "ADP", [81, 82]], ["v\u00fdvarem", "v\u00fdvar", "NOUN", [83, 90]], [".", ".", "PUNCT", [90, 91]]]], ["calgarske-listy_2003_unor_ocr.txt", "Hol\u010di\u010dka, za\u010dala kuckat a prskat.", [["Hol\u010di\u010dka", "hol\u010di\u010dka", "NOUN", [0, 8]], [",", ",", "PUNCT", [8, 9]], ["za\u010dala", "za\u010d\u00edt", "VERB", [10, 16]], ["kuckat", "kuckat", "VERB", [17, 23]], ["a", "a", "CCONJ", [24, 25]], ["prskat", "prskat", "VERB", [26, 32]], [".", ".", "PUNCT", [32, 33]]]], ["calgarske-listy_2003_unor_ocr.txt", "\"Tak to nep\u016fjde,\" ot\u0159el si Johny ruk\u00e1vem tv\u00e1\u0159.", [["\"", "\"", "PUNCT", [0, 1]], ["Tak", "tak", "ADV", [1, 4]], ["to", "ten", "DET", [5, 7]], ["nep\u016fjde", "j\u00edt", "VERB", [8, 15]], [",", ",", "PUNCT", [15, 16]], ["\"", "\"", "PUNCT", [16, 17]], ["ot\u0159el", "ot\u0159\u00edt", "VERB", [18, 23]], ["si", "se", "PRON", [24, 26]], ["Johny", "Johny", "PROPN", [27, 32]], ["ruk\u00e1vem", "ruk\u00e1v", "NOUN", [33, 40]], ["tv\u00e1\u0159", "tv\u00e1\u0159", "NOUN", [41, 45]], [".", ".", "PUNCT", [45, 46]]]], ["calgarske-listy_2003_unor_ocr.txt", "\"Nebyla v tom srubu n\u011bjak\u00e1 fla\u0161ka?\"", [["\"", "\"", "PUNCT", [0, 1]], ["Nebyla", "b\u00fdt", "AUX", [1, 7]], ["v", "v", "ADP", [8, 9]], ["tom", "ten", "DET", [10, 13]], ["srubu", "srub", "NOUN", [14, 19]], ["n\u011bjak\u00e1", "n\u011bjak\u00fd", "DET", [20, 26]], ["fla\u0161ka", "fla\u0161ka", "NOUN", [27, 33]], ["?", "?", "PUNCT", [33, 34]], ["\"", "\"", "PUNCT", [34, 35]]]], ["calgarske-listy_2003_unor_ocr.txt", "\"Nevid\u011bl jsem tam nic takov\u00fdho\" Bili polo\u017eil l\u017e\u00edci, \"tak co te\u010f?\"", [["\"", "\"", "PUNCT", [0, 1]], ["Nevid\u011bl", "vid\u011bt", "VERB", [1, 8]], ["jsem", "b\u00fdt", "AUX", [9, 13]], ["tam", "tam", "ADV", [14, 17]], ["nic", "nic", "PRON", [18, 21]], ["takov\u00fdho", "takov\u00fd", "DET", [22, 30]], ["\"", "\"", "PUNCT", [30, 31]], ["Bili", "b\u00edt", "VERB", [32, 36]], ["polo\u017eil", "polo\u017eit", "VERB", [37, 44]], ["l\u017e\u00edci", "l\u017e\u00edce", "NOUN", [45, 50]], [",", ",", "PUNCT", [50, 51]], ["\"", "\"", "PUNCT", [52, 53]], ["tak", "tak", "ADV", [53, 56]], ["co", "co", "PRON", [57, 59]], ["te\u010f", "te\u010f", "ADV", [60, 63]], ["?", "?", "PUNCT", [63, 64]], ["\"", "\"", "PUNCT", [64, 65]]]], ["calgarske-listy_2003_unor_ocr.txt", "\"To jsem netu\u0161il jak je to slo\u017eit\u00fd m\u00edt d\u00edt\u011b!", [["\"", "\"", "PUNCT", [0, 1]], ["To", "ten", "DET", [1, 3]], ["jsem", "b\u00fdt", "AUX", [4, 8]], ["netu\u0161il", "tu\u0161it", "VERB", [9, 16]], ["jak", "jak", "ADV", [17, 20]], ["je", "b\u00fdt", "AUX", [21, 23]], ["to", "ten", "DET", [24, 26]], ["slo\u017eit\u00fd", "slo\u017eit\u00fd", "ADJ", [27, 34]], ["m\u00edt", "m\u00edt", "VERB", [35, 38]], ["d\u00edt\u011b", "d\u00edt\u011b", "NOUN", [39, 43]], ["!", "!", "PUNCT", [43, 44]]]], ["calgarske-listy_2003_unor_ocr.txt", "Je\u0161t\u011b \u017ee nejsem \u017eensk\u00e1!\"", [["Je\u0161t\u011b", "je\u0161t\u011b", "ADV", [0, 5]], ["\u017ee", "\u017ee", "SCONJ", [6, 8]], ["nejsem", "b\u00fdt", "AUX", [9, 15]], ["\u017eensk\u00e1", "\u017eensk\u00fd", "ADJ", [16, 22]], ["!", "!", "PUNCT", [22, 23]], ["\"", "\"", "PUNCT", [23, 24]]]], ["calgarske-listy_2003_unor_ocr.txt", "\"J\u00e1 bych rad\u0161i kdybys byl!", [["\"", "\"", "PUNCT", [0, 1]], ["J\u00e1", "j\u00e1", "PRON", [1, 3]], ["bych", "b\u00fdt", "AUX", [4, 8]], ["rad\u0161i", "r\u00e1d", "ADV", [9, 14]], ["kdy\u017e", "kdy\u017e", "SCONJ", [-24829, -24829]], ["byss", "byss", "NOUN", [-24829, -24829]], ["byl", "b\u00fdt", "AUX", [22, 25]], ["!", "!", "PUNCT", [25, 26]]]], ["calgarske-listy_2003_unor_ocr.txt", "Hele Dave, kolik je tam v t\u00e9 fla\u0161ce je\u0161t\u011b t\u00fd whisky?\"", [["Hele", "Hele", "PROPN", [0, 4]], ["Dave", "Dave", "PROPN", [5, 9]], [",", ",", "PUNCT", [9, 10]], ["kolik", "kolik", "DET", [11, 16]], ["je", "b\u00fdt", "AUX", [17, 19]], ["tam", "tam", "ADV", [20, 23]], ["v", "v", "ADP", [24, 25]], ["t\u00e9", "ten", "DET", [26, 28]], ["fla\u0161ce", "fla\u0161ec", "NOUN", [29, 35]], ["je\u0161t\u011b", "je\u0161t\u011b", "ADV", [36, 41]], ["t\u00fd", "t\u00fd", "INTJ", [42, 44]], ["whisky", "whisky", "NOUN", [45, 51]], ["?", "?", "PUNCT", [51, 52]], ["\"", "\"", "PUNCT", [52, 53]]]], ["calgarske-listy_2003_unor_ocr.txt", "\"\u017d\u00e1dn\u00e1!\" \u0159ekl Dave a dopil posledn\u00ed hlt.", [["\"", "\"", "PUNCT", [0, 1]], ["\u017d\u00e1dn\u00e1", "\u017e\u00e1dn\u00fd", "DET", [1, 6]], ["!", "!", "PUNCT", [6, 7]], ["\"", "\"", "PUNCT", [7, 8]], ["\u0159ekl", "\u0159\u00edci", "VERB", [9, 13]], ["Dave", "Dave", "PROPN", [14, 18]], ["a", "a", "CCONJ", [19, 20]], ["dopil", "dop\u00edt", "VERB", [21, 26]], ["posledn\u00ed", "posledn\u00ed", "ADJ", [27, 35]], ["hlt", "hlt", "NOUN", [36, 39]], [".", ".", "PUNCT", [39, 40]]]], ["calgarske-listy_2003_unor_ocr.txt", "\"Tak a m\u00e1me fla\u0161ku\" \u0159ekl spokojen\u011b Johny, \"te\u010f je\u0161t\u011b dudl\u00edk, Dave ty m\u00e1\u0161 dvoje ko\u017een\u00e9 rukavice, dej mi jedny.\"", [["\"", "\"", "PUNCT", [0, 1]], ["Tak", "tak", "ADV", [1, 4]], ["a", "a", "CCONJ", [5, 6]], ["m\u00e1me", "m\u00edt", "VERB", [7, 11]], ["fla\u0161ku", "fla\u0161ek", "NOUN", [12, 18]], ["\"", "\"", "PUNCT", [18, 19]], ["\u0159ekl", "\u0159\u00edci", "VERB", [20, 24]], ["spokojen\u011b", "spokojen\u011b", "ADV", [25, 34]], ["Johny", "Johny", "PROPN", [35, 40]], [",", ",", "PUNCT", [40, 41]], ["\"", "\"", "PUNCT", [42, 43]], ["te\u010f", "te\u010f", "ADV", [43, 46]], ["je\u0161t\u011b", "je\u0161t\u011b", "ADV", [47, 52]], ["dudl\u00edk", "dudl\u00edk", "NOUN", [53, 59]], [",", ",", "PUNCT", [59, 60]], ["Dave", "Dave", "PROPN", [61, 65]], ["ty", "ten", "DET", [66, 68]], ["m\u00e1\u0161", "m\u00edt", "VERB", [69, 72]], ["dvoje", "dvoj\u00ed", "ADJ", [73, 78]], ["ko\u017een\u00e9", "ko\u017een\u00fd", "ADJ", [79, 85]], ["rukavice", "rukavice", "NOUN", [86, 94]], [",", ",", "PUNCT", [94, 95]], ["dej", "d\u00e1t", "VERB", [96, 99]], ["mi", "j\u00e1", "PRON", [100, 102]], ["jedny", "jedny", "ADV", [103, 108]], [".", ".", "PUNCT", [108, 109]], ["\"", "\"", "PUNCT", [109, 110]]]], ["calgarske-listy_2003_unor_ocr.txt", "Dave se ne\u0161\u0165astn\u011b d\u00edval, jak Johny nel\u00edtostn\u011b u\u0159\u00edzl z rukavice jeden prst.", [["Dave", "Dave", "PROPN", [0, 4]], ["se", "se", "PRON", [5, 7]], ["ne\u0161\u0165astn\u011b", "\u0161\u0165astn\u011b", "ADV", [8, 17]], ["d\u00edval", "d\u00edvat", "VERB", [18, 23]], [",", ",", "PUNCT", [23, 24]], ["jak", "jak", "ADV", [25, 28]], ["Johny", "Johny", "PROPN", [29, 34]], ["nel\u00edtostn\u011b", "l\u00edtostn\u011b", "ADV", [35, 45]], ["u\u0159\u00edzl", "u\u0159\u00edznout", "VERB", [46, 51]], ["z", "z", "ADP", [52, 53]], ["rukavice", "rukavice", "NOUN", [54, 62]], ["jeden", "jeden", "NUM", [63, 68]], ["prst", "prst", "NOUN", [69, 73]], [".", ".", "PUNCT", [73, 74]]]], ["calgarske-listy_2003_unor_ocr.txt", "\"Ty ses zbl\u00e1znil!", [["\"", "\"", "PUNCT", [0, 1]], ["Ty", "ten", "DET", [1, 3]], ["ses", "ses", "NOUN", [4, 7]], ["zbl\u00e1znil", "zbl\u00e1znit", "VERB", [8, 16]], ["!", "!", "PUNCT", [16, 17]]]], ["calgarske-listy_2003_unor_ocr.txt", "Jin\u00fd tady nese\u017eenu!\"", [["Jin\u00fd", "jin\u00fd", "ADJ", [0, 4]], ["tady", "tady", "ADV", [5, 9]], ["nese\u017eenu", "sehnat", "VERB", [10, 18]], ["!", "!", "PUNCT", [18, 19]], ["\"", "\"", "PUNCT", [19, 20]]]], ["calgarske-listy_2003_unor_ocr.txt", "\"M\u00e1\u0161 druh\u00fd, dal bych svoji, ale pak abych do konce zimy nosil ruku v kapse a to po mn\u011b nem\u016f\u017ee\u0161 cht\u00edt.", [["\"", "\"", "PUNCT", [0, 1]], ["M\u00e1\u0161", "m\u00edt", "VERB", [1, 4]], ["druh\u00fd", "druh\u00fd", "ADJ", [5, 10]], [",", ",", "PUNCT", [10, 11]], ["dal", "d\u00e1t", "VERB", [12, 15]], ["bych", "b\u00fdt", "AUX", [16, 20]], ["svoji", "sv\u016fj", "DET", [21, 26]], [",", ",", "PUNCT", [26, 27]], ["ale", "ale", "CCONJ", [28, 31]], ["pak", "pak", "ADV", [32, 35]], ["aby", "aby", "SCONJ", [-25176, -25176]], ["bych", "b\u00fdt", "AUX", [-25176, -25176]], ["do", "do", "ADP", [42, 44]], ["konce", "konec", "NOUN", [45, 50]], ["zimy", "zima", "NOUN", [51, 55]], ["nosil", "nosit", "VERB", [56, 61]], ["ruku", "ruka", "NOUN", [62, 66]], ["v", "v", "ADP", [67, 68]], ["kapse", "kapsa", "NOUN", [69, 74]], ["a", "a", "CCONJ", [75, 76]], ["to", "ten", "DET", [77, 79]], ["po", "po", "ADP", [80, 82]], ["mn\u011b", "j\u00e1", "PRON", [83, 86]], ["nem\u016f\u017ee\u0161", "moci", "VERB", [87, 94]], ["cht\u00edt", "cht\u00edt", "VERB", [95, 100]], [".", ".", "PUNCT", [100, 101]]]], ["calgarske-listy_2003_unor_ocr.txt", "Johny navl\u00e9kl prst z rukavice na hrdlo lahve.", [["Johny", "Johny", "PROPN", [0, 5]], ["navl\u00e9kl", "navl\u00e9knout", "VERB", [6, 13]], ["prst", "prst", "NOUN", [14, 18]], ["z", "z", "ADP", [19, 20]], ["rukavice", "rukavice", "NOUN", [21, 29]], ["na", "na", "ADP", [30, 32]], ["hrdlo", "hrdlo", "NOUN", [33, 38]], ["lahve", "lahev", "NOUN", [39, 44]], [".", ".", "PUNCT", [44, 45]]]], ["calgarske-listy_2003_unor_ocr.txt", "\"P\u016fjde to!\"", [["\"", "\"", "PUNCT", [0, 1]], ["P\u016fjde", "j\u00edt", "VERB", [1, 6]], ["to", "ten", "DET", [7, 9]], ["!", "!", "PUNCT", [9, 10]], ["\"", "\"", "PUNCT", [10, 11]]]], ["calgarske-listy_2003_unor_ocr.txt", "Nalili do fla\u0161ky v\u00fdvar a str\u010dili hol\u010di\u010dce do pusy.", [["Nalili", "nal\u00edt", "VERB", [0, 6]], ["do", "do", "ADP", [7, 9]], ["fla\u0161ky", "fla\u0161ka", "NOUN", [10, 16]], ["v\u00fdvar", "v\u00fdvar", "NOUN", [17, 22]], ["a", "a", "CCONJ", [23, 24]], ["str\u010dili", "str\u010dit", "VERB", [25, 32]], ["hol\u010di\u010dce", "hol\u010di\u010dka", "NOUN", [33, 41]], ["do", "do", "ADP", [42, 44]], ["pusy", "pusa", "NOUN", [45, 49]], [".", ".", "PUNCT", [49, 50]]]], ["calgarske-listy_2003_unor_ocr.txt", "D\u00edt\u011b n\u011bkolikr\u00e1t improvizovan\u00fd dudl\u00edk vyplivlo, ale pak za\u010dalo p\u00edt a pomlask\u00e1vat.", [["D\u00edt\u011b", "d\u00edt\u011b", "NOUN", [0, 4]], ["n\u011bkolikr\u00e1t", "n\u011bkolikr\u00e1t", "ADV", [5, 15]], ["improvizovan\u00fd", "improvizovan\u00fd", "ADJ", [16, 29]], ["dudl\u00edk", "dudl\u00edk", "NOUN", [30, 36]], ["vyplivlo", "vyplivnout", "VERB", [37, 45]], [",", ",", "PUNCT", [45, 46]], ["ale", "ale", "CCONJ", [47, 50]], ["pak", "pak", "ADV", [51, 54]], ["za\u010dalo", "za\u010d\u00edt", "VERB", [55, 61]], ["p\u00edt", "p\u00edt", "VERB", [62, 65]], ["a", "a", "CCONJ", [66, 67]], ["pomlask\u00e1vat", "pomlask\u00e1vat", "VERB", [68, 79]], [".", ".", "PUNCT", [79, 80]]]], ["calgarske-listy_2003_unor_ocr.txt", "V\u0161ichni t\u0159i chlapci na ni s nad\u0161en\u00edm koukali.", [["V\u0161ichni", "v\u0161echen", "DET", [0, 7]], ["t\u0159i", "t\u0159i", "NUM", [8, 11]], ["chlapci", "chlapec", "NOUN", [12, 19]], ["na", "na", "ADP", [20, 22]], ["ni", "on", "PRON", [23, 25]], ["s", "s", "ADP", [26, 27]], ["nad\u0161en\u00edm", "nad\u0161en\u00ed", "NOUN", [28, 36]], ["koukali", "koukat", "VERB", [37, 44]], [".", ".", "PUNCT", [44, 45]]]], ["calgarske-listy_2003_unor_ocr.txt", "\"Tak jsme to zvl\u00e1dli\" pochv\u00e1lil Bili.", [["\"", "\"", "PUNCT", [0, 1]], ["Tak", "tak", "ADV", [1, 4]], ["jsme", "b\u00fdt", "AUX", [5, 9]], ["to", "ten", "DET", [10, 12]], ["zvl\u00e1dli", "zvl\u00e1dnout", "VERB", [13, 20]], ["\"", "\"", "PUNCT", [20, 21]], ["pochv\u00e1lil", "pochv\u00e1lit", "VERB", [22, 31]], ["Bili", "b\u00edt", "VERB", [32, 36]], [".", ".", "PUNCT", [36, 37]]]], ["calgarske-listy_2003_unor_ocr.txt", "Ve srubu u\u017e bylo p\u0159\u00edjemn\u011b teplo.", [["Ve", "v", "ADP", [0, 2]], ["srubu", "srub", "NOUN", [3, 8]], ["u\u017e", "u\u017e", "ADV", [9, 11]], ["bylo", "b\u00fdt", "AUX", [12, 16]], ["p\u0159\u00edjemn\u011b", "p\u0159\u00edjemn\u011b", "ADV", [17, 25]], ["teplo", "teplo", "NOUN", [26, 31]], [".", ".", "PUNCT", [31, 32]]]], ["calgarske-listy_2003_unor_ocr.txt", "Rozbalili hol\u010di\u010dku a Dave za\u010dal jemn\u011b had\u0159\u00edkem ot\u00edrat z neuv\u011b\u0159iteln\u011b drobn\u00e9ho t\u011bl\u00ed\u010dka zbytky krve po porodu.", [["Rozbalili", "rozbalit", "VERB", [0, 9]], ["hol\u010di\u010dku", "hol\u010di\u010dka", "NOUN", [10, 18]], ["a", "a", "CCONJ", [19, 20]], ["Dave", "Dave", "PROPN", [21, 25]], ["za\u010dal", "za\u010d\u00edt", "VERB", [26, 31]], ["jemn\u011b", "jemn\u011b", "ADV", [32, 37]], ["had\u0159\u00edkem", "had\u0159\u00edk", "NOUN", [38, 46]], ["ot\u00edrat", "ot\u00edrat", "VERB", [47, 53]], ["z", "z", "ADP", [54, 55]], ["neuv\u011b\u0159iteln\u011b", "uv\u011b\u0159iteln\u011b", "ADV", [56, 68]], ["drobn\u00e9ho", "drobn\u00fd", "ADJ", [69, 77]], ["t\u011bl\u00ed\u010dka", "t\u011bl\u00ed\u010dko", "NOUN", [78, 85]], ["zbytky", "zbytek", "NOUN", [86, 92]], ["krve", "krev", "NOUN", [93, 97]], ["po", "po", "ADP", [98, 100]], ["porodu", "porod", "NOUN", [101, 107]], [".", ".", "PUNCT", [107, 108]]]], ["calgarske-listy_2003_unor_ocr.txt", "Hol\u010di\u010dce se u\u017e zav\u00edrala o\u010di\u010dka a ne\u017e ji znovu 6  obl\u00e9kli, spokojen\u011b spala.", [["Hol\u010di\u010dce", "hol\u010di\u010dka", "NOUN", [0, 8]], ["se", "se", "PRON", [9, 11]], ["u\u017e", "u\u017e", "ADV", [12, 14]], ["zav\u00edrala", "zav\u00edrat", "VERB", [15, 23]], ["o\u010di\u010dka", "o\u010di\u010dka", "NOUN", [24, 30]], ["a", "a", "CCONJ", [31, 32]], ["ne\u017e", "ne\u017e", "SCONJ", [33, 36]], ["ji", "on", "PRON", [37, 39]], ["znovu", "znovu", "ADV", [40, 45]], ["6", "6", "NUM", [46, 47]], ["obl\u00e9kli", "obl\u00e9knout", "VERB", [49, 56]], [",", ",", "PUNCT", [56, 57]], ["spokojen\u011b", "spokojen\u011b", "ADV", [58, 67]], ["spala", "sp\u00e1t", "VERB", [68, 73]], [".", ".", "PUNCT", [73, 74]]]], ["calgarske-listy_2003_unor_ocr.txt", "S \u00fa\u017easem se d\u00edvali na nenad\u00e1l\u00fd v\u00e1no\u010dn\u00ed d\u00e1rek.", [["S", "s", "ADP", [0, 1]], ["\u00fa\u017easem", "\u00fa\u017eas", "NOUN", [2, 8]], ["se", "se", "PRON", [9, 11]], ["d\u00edvali", "d\u00edvat", "VERB", [12, 18]], ["na", "na", "ADP", [19, 21]], ["nenad\u00e1l\u00fd", "nad\u00e1l\u00fd", "ADJ", [22, 30]], ["v\u00e1no\u010dn\u00ed", "v\u00e1no\u010dn\u00ed", "ADJ", [31, 38]], ["d\u00e1rek", "d\u00e1rek", "NOUN", [39, 44]], [".", ".", "PUNCT", [44, 45]]]], ["calgarske-listy_2003_unor_ocr.txt", "Johny za\u010dal zp\u00edvat rozechv\u011bl\u00fdm hlasem.......\"tich\u00e1 noc,sv\u00e1t\u00e1 noc\".", [["Johny", "Johny", "PROPN", [0, 5]], ["za\u010dal", "za\u010d\u00edt", "VERB", [6, 11]], ["zp\u00edvat", "zp\u00edvat", "VERB", [12, 18]], ["rozechv\u011bl\u00fdm", "rozechv\u011bl\u00fd", "ADJ", [19, 30]], ["hlasem", "hlas", "NOUN", [31, 37]], [".", ".", "PUNCT", [37, 38]], [".", ".", "PUNCT", [38, 39]], [".", ".", "PUNCT", [39, 40]], [".", ".", "PUNCT", [40, 41]], [".", ".", "PUNCT", [41, 42]], [".", ".", "PUNCT", [42, 43]], [".", ".", "PUNCT", [43, 44]], ["\"", "\"", "PUNCT", [44, 45]], ["tich\u00e1", "tich\u00fd", "ADJ", [45, 50]], ["noc", "noc", "NOUN", [51, 54]], [",", ",", "PUNCT", [54, 55]], ["sv\u00e1t\u00e1", "sv\u00e1tat", "VERB", [55, 60]], ["noc", "noc", "NOUN", [61, 64]], ["\"", "\"", "PUNCT", [64, 65]], [".", ".", "PUNCT", [65, 66]]]], ["calgarske-listy_2003_unor_ocr.txt", "Bill a Dave se k n\u011bmu p\u0159idali a z d\u00e1lky je doprov\u00e1zelo t\u00e1hl\u00e9 vyt\u00ed vl\u010d\u00ed sme\u010dky.", [["Bill", "Bill", "PROPN", [0, 4]], ["a", "a", "CCONJ", [5, 6]], ["Dave", "Dave", "PROPN", [7, 11]], ["se", "se", "PRON", [12, 14]], ["k", "k", "ADP", [15, 16]], ["n\u011bmu", "on", "PRON", [17, 21]], ["p\u0159idali", "p\u0159idat", "VERB", [22, 29]], ["a", "a", "CCONJ", [30, 31]], ["z", "z", "ADP", [32, 33]], ["d\u00e1lky", "d\u00e1lka", "NOUN", [34, 39]], ["je", "on", "PRON", [40, 42]], ["doprov\u00e1zelo", "doprov\u00e1zet", "VERB", [43, 54]], ["t\u00e1hl\u00e9", "t\u00e1hl\u00fd", "ADJ", [55, 60]], ["vyt\u00ed", "vyt\u00ed", "NOUN", [61, 65]], ["vl\u010d\u00ed", "vl\u010d\u00ed", "ADJ", [66, 70]], ["sme\u010dky", "sme\u010dka", "NOUN", [71, 77]], [".", ".", "PUNCT", [77, 78]]]], ["calgarske-listy_2003_unor_ocr.txt", "Hol\u010di\u010dka se stala st\u0159edem pozornosti na Eldor\u00e1du, mil\u00e1\u010dkem v\u0161ech zlatokop\u016f.", [["Hol\u010di\u010dka", "hol\u010di\u010dka", "NOUN", [0, 8]], ["se", "se", "PRON", [9, 11]], ["stala", "st\u00e1t", "VERB", [12, 17]], ["st\u0159edem", "st\u0159ed", "NOUN", [18, 25]], ["pozornosti", "pozornost", "NOUN", [26, 36]], ["na", "na", "ADP", [37, 39]], ["Eldor\u00e1du", "Eldor\u00e1d", "PROPN", [40, 48]], [",", ",", "PUNCT", [48, 49]], ["mil\u00e1\u010dkem", "mil\u00e1\u010dek", "NOUN", [50, 58]], ["v\u0161ech", "v\u0161echen", "DET", [59, 64]], ["zlatokop\u016f", "zlatokop", "NOUN", [65, 74]], [".", ".", "PUNCT", [74, 75]]]], ["calgarske-listy_2003_unor_ocr.txt", "Pok\u0159tili ji na ja\u0159e jm\u00e9nem Edna Eldorado.", [["Pok\u0159tili", "pok\u0159t\u00edt", "VERB", [0, 8]], ["ji", "on", "PRON", [9, 11]], ["na", "na", "ADP", [12, 14]], ["ja\u0159e", "jaro", "NOUN", [15, 19]], ["jm\u00e9nem", "jm\u00e9no", "NOUN", [20, 26]], ["Edna", "Edna", "PROPN", [27, 31]], ["Eldorado", "Eldorado", "PROPN", [32, 40]], [".", ".", "PUNCT", [40, 41]]]], ["calgarske-listy_2003_unor_ocr.txt", "K\u0159est se odehr\u00e1val venku a hol\u010di\u010dka kolem sebe m\u011bla hromadu nuget\u016f a pytl\u00edk\u016f se zlat\u00fdm prachem, dary od n\u011bkolika des\u00edtek kmotr\u016f.", [["K\u0159est", "k\u0159est", "NOUN", [0, 5]], ["se", "se", "PRON", [6, 8]], ["odehr\u00e1val", "odehr\u00e1vat", "VERB", [9, 18]], ["venku", "venku", "ADV", [19, 24]], ["a", "a", "CCONJ", [25, 26]], ["hol\u010di\u010dka", "hol\u010di\u010dka", "NOUN", [27, 35]], ["kolem", "kolem", "ADP", [36, 41]], ["sebe", "se", "PRON", [42, 46]], ["m\u011bla", "m\u00edt", "VERB", [47, 51]], ["hromadu", "hromada", "NOUN", [52, 59]], ["nuget\u016f", "nuget", "NOUN", [60, 66]], ["a", "a", "CCONJ", [67, 68]], ["pytl\u00edk\u016f", "pytl\u00edk", "NOUN", [69, 76]], ["se", "s", "ADP", [77, 79]], ["zlat\u00fdm", "zlat\u00fd", "ADJ", [80, 86]], ["prachem", "prach", "NOUN", [87, 94]], [",", ",", "PUNCT", [94, 95]], ["dary", "dar", "NOUN", [96, 100]], ["od", "od", "ADP", [101, 103]], ["n\u011bkolika", "n\u011bkolik", "DET", [104, 112]], ["des\u00edtek", "des\u00edtka", "NOUN", [113, 120]], ["kmotr\u016f", "kmotr", "NOUN", [121, 127]], [".", ".", "PUNCT", [127, 128]]]], ["calgarske-listy_2003_unor_ocr.txt", "I ti nejtvrd\u0161\u00ed mu\u017ei severu ten den plakali dojet\u00edm.", [["I", "i", "CCONJ", [0, 1]], ["ti", "ten", "DET", [2, 4]], ["nejtvrd\u0161\u00ed", "tvrd\u00fd", "ADJ", [5, 14]], ["mu\u017ei", "mu\u017e", "NOUN", [15, 19]], ["severu", "sever", "NOUN", [20, 26]], ["ten", "ten", "DET", [27, 30]], ["den", "den", "NOUN", [31, 34]], ["plakali", "plakat", "VERB", [35, 42]], ["dojet\u00edm", "dojet\u00ed", "NOUN", [43, 50]], [".", ".", "PUNCT", [50, 51]]]], ["calgarske-listy_2003_unor_ocr.txt", "Nemoc \u0161\u00edlen\u00fdch krav - hlasatel v televizn\u00edch novin\u00e1ch: V\u00e1\u017een\u00ed poslucha\u010di, m\u00e1m dv\u011b zpr\u00e1vy.", [["Nemoc", "nemoc", "NOUN", [0, 5]], ["\u0161\u00edlen\u00fdch", "\u0161\u00edlen\u00fd", "ADJ", [6, 14]], ["krav", "kr\u00e1va", "NOUN", [15, 19]], ["-", "-", "PUNCT", [20, 21]], ["hlasatel", "hlasatel", "NOUN", [22, 30]], ["v", "v", "ADP", [31, 32]], ["televizn\u00edch", "televizn\u00ed", "ADJ", [33, 44]], ["novin\u00e1ch", "noviny", "NOUN", [45, 53]], [":", ":", "PUNCT", [53, 54]], ["V\u00e1\u017een\u00ed", "v\u00e1\u017een\u00fd", "ADJ", [55, 61]], ["poslucha\u010di", "poslucha\u010d", "NOUN", [62, 72]], [",", ",", "PUNCT", [72, 73]], ["m\u00e1m", "m\u00edt", "VERB", [74, 77]], ["dv\u011b", "dva", "NUM", [78, 81]], ["zpr\u00e1vy", "zpr\u00e1va", "NOUN", [82, 88]], [".", ".", "PUNCT", [88, 89]]]], ["calgarske-listy_2003_unor_ocr.txt", "Jednu dobrou a jednu \u0161patnou.", [["Jednu", "jeden", "NUM", [0, 5]], ["dobrou", "dobr\u00fd", "ADJ", [6, 12]], ["a", "a", "CCONJ", [13, 14]], ["jednu", "jeden", "NUM", [15, 20]], ["\u0161patnou", "\u0161patn\u00fd", "ADJ", [21, 28]], [".", ".", "PUNCT", [28, 29]]]], ["calgarske-listy_2003_unor_ocr.txt", "Ta \u0161patn\u00e1 je, \u017ee dva poslanci parlamentu onemocn\u011bli nemoc\u00ed \u0161\u00edlen\u00fdch krav.", [["Ta", "ten", "DET", [0, 2]], ["\u0161patn\u00e1", "\u0161patn\u00fd", "ADJ", [3, 9]], ["je", "b\u00fdt", "AUX", [10, 12]], [",", ",", "PUNCT", [12, 13]], ["\u017ee", "\u017ee", "SCONJ", [14, 16]], ["dva", "dva", "NUM", [17, 20]], ["poslanci", "poslanec", "NOUN", [21, 29]], ["parlamentu", "parlament", "NOUN", [30, 40]], ["onemocn\u011bli", "onemocn\u011bt", "VERB", [41, 51]], ["nemoc\u00ed", "nemoc", "NOUN", [52, 58]], ["\u0161\u00edlen\u00fdch", "\u0161\u00edlen\u00fd", "ADJ", [59, 67]], ["krav", "kr\u00e1va", "NOUN", [68, 72]], [".", ".", "PUNCT", [72, 73]]]], ["calgarske-listy_2003_unor_ocr.txt", "Ta dobr\u00e1 je, \u017ee bude muset b\u00fdt utraceno cel\u00e9 st\u00e1do!\"", [["Ta", "ten", "DET", [0, 2]], ["dobr\u00e1", "dobr\u00fd", "ADJ", [3, 8]], ["je", "b\u00fdt", "AUX", [9, 11]], [",", ",", "PUNCT", [11, 12]], ["\u017ee", "\u017ee", "SCONJ", [13, 15]], ["bude", "b\u00fdt", "AUX", [16, 20]], ["muset", "muset", "VERB", [21, 26]], ["b\u00fdt", "b\u00fdt", "AUX", [27, 30]], ["utraceno", "utracen\u00fd", "ADJ", [31, 39]], ["cel\u00e9", "cel\u00fd", "ADJ", [40, 44]], ["st\u00e1do", "st\u00e1do", "NOUN", [45, 50]], ["!", "!", "PUNCT", [50, 51]], ["\"", "\"", "PUNCT", [51, 52]]]], ["calgarske-listy_2003_unor_ocr.txt", "T\u00ddDEN POD PSA : od Jardy Pl\u0161ka z Austr\u00e1lie.", [["T\u00ddDEN", "t\u00fdden", "NOUN", [0, 5]], ["POD", "pod", "ADP", [6, 9]], ["PSA", "PSA", "NOUN", [10, 13]], [":", ":", "PUNCT", [14, 15]], ["od", "od", "ADP", [16, 18]], ["Jardy", "Jarda", "PROPN", [19, 24]], ["Pl\u0161ka", "Pl\u0161ek", "PROPN", [25, 30]], ["z", "z", "ADP", [31, 32]], ["Austr\u00e1lie", "Austr\u00e1lie", "PROPN", [33, 42]], [".", ".", "PUNCT", [42, 43]]]], ["calgarske-listy_2003_unor_ocr.txt", "prest@hunterli nk. net. au Pond\u011bl\u00ed 16.12.2002 -", [["prest@hunterli", "prest@hunterlerl", "NOUN", [0, 14]], ["nk", "nk", "NOUN", [15, 17]], [".", ".", "PUNCT", [17, 18]], ["net", "net", "NOUN", [19, 22]], [".", ".", "PUNCT", [22, 23]], ["au", "au", "X", [24, 26]], ["Pond\u011bl\u00ed", "pond\u011bl\u00ed", "NOUN", [27, 34]], ["16.12.2002", "16.12.2002", "NUM", [35, 45]], ["-", "-", "PUNCT", [46, 47]]]], ["calgarske-listy_2003_unor_ocr.txt", "Co se semlelo, umlelo a podemlelo ...", [["Co", "co", "PRON", [0, 2]], ["se", "se", "PRON", [3, 5]], ["semlelo", "semlet", "VERB", [6, 13]], [",", ",", "PUNCT", [13, 14]], ["umlelo", "umlet", "VERB", [15, 21]], ["a", "a", "CCONJ", [22, 23]], ["podemlelo", "podemlet", "VERB", [24, 33]], [".", ".", "PUNCT", [34, 35]], [".", ".", "PUNCT", [35, 36]], [".", ".", "PUNCT", [36, 37]]]], ["calgarske-listy_2003_unor_ocr.txt", "Politick\u00e9 ud\u00e1losti minul\u00e9ho t\u00fddne, vzh\u016fru nohama a v k\u0159iv\u00e9m zrcadle - vid\u011bno a sarkasticky komentov\u00e1no z Austr\u00e1lie.", [["Politick\u00e9", "politick\u00fd", "ADJ", [0, 9]], ["ud\u00e1losti", "ud\u00e1lost", "NOUN", [10, 18]], ["minul\u00e9ho", "minul\u00fd", "ADJ", [19, 27]], ["t\u00fddne", "t\u00fdden", "NOUN", [28, 33]], [",", ",", "PUNCT", [33, 34]], ["vzh\u016fru", "vzh\u016fru", "ADV", [35, 41]], ["nohama", "noha", "NOUN", [42, 48]], ["a", "a", "CCONJ", [49, 50]], ["v", "v", "ADP", [51, 52]], ["k\u0159iv\u00e9m", "k\u0159iv\u00fd", "ADJ", [53, 59]], ["zrcadle", "zrcadlo", "NOUN", [60, 67]], ["-", "-", "PUNCT", [68, 69]], ["vid\u011bno", "vid\u011bn\u00fd", "ADJ", [70, 76]], ["a", "a", "CCONJ", [77, 78]], ["sarkasticky", "sarkasticky", "ADV", [79, 90]], ["komentov\u00e1no", "komentovan\u00fd", "ADJ", [91, 102]], ["z", "z", "ADP", [103, 104]], ["Austr\u00e1lie", "Austr\u00e1lie", "PROPN", [105, 114]], [".", ".", "PUNCT", [114, 115]]]], ["calgarske-listy_2003_unor_ocr.txt", "POND\u011aL\u00cd - 9.12.2002.", [["POND\u011aL\u00cd", "pond\u011bl\u00ed", "NOUN", [0, 7]], ["-", "-", "PUNCT", [8, 9]], ["9.12.2002", "9.12.2002", "NUM", [10, 19]], [".", ".", "PUNCT", [19, 20]]]], ["calgarske-listy_2003_unor_ocr.txt", "Izraelsk\u00fd tisk zve\u0159ejnil informace, podle nich\u017e by izrael\u0161t\u00ed turist\u00e9 v Praze mohli b\u00fdt ter\u010dem \u00fatoku muslimsk\u00fdch fanatik\u016f.", [["Izraelsk\u00fd", "izraelsk\u00fd", "ADJ", [0, 9]], ["tisk", "tisk", "NOUN", [10, 14]], ["zve\u0159ejnil", "zve\u0159ejnit", "VERB", [15, 24]], ["informace", "informace", "NOUN", [25, 34]], [",", ",", "PUNCT", [34, 35]], ["podle", "podle", "ADP", [36, 41]], ["nich\u017e", "jen\u017e", "PRON", [42, 47]], ["by", "b\u00fdt", "AUX", [48, 50]], ["izrael\u0161t\u00ed", "izraelsk\u00fd", "ADJ", [51, 60]], ["turist\u00e9", "turista", "NOUN", [61, 68]], ["v", "v", "ADP", [69, 70]], ["Praze", "Praha", "PROPN", [71, 76]], ["mohli", "moci", "VERB", [77, 82]], ["b\u00fdt", "b\u00fdt", "AUX", [83, 86]], ["ter\u010dem", "ter\u010d", "NOUN", [87, 93]], ["\u00fatoku", "\u00fatok", "NOUN", [94, 99]], ["muslimsk\u00fdch", "muslimsk\u00fd", "ADJ", [100, 111]], ["fanatik\u016f", "fanatik", "NOUN", [112, 120]], [".", ".", "PUNCT", [120, 121]]]], ["calgarske-listy_2003_unor_ocr.txt", "Cena, za kterou izraelsk\u00fd tisk nab\u00eddl tyto informace organizaci Al Qaida, zve\u0159ejn\u011bna v nebyla.", [["Cena", "cena", "NOUN", [0, 4]], [",", ",", "PUNCT", [4, 5]], ["za", "za", "ADP", [6, 8]], ["kterou", "kter\u00fd", "DET", [9, 15]], ["izraelsk\u00fd", "izraelsk\u00fd", "ADJ", [16, 25]], ["tisk", "tisk", "NOUN", [26, 30]], ["nab\u00eddl", "nab\u00eddnout", "VERB", [31, 37]], ["tyto", "tento", "DET", [38, 42]], ["informace", "informace", "NOUN", [43, 52]], ["organizaci", "organizace", "NOUN", [53, 63]], ["Al", "Al", "X", [64, 66]], ["Qaida", "Qaida", "X", [67, 72]], [",", ",", "PUNCT", [72, 73]], ["zve\u0159ejn\u011bna", "zve\u0159ejn\u011bn\u00fd", "ADJ", [74, 84]], ["v", "v", "ADP", [85, 86]], ["nebyla", "b\u00fdt", "AUX", [87, 93]], [".", ".", "PUNCT", [93, 94]]]], ["calgarske-listy_2003_unor_ocr.txt", "\u010cesk\u00e9 bezpe\u010dnostn\u00ed slo\u017eky nepotvrdily tyto izraelsk\u00e9 informace s odvol\u00e1n\u00edm na partnersk\u00e9 tajn\u00e9 slu\u017eby.", [["\u010cesk\u00e9", "\u010desk\u00fd", "ADJ", [0, 5]], ["bezpe\u010dnostn\u00ed", "bezpe\u010dnostn\u00ed", "ADJ", [6, 18]], ["slo\u017eky", "slo\u017eka", "NOUN", [19, 25]], ["nepotvrdily", "potvrdit", "VERB", [26, 37]], ["tyto", "tento", "DET", [38, 42]], ["izraelsk\u00e9", "izraelsk\u00fd", "ADJ", [43, 52]], ["informace", "informace", "NOUN", [53, 62]], ["s", "s", "ADP", [63, 64]], ["odvol\u00e1n\u00edm", "odvol\u00e1n\u00ed", "NOUN", [65, 74]], ["na", "na", "ADP", [75, 77]], ["partnersk\u00e9", "partnersk\u00fd", "ADJ", [78, 88]], ["tajn\u00e9", "tajn\u00fd", "ADJ", [89, 94]], ["slu\u017eby", "slu\u017eba", "NOUN", [95, 101]], [".", ".", "PUNCT", [101, 102]]]], ["calgarske-listy_2003_unor_ocr.txt", "Podle nich, raketometn\u00e1 zbra\u0148, nalezen\u00e1 v bl\u00edzkosti pra\u017esk\u00e9ho leti\u0161t\u011b, byla houfnice.", [["Podle", "podle", "ADP", [0, 5]], ["nich", "on", "PRON", [6, 10]], [",", ",", "PUNCT", [10, 11]], ["raketometn\u00e1", "raketometn\u00fd", "ADJ", [12, 23]], ["zbra\u0148", "zbra\u0148", "NOUN", [24, 29]], [",", ",", "PUNCT", [29, 30]], ["nalezen\u00e1", "nalezen\u00fd", "ADJ", [31, 39]], ["v", "v", "ADP", [40, 41]], ["bl\u00edzkosti", "bl\u00edzkost", "NOUN", [42, 51]], ["pra\u017esk\u00e9ho", "pra\u017esk\u00fd", "ADJ", [52, 61]], ["leti\u0161t\u011b", "leti\u0161t\u011b", "NOUN", [62, 69]], [",", ",", "PUNCT", [69, 70]], ["byla", "b\u00fdt", "AUX", [71, 75]], ["houfnice", "houfnice", "NOUN", [76, 84]], [".", ".", "PUNCT", [84, 85]]]], ["calgarske-listy_2003_unor_ocr.txt", "\u0158\u00edk\u00e1 se j\u00ed tak proto, \u017ee je ur\u010dena k pla\u0161en\u00ed pta\u010d\u00edch houfu, a ne k sest\u0159elov\u00e1n\u00ed izraelsk\u00fdch dopravn\u00edch letadel.", [["\u0158\u00edk\u00e1", "\u0159\u00edkat", "VERB", [0, 4]], ["se", "se", "PRON", [5, 7]], ["j\u00ed", "on", "PRON", [8, 10]], ["tak", "tak", "ADV", [11, 14]], ["proto", "proto", "ADV", [15, 20]], [",", ",", "PUNCT", [20, 21]], ["\u017ee", "\u017ee", "SCONJ", [22, 24]], ["je", "b\u00fdt", "AUX", [25, 27]], ["ur\u010dena", "ur\u010den\u00fd", "ADJ", [28, 34]], ["k", "k", "ADP", [35, 36]], ["pla\u0161en\u00ed", "pla\u0161en\u00ed", "NOUN", [37, 44]], ["pta\u010d\u00edch", "pta\u010d\u00ed", "ADJ", [45, 52]], ["houfu", "houf", "NOUN", [53, 58]], [",", ",", "PUNCT", [58, 59]], ["a", "a", "CCONJ", [60, 61]], ["ne", "ne", "PART", [62, 64]], ["k", "k", "ADP", [65, 66]], ["sest\u0159elov\u00e1n\u00ed", "sest\u0159elov\u00e1n\u00ed", "NOUN", [67, 79]], ["izraelsk\u00fdch", "izraelsk\u00fd", "ADJ", [80, 91]], ["dopravn\u00edch", "dopravn\u00ed", "ADJ", [92, 102]], ["letadel", "letadlo", "NOUN", [103, 110]], [".", ".", "PUNCT", [110, 111]]]], ["calgarske-listy_2003_unor_ocr.txt", "160 tis\u00edc turist\u016f z Izraele nav\u0161t\u00edvilo b\u011bhem uplynul\u00e9ho roku Prahu, jeden turista pr\u016fm\u011brn\u011b utrat\u00ed 86 dolar\u016f za den, pr\u016fm\u011br pobytu \u010dty\u0159i dny.", [["160", "160", "NUM", [0, 3]], ["tis\u00edc", "tis\u00edc", "NUM", [4, 9]], ["turist\u016f", "turista", "NOUN", [10, 17]], ["z", "z", "ADP", [18, 19]], ["Izraele", "Izrael", "PROPN", [20, 27]], ["nav\u0161t\u00edvilo", "nav\u0161t\u00edvit", "VERB", [28, 38]], ["b\u011bhem", "b\u011bhem", "ADP", [39, 44]], ["uplynul\u00e9ho", "uplynul\u00fd", "ADJ", [45, 55]], ["roku", "rok", "NOUN", [56, 60]], ["Prahu", "Praha", "PROPN", [61, 66]], [",", ",", "PUNCT", [66, 67]], ["jeden", "jeden", "NUM", [68, 73]], ["turista", "turista", "NOUN", [74, 81]], ["pr\u016fm\u011brn\u011b", "pr\u016fm\u011brn\u011b", "ADV", [82, 90]], ["utrat\u00ed", "utratit", "VERB", [91, 97]], ["86", "86", "NUM", [98, 100]], ["dolar\u016f", "dolar", "NOUN", [101, 107]], ["za", "za", "ADP", [108, 110]], ["den", "den", "NOUN", [111, 114]], [",", ",", "PUNCT", [114, 115]], ["pr\u016fm\u011br", "pr\u016fm\u011br", "NOUN", [116, 122]], ["pobytu", "pobyt", "NOUN", [123, 129]], ["\u010dty\u0159i", "\u010dty\u0159i", "NUM", [130, 135]], ["dny", "den", "NOUN", [136, 139]], [".", ".", "PUNCT", [139, 140]]]], ["calgarske-listy_2003_unor_ocr.txt", "Sv\u00e1 vyd\u00e1n\u00ed hradili izrael\u0161t\u00ed turist\u00e9 prodejem k\u0159es\u0165ansk\u00fdch relikvi\u00ed, kter\u00e9 si za t\u00edm \u00fa\u010delem s sebou p\u0159ivezli.", [["Sv\u00e1", "sv\u016fj", "DET", [0, 3]], ["vyd\u00e1n\u00ed", "vyd\u00e1n\u00ed", "NOUN", [4, 10]], ["hradili", "hradit", "VERB", [11, 18]], ["izrael\u0161t\u00ed", "izraelsk\u00fd", "ADJ", [19, 28]], ["turist\u00e9", "turista", "NOUN", [29, 36]], ["prodejem", "prodej", "NOUN", [37, 45]], ["k\u0159es\u0165ansk\u00fdch", "k\u0159es\u0165ansk\u00fd", "ADJ", [46, 58]], ["relikvi\u00ed", "relikvie", "NOUN", [59, 67]], [",", ",", "PUNCT", [67, 68]], ["kter\u00e9", "kter\u00fd", "DET", [69, 74]], ["si", "se", "PRON", [75, 77]], ["za", "za", "ADP", [78, 80]], ["t\u00edm", "ten", "DET", [81, 84]], ["\u00fa\u010delem", "\u00fa\u010del", "NOUN", [85, 91]], ["s", "s", "ADP", [92, 93]], ["sebou", "se", "PRON", [94, 99]], ["p\u0159ivezli", "p\u0159iv\u00e9zt", "VERB", [100, 108]], [".", ".", "PUNCT", [108, 109]]]], ["calgarske-listy_2003_unor_ocr.txt", "Jen za lo\u0148sk\u00fd rok tak prodali 1200 trnov\u00fdch korun, 3600 Je\u017e\u00ed\u0161kov\u00fdch pl\u00ednek a 38 kubick\u00fdch metr\u016f sv\u00e1t\u00e9ho k\u0159\u00ed\u017ee.", [["Jen", "jen", "PART", [0, 3]], ["za", "za", "ADP", [4, 6]], ["lo\u0148sk\u00fd", "lo\u0148sk\u00fd", "ADJ", [7, 13]], ["rok", "rok", "NOUN", [14, 17]], ["tak", "tak", "ADV", [18, 21]], ["prodali", "prodat", "VERB", [22, 29]], ["1200", "1200", "NUM", [30, 34]], ["trnov\u00fdch", "trnov\u00fd", "ADJ", [35, 43]], ["korun", "koruna", "NOUN", [44, 49]], [",", ",", "PUNCT", [49, 50]], ["3600", "3600", "NUM", [51, 55]], ["Je\u017e\u00ed\u0161kov\u00fdch", "Je\u017e\u00ed\u0161k\u016fv", "ADJ", [56, 67]], ["pl\u00ednek", "pl\u00ednka", "NOUN", [68, 74]], ["a", "a", "CCONJ", [75, 76]], ["38", "38", "NUM", [77, 79]], ["kubick\u00fdch", "kubick\u00fd", "ADJ", [80, 89]], ["metr\u016f", "metr", "NOUN", [90, 95]], ["sv\u00e1t\u00e9ho", "sv\u00e1t\u00fd", "ADJ", [96, 103]], ["k\u0159\u00ed\u017ee", "k\u0159\u00ed\u017e", "NOUN", [104, 109]], [".", ".", "PUNCT", [109, 110]]]], ["calgarske-listy_2003_unor_ocr.txt", "V\u00fdkonn\u00fd v\u00fdbor soci\u00e1ln\u00ed demokracie potvrdil v sobotu Jaroslava Bure\u0161e jako kandid\u00e1ta na prezidentsk\u00fd \u00fa\u0159ad.", [["V\u00fdkonn\u00fd", "v\u00fdkonn\u00fd", "ADJ", [0, 7]], ["v\u00fdbor", "v\u00fdbor", "NOUN", [8, 13]], ["soci\u00e1ln\u00ed", "soci\u00e1ln\u00ed", "ADJ", [14, 22]], ["demokracie", "demokracie", "NOUN", [23, 33]], ["potvrdil", "potvrdit", "VERB", [34, 42]], ["v", "v", "ADP", [43, 44]], ["sobotu", "sobota", "NOUN", [45, 51]], ["Jaroslava", "Jaroslav", "PROPN", [52, 61]], ["Bure\u0161e", "Bure\u0161", "PROPN", [62, 68]], ["jako", "jako", "SCONJ", [69, 73]], ["kandid\u00e1ta", "kandid\u00e1t", "NOUN", [74, 83]], ["na", "na", "ADP", [84, 86]], ["prezidentsk\u00fd", "prezidentsk\u00fd", "ADJ", [87, 99]], ["\u00fa\u0159ad", "\u00fa\u0159ad", "NOUN", [100, 104]], [".", ".", "PUNCT", [104, 105]]]], ["calgarske-listy_2003_unor_ocr.txt", "Tisk\u00e1rny to ani na okam\u017eik nevyvedlo z m\u00edry a pokra\u010duj\u00ed ve v\u00fdrob\u011b z\u00e1sob fotografi\u00ed Milo\u0161e Zemana a V\u00e1clava Klause, aby hned po volb\u00e1ch jeden z nich mohl viset na m\u00edstech k tomu ur\u010den\u00fdch.", [["Tisk\u00e1rny", "tisk\u00e1rna", "NOUN", [0, 8]], ["to", "ten", "DET", [9, 11]], ["ani", "ani", "CCONJ", [12, 15]], ["na", "na", "ADP", [16, 18]], ["okam\u017eik", "okam\u017eik", "NOUN", [19, 26]], ["nevyvedlo", "vyv\u00e9st", "VERB", [27, 36]], ["z", "z", "ADP", [37, 38]], ["m\u00edry", "m\u00edra", "NOUN", [39, 43]], ["a", "a", "CCONJ", [44, 45]], ["pokra\u010duj\u00ed", "pokra\u010dovat", "VERB", [46, 55]], ["ve", "v", "ADP", [56, 58]], ["v\u00fdrob\u011b", "v\u00fdroba", "NOUN", [59, 65]], ["z\u00e1sob", "z\u00e1soba", "NOUN", [66, 71]], ["fotografi\u00ed", "fotografie", "NOUN", [72, 82]], ["Milo\u0161e", "Milo\u0161", "PROPN", [83, 89]], ["Zemana", "Zeman", "PROPN", [90, 96]], ["a", "a", "CCONJ", [97, 98]], ["V\u00e1clava", "V\u00e1clav", "PROPN", [99, 106]], ["Klause", "Klaus", "PROPN", [107, 113]], [",", ",", "PUNCT", [113, 114]], ["aby", "aby", "SCONJ", [-27759, -27759]], ["by", "b\u00fdt", "AUX", [-27759, -27759]], ["hned", "hned", "ADV", [119, 123]], ["po", "po", "ADP", [124, 126]], ["volb\u00e1ch", "volba", "NOUN", [127, 134]], ["jeden", "jeden", "NUM", [135, 140]], ["z", "z", "ADP", [141, 142]], ["nich", "on", "PRON", [143, 147]], ["mohl", "moci", "VERB", [148, 152]], ["viset", "viset", "VERB", [153, 158]], ["na", "na", "ADP", [159, 161]], ["m\u00edstech", "m\u00edsto", "NOUN", [162, 169]], ["k", "k", "ADP", [170, 171]], ["tomu", "ten", "DET", [172, 176]], ["ur\u010den\u00fdch", "ur\u010den\u00fd", "ADJ", [177, 185]], [".", ".", "PUNCT", [185, 186]]]], ["calgarske-listy_2003_unor_ocr.txt", "Zdravotnick\u00e9 odbory v sobotu ozn\u00e1mily, \u017ee jsou p\u0159ipraveny j\u00edt do st\u00e1vky, pokud by m\u011bly pokra\u010dovat \u0161krty ve v\u00fddaj\u00edch na zdravotnictv\u00ed.", [["Zdravotnick\u00e9", "zdravotnick\u00fd", "ADJ", [0, 12]], ["odbory", "odbory", "NOUN", [13, 19]], ["v", "v", "ADP", [20, 21]], ["sobotu", "sobota", "NOUN", [22, 28]], ["ozn\u00e1mily", "ozn\u00e1mit", "VERB", [29, 37]], [",", ",", "PUNCT", [37, 38]], ["\u017ee", "\u017ee", "SCONJ", [39, 41]], ["jsou", "b\u00fdt", "AUX", [42, 46]], ["p\u0159ipraveny", "p\u0159ipraven\u00fd", "ADJ", [47, 57]], ["j\u00edt", "j\u00edt", "VERB", [58, 61]], ["do", "do", "ADP", [62, 64]], ["st\u00e1vky", "st\u00e1vka", "NOUN", [65, 71]], [",", ",", "PUNCT", [71, 72]], ["pokud", "pokud", "SCONJ", [73, 78]], ["by", "b\u00fdt", "AUX", [79, 81]], ["m\u011bly", "m\u00edt", "VERB", [82, 86]], ["pokra\u010dovat", "pokra\u010dovat", "VERB", [87, 97]], ["\u0161krty", "\u0161krt", "NOUN", [98, 103]], ["ve", "v", "ADP", [104, 106]], ["v\u00fddaj\u00edch", "v\u00fddaj", "NOUN", [107, 115]], ["na", "na", "ADP", [116, 118]], ["zdravotnictv\u00ed", "zdravotnictv\u00ed", "NOUN", [119, 132]], [".", ".", "PUNCT", [132, 133]]]], ["calgarske-listy_2003_unor_ocr.txt", "Do budoucna to vypad\u00e1, \u017ee si ministerstvo zdravotnictv\u00ed ani ne\u0161krtne.", [["Do", "do", "ADP", [0, 2]], ["budoucna", "budoucno", "NOUN", [3, 11]], ["to", "ten", "DET", [12, 14]], ["vypad\u00e1", "vypadat", "VERB", [15, 21]], [",", ",", "PUNCT", [21, 22]], ["\u017ee", "\u017ee", "SCONJ", [23, 25]], ["si", "se", "PRON", [26, 28]], ["ministerstvo", "ministerstvo", "NOUN", [29, 41]], ["zdravotnictv\u00ed", "zdravotnictv\u00ed", "NOUN", [42, 55]], ["ani", "ani", "CCONJ", [56, 59]], ["ne\u0161krtne", "\u0161krtnout", "VERB", [60, 68]], [".", ".", "PUNCT", [68, 69]]]], ["calgarske-listy_2003_unor_ocr.txt", "Policist\u00e9 ud\u011blali dal\u0161\u00ed razii proti vietnamsk\u00fdm trhovc\u016fm, tentokr\u00e1t v ned\u011bli ve Vojtanov\u011b na Chebsku.", [["Policist\u00e9", "policista", "NOUN", [0, 9]], ["ud\u011blali", "ud\u011blat", "VERB", [10, 17]], ["dal\u0161\u00ed", "dal\u0161\u00ed", "ADJ", [18, 23]], ["razii", "razie", "NOUN", [24, 29]], ["proti", "proti", "ADP", [30, 35]], ["vietnamsk\u00fdm", "vietnamsk\u00fd", "ADJ", [36, 47]], ["trhovc\u016fm", "trhovec", "NOUN", [48, 56]], [",", ",", "PUNCT", [56, 57]], ["tentokr\u00e1t", "tentokr\u00e1t", "ADV", [58, 67]], ["v", "v", "ADP", [68, 69]], ["ned\u011bli", "ned\u011ble", "NOUN", [70, 76]], ["ve", "v", "ADP", [77, 79]], ["Vojtanov\u011b", "Vojtanov", "PROPN", [80, 89]], ["na", "na", "ADP", [90, 92]], ["Chebsku", "Chebsko", "PROPN", [93, 100]], [".", ".", "PUNCT", [100, 101]]]], ["calgarske-listy_2003_unor_ocr.txt", "Policejn\u00ed z\u00e1krok vyvolala nekal\u00e1 konkurence r\u00e1kosn\u00edk\u016f sv\u011btov\u00fdm zna\u010dk\u00e1m, jako je Adidas a Reebok.", [["Policejn\u00ed", "policejn\u00ed", "ADJ", [0, 9]], ["z\u00e1krok", "z\u00e1krok", "NOUN", [10, 16]], ["vyvolala", "vyvolat", "VERB", [17, 25]], ["nekal\u00e1", "kal\u00fd", "ADJ", [26, 32]], ["konkurence", "konkurence", "NOUN", [33, 43]], ["r\u00e1kosn\u00edk\u016f", "r\u00e1kosn\u00edk", "NOUN", [44, 53]], ["sv\u011btov\u00fdm", "sv\u011btov\u00fd", "ADJ", [54, 62]], ["zna\u010dk\u00e1m", "zna\u010dka", "NOUN", [63, 70]], [",", ",", "PUNCT", [70, 71]], ["jako", "jako", "SCONJ", [72, 76]], ["je", "b\u00fdt", "AUX", [77, 79]], ["Adidas", "Adidas", "PROPN", [80, 86]], ["a", "a", "CCONJ", [87, 88]], ["Reebok", "Reebok", "PROPN", [89, 95]], [".", ".", "PUNCT", [95, 96]]]], ["calgarske-listy_2003_unor_ocr.txt", "Uk\u00e1zalo se toti\u017e, \u017ee napodobeniny, kter\u00e9 trhovci prod\u00e1vaj\u00ed, jsou lep\u0161\u00ed ne\u017e origin\u00e1l.", [["Uk\u00e1zalo", "uk\u00e1zat", "VERB", [0, 7]], ["se", "se", "PRON", [8, 10]], ["toti\u017e", "toti\u017e", "CCONJ", [11, 16]], [",", ",", "PUNCT", [16, 17]], ["\u017ee", "\u017ee", "SCONJ", [18, 20]], ["napodobeniny", "napodobenina", "NOUN", [21, 33]], [",", ",", "PUNCT", [33, 34]], ["kter\u00e9", "kter\u00fd", "DET", [35, 40]], ["trhovci", "trhovec", "NOUN", [41, 48]], ["prod\u00e1vaj\u00ed", "prod\u00e1vat", "VERB", [49, 58]], [",", ",", "PUNCT", [58, 59]], ["jsou", "b\u00fdt", "AUX", [60, 64]], ["lep\u0161\u00ed", "lep\u0161\u00ed", "ADJ", [65, 70]], ["ne\u017e", "ne\u017e", "SCONJ", [71, 74]], ["origin\u00e1l", "origin\u00e1l", "NOUN", [75, 83]], [".", ".", "PUNCT", [83, 84]]]], ["calgarske-listy_2003_unor_ocr.txt", "7", [["7", "7", "NUM", [0, 1]]]], ["calgarske-listy_2003_unor_ocr.txt", "V Prost\u011bjov\u011b se vyskytl \u010dern\u00fd ka\u0161el, to je nemoc, kter\u00e1 se u\u017e des\u00edtky let v na\u0161\u00ed zemi neobjevila, ale kter\u00e1 je na seznamu nemoc\u00ed EU a bez kter\u00e9 by n\u00e1s tam asi mezi sebe nevzali.", [["V", "v", "ADP", [0, 1]], ["Prost\u011bjov\u011b", "Prost\u011bjov", "PROPN", [2, 12]], ["se", "se", "PRON", [13, 15]], ["vyskytl", "vyskytnout", "VERB", [16, 23]], ["\u010dern\u00fd", "\u010dern\u00fd", "ADJ", [24, 29]], ["ka\u0161el", "ka\u0161el", "NOUN", [30, 35]], [",", ",", "PUNCT", [35, 36]], ["to", "ten", "DET", [37, 39]], ["je", "b\u00fdt", "AUX", [40, 42]], ["nemoc", "nemoc", "NOUN", [43, 48]], [",", ",", "PUNCT", [48, 49]], ["kter\u00e1", "kter\u00fd", "DET", [50, 55]], ["se", "se", "PRON", [56, 58]], ["u\u017e", "u\u017e", "ADV", [59, 61]], ["des\u00edtky", "des\u00edtka", "NOUN", [62, 69]], ["let", "l\u00e9ta", "NOUN", [70, 73]], ["v", "v", "ADP", [74, 75]], ["na\u0161\u00ed", "n\u00e1\u0161", "DET", [76, 80]], ["zemi", "zem\u011b", "NOUN", [81, 85]], ["neobjevila", "objevit", "VERB", [86, 96]], [",", ",", "PUNCT", [96, 97]], ["ale", "ale", "CCONJ", [98, 101]], ["kter\u00e1", "kter\u00fd", "DET", [102, 107]], ["je", "b\u00fdt", "AUX", [108, 110]], ["na", "na", "ADP", [111, 113]], ["seznamu", "seznam", "NOUN", [114, 121]], ["nemoc\u00ed", "nemoc", "NOUN", [122, 128]], ["EU", "EU", "PROPN", [129, 131]], ["a", "a", "CCONJ", [132, 133]], ["bez", "bez", "ADP", [134, 137]], ["kter\u00e9", "kter\u00fd", "DET", [138, 143]], ["by", "b\u00fdt", "AUX", [144, 146]], ["n\u00e1s", "my", "PRON", [147, 150]], ["tam", "tam", "ADV", [151, 154]], ["asi", "asi", "PART", [155, 158]], ["mezi", "mezi", "ADP", [159, 163]], ["sebe", "se", "PRON", [164, 168]], ["nevzali", "vz\u00edt", "VERB", [169, 176]], [".", ".", "PUNCT", [176, 177]]]], ["calgarske-listy_2003_unor_ocr.txt", "Lupi\u010di s pistolemi a samopalem p\u0159epadli v ned\u011bli j\u00eddelnu KFC v Praze ve Zli\u010d\u00edn\u011b a donutili zam\u011bstnance vyzradit tajemstv\u00ed receptu, podle kter\u00e9ho za pomoci jeden\u00e1cti bylinek lze usma\u017eit kr\u00e1l\u00edka tak, \u017ee vypad\u00e1 jako sma\u017een\u00e9 ku\u0159e.", [["Lupi\u010di", "lupi\u010d", "NOUN", [0, 6]], ["s", "s", "ADP", [7, 8]], ["pistolemi", "pistole", "NOUN", [9, 18]], ["a", "a", "CCONJ", [19, 20]], ["samopalem", "samopal", "NOUN", [21, 30]], ["p\u0159epadli", "p\u0159epadnout", "VERB", [31, 39]], ["v", "v", "ADP", [40, 41]], ["ned\u011bli", "ned\u011ble", "NOUN", [42, 48]], ["j\u00eddelnu", "j\u00eddelna", "NOUN", [49, 56]], ["KFC", "KFC", "NOUN", [57, 60]], ["v", "v", "ADP", [61, 62]], ["Praze", "Praha", "PROPN", [63, 68]], ["ve", "v", "ADP", [69, 71]], ["Zli\u010d\u00edn\u011b", "Zli\u010d\u00edn", "PROPN", [72, 79]], ["a", "a", "CCONJ", [80, 81]], ["donutili", "donutit", "VERB", [82, 90]], ["zam\u011bstnance", "zam\u011bstnanec", "NOUN", [91, 102]], ["vyzradit", "vyzradit", "VERB", [103, 111]], ["tajemstv\u00ed", "tajemstv\u00ed", "NOUN", [112, 121]], ["receptu", "recept", "NOUN", [122, 129]], [",", ",", "PUNCT", [129, 130]], ["podle", "podle", "ADP", [131, 136]], ["kter\u00e9ho", "kter\u00fd", "DET", [137, 144]], ["za", "za", "ADP", [145, 147]], ["pomoci", "pomoc", "NOUN", [148, 154]], ["jeden\u00e1cti", "jeden\u00e1ct", "NUM", [155, 164]], ["bylinek", "bylinka", "NOUN", [165, 172]], ["lze", "lze", "VERB", [173, 176]], ["usma\u017eit", "usma\u017eit", "VERB", [177, 184]], ["kr\u00e1l\u00edka", "kr\u00e1l\u00edk", "NOUN", [185, 192]], ["tak", "tak", "ADV", [193, 196]], [",", ",", "PUNCT", [196, 197]], ["\u017ee", "\u017ee", "SCONJ", [198, 200]], ["vypad\u00e1", "vypadat", "VERB", [201, 207]], ["jako", "jako", "SCONJ", [208, 212]], ["sma\u017een\u00e9", "sma\u017een\u00fd", "ADJ", [213, 220]], ["ku\u0159e", "ku\u0159e", "NOUN", [221, 225]], [".", ".", "PUNCT", [225, 226]]]], ["calgarske-listy_2003_unor_ocr.txt", "\u00daTER\u00dd - 10.12.2002.", [["\u00daTER\u00dd", "\u00fater\u00fd", "NOUN", [0, 5]], ["-", "-", "PUNCT", [6, 7]], ["10.12.2002", "10.12.2002", "NUM", [8, 18]], [".", ".", "PUNCT", [18, 19]]]], ["calgarske-listy_2003_unor_ocr.txt", "Otakar Motejl odm\u00edt\u00e1 b\u00fdt protikandid\u00e1tem Jaroslava Bure\u0161e v prezidentsk\u00fdch volb\u00e1ch, jeliko\u017e se - dle sv\u00fdch slov - dal k disposici \u010cSSD a te\u010f si p\u0159ipad\u00e1 jak prodan\u00e1 nev\u011bsta.", [["Otakar", "Otakar", "PROPN", [0, 6]], ["Motejl", "Motejl", "PROPN", [7, 13]], ["odm\u00edt\u00e1", "odm\u00edtat", "VERB", [14, 20]], ["b\u00fdt", "b\u00fdt", "AUX", [21, 24]], ["protikandid\u00e1tem", "protikandid\u00e1t", "NOUN", [25, 40]], ["Jaroslava", "Jaroslav", "PROPN", [41, 50]], ["Bure\u0161e", "Bure\u0161", "PROPN", [51, 57]], ["v", "v", "ADP", [58, 59]], ["prezidentsk\u00fdch", "prezidentsk\u00fd", "ADJ", [60, 74]], ["volb\u00e1ch", "volba", "NOUN", [75, 82]], [",", ",", "PUNCT", [82, 83]], ["jeliko\u017e", "jeliko\u017e", "SCONJ", [84, 91]], ["se", "se", "PRON", [92, 94]], ["-", "-", "PUNCT", [95, 96]], ["dle", "dle", "ADP", [97, 100]], ["sv\u00fdch", "sv\u016fj", "DET", [101, 106]], ["slov", "slovo", "NOUN", [107, 111]], ["-", "-", "PUNCT", [112, 113]], ["dal", "d\u00e1t", "VERB", [114, 117]], ["k", "k", "ADP", [118, 119]], ["disposici", "disposice", "NOUN", [120, 129]], ["\u010cSSD", "\u010cSSD", "PROPN", [130, 134]], ["a", "a", "CCONJ", [135, 136]], ["te\u010f", "te\u010f", "ADV", [137, 140]], ["si", "se", "PRON", [141, 143]], ["p\u0159ipad\u00e1", "p\u0159ipadat", "VERB", [144, 151]], ["jak", "jak", "ADV", [152, 155]], ["prodan\u00e1", "prodan\u00fd", "ADJ", [156, 163]], ["nev\u011bsta", "nev\u011bsta", "NOUN", [164, 171]], [".", ".", "PUNCT", [171, 172]]]], ["calgarske-listy_2003_unor_ocr.txt", "Jen se nev\u00ed, kterou \u010d\u00e1st m\u00e1 pan Motejl na mysli.", [["Jen", "jen", "PART", [0, 3]], ["se", "se", "PRON", [4, 6]], ["nev\u00ed", "v\u011bd\u011bt", "VERB", [7, 11]], [",", ",", "PUNCT", [11, 12]], ["kterou", "kter\u00fd", "DET", [13, 19]], ["\u010d\u00e1st", "\u010d\u00e1st", "NOUN", [20, 24]], ["m\u00e1", "m\u00edt", "VERB", [25, 27]], ["pan", "pan", "NOUN", [28, 31]], ["Motejl", "Motejl", "PROPN", [32, 38]], ["na", "na", "ADP", [39, 41]], ["mysli", "mysl", "NOUN", [42, 47]], [".", ".", "PUNCT", [47, 48]]]], ["calgarske-listy_2003_unor_ocr.txt", "Na duet \"V\u011brn\u00e9 na\u0161e milov\u00e1n\u00ed\" to nevypad\u00e1, sp\u00ed\u0161 na \"Rozmysli si Ma\u0159enko rozmysli\".", [["Na", "na", "ADP", [0, 2]], ["duet", "duet", "NOUN", [3, 7]], ["\"", "\"", "PUNCT", [8, 9]], ["V\u011brn\u00e9", "v\u011brn\u00fd", "ADJ", [9, 14]], ["na\u0161e", "n\u00e1\u0161", "DET", [15, 19]], ["milov\u00e1n\u00ed", "milov\u00e1n\u00ed", "NOUN", [20, 28]], ["\"", "\"", "PUNCT", [28, 29]], ["to", "ten", "DET", [30, 32]], ["nevypad\u00e1", "vypadat", "VERB", [33, 41]], [",", ",", "PUNCT", [41, 42]], ["sp\u00ed\u0161", "sp\u00ed\u0161", "PART", [43, 47]], ["na", "na", "ADP", [48, 50]], ["\"", "\"", "PUNCT", [51, 52]], ["Rozmysli", "rozmyslit", "VERB", [52, 60]], ["si", "se", "PRON", [61, 63]], ["Ma\u0159enko", "Ma\u0159enko", "PROPN", [64, 71]], ["rozmysli", "rozmyslit", "VERB", [72, 80]], ["\"", "\"", "PUNCT", [80, 81]], [".", ".", "PUNCT", [81, 82]]]], ["calgarske-listy_2003_unor_ocr.txt", "Kuvajt nezaplat\u00ed pobyt 250 \u010desk\u00fdch voj\u00e1k\u016f z protichemick\u00e9 roty, dokud n\u011bkdo nezaplat\u00ed za ten ukraden\u00fd svetr.", [["Kuvajt", "Kuvajt", "PROPN", [0, 6]], ["nezaplat\u00ed", "zaplatit", "VERB", [7, 16]], ["pobyt", "pobyt", "NOUN", [17, 22]], ["250", "250", "NUM", [23, 26]], ["\u010desk\u00fdch", "\u010desk\u00fd", "ADJ", [27, 34]], ["voj\u00e1k\u016f", "voj\u00e1k", "NOUN", [35, 41]], ["z", "z", "ADP", [42, 43]], ["protichemick\u00e9", "protichemick\u00fd", "ADJ", [44, 57]], ["roty", "rota", "NOUN", [58, 62]], [",", ",", "PUNCT", [62, 63]], ["dokud", "dokud", "SCONJ", [64, 69]], ["n\u011bkdo", "n\u011bkdo", "PRON", [70, 75]], ["nezaplat\u00ed", "zaplatit", "VERB", [76, 85]], ["za", "za", "ADP", [86, 88]], ["ten", "ten", "DET", [89, 92]], ["ukraden\u00fd", "ukraden\u00fd", "ADJ", [93, 101]], ["svetr", "svetr", "NOUN", [102, 107]], [".", ".", "PUNCT", [107, 108]]]], ["calgarske-listy_2003_unor_ocr.txt", "\u010cesk\u00e1 republika nem\u00e1 na vydr\u017eov\u00e1n\u00ed chemick\u00e9 roty v Kuvajtu pen\u00edze.", [["\u010cesk\u00e1", "\u010desk\u00fd", "ADJ", [0, 5]], ["republika", "republika", "NOUN", [6, 15]], ["nem\u00e1", "m\u00edt", "VERB", [16, 20]], ["na", "na", "ADP", [21, 23]], ["vydr\u017eov\u00e1n\u00ed", "vydr\u017eov\u00e1n\u00ed", "NOUN", [24, 34]], ["chemick\u00e9", "chemick\u00fd", "ADJ", [35, 43]], ["roty", "rota", "NOUN", [44, 48]], ["v", "v", "ADP", [49, 50]], ["Kuvajtu", "Kuvajt", "PROPN", [51, 58]], ["pen\u00edze", "pen\u00edze", "NOUN", [59, 65]], [".", ".", "PUNCT", [65, 66]]]], ["calgarske-listy_2003_unor_ocr.txt", "Podle kuvajtsk\u00fdch zvyk\u016f mus\u00ed m\u00edt ka\u017ed\u00fd mu\u017e nejm\u00e9n\u011b t\u0159i hurisky, p\u011bti\u010dlenn\u00e9 slu\u017eebnictvo, deset velbloud\u016f a osobn\u00ed letadlo a to z \u017eoldu \u010desk\u00e9ho voj\u00e1ka jeden nepo\u0159\u00edd\u00ed.", [["Podle", "podle", "ADP", [0, 5]], ["kuvajtsk\u00fdch", "kuvajtsk\u00fd", "ADJ", [6, 17]], ["zvyk\u016f", "zvyk", "NOUN", [18, 23]], ["mus\u00ed", "muset", "VERB", [24, 28]], ["m\u00edt", "m\u00edt", "VERB", [29, 32]], ["ka\u017ed\u00fd", "ka\u017ed\u00fd", "DET", [33, 38]], ["mu\u017e", "mu\u017e", "NOUN", [39, 42]], ["nejm\u00e9n\u011b", "m\u00e9n\u011b", "ADV", [43, 50]], ["t\u0159i", "t\u0159i", "NUM", [51, 54]], ["hurisky", "huriska", "NOUN", [55, 62]], [",", ",", "PUNCT", [62, 63]], ["p\u011bti\u010dlenn\u00e9", "p\u011bti\u010dlenn\u00fd", "ADJ", [64, 74]], ["slu\u017eebnictvo", "slu\u017eebnictvo", "NOUN", [75, 87]], [",", ",", "PUNCT", [87, 88]], ["deset", "deset", "NUM", [89, 94]], ["velbloud\u016f", "velbloud", "NOUN", [95, 104]], ["a", "a", "CCONJ", [105, 106]], ["osobn\u00ed", "osobn\u00ed", "ADJ", [107, 113]], ["letadlo", "letadlo", "NOUN", [114, 121]], ["a", "a", "CCONJ", [122, 123]], ["to", "to", "PART", [124, 126]], ["z", "z", "ADP", [127, 128]], ["\u017eoldu", "\u017eold", "NOUN", [129, 134]], ["\u010desk\u00e9ho", "\u010desk\u00fd", "ADJ", [135, 142]], ["voj\u00e1ka", "voj\u00e1k", "NOUN", [143, 149]], ["jeden", "jeden", "NUM", [150, 155]], ["nepo\u0159\u00edd\u00ed", "po\u0159\u00eddit", "VERB", [156, 164]], [".", ".", "PUNCT", [164, 165]]]], ["calgarske-listy_2003_unor_ocr.txt", "Vl\u00e1da schv\u00e1lila program reorganizace Bezpe\u010dnostn\u00ed strategie \u010cR s ohledem na rostouc\u00ed hrozbu terorismu.", [["Vl\u00e1da", "vl\u00e1da", "NOUN", [0, 5]], ["schv\u00e1lila", "schv\u00e1lit", "VERB", [6, 15]], ["program", "program", "NOUN", [16, 23]], ["reorganizace", "reorganizace", "NOUN", [24, 36]], ["Bezpe\u010dnostn\u00ed", "bezpe\u010dnostn\u00ed", "ADJ", [37, 49]], ["strategie", "strategie", "NOUN", [50, 59]], ["\u010cR", "\u010cR", "PROPN", [60, 62]], ["s", "s", "ADP", [63, 64]], ["ohledem", "ohled", "NOUN", [65, 72]], ["na", "na", "ADP", [73, 75]], ["rostouc\u00ed", "rostouc\u00ed", "ADJ", [76, 84]], ["hrozbu", "hrozba", "NOUN", [85, 91]], ["terorismu", "terorismus", "NOUN", [92, 101]], [".", ".", "PUNCT", [101, 102]]]], ["calgarske-listy_2003_unor_ocr.txt", "V prvn\u00ed f\u00e1zi se zlikviduje b\u00f6rdel v arm\u00e1d\u011b.", [["V", "v", "ADP", [0, 1]], ["prvn\u00ed", "prvn\u00ed", "ADJ", [2, 7]], ["f\u00e1zi", "f\u00e1ze", "NOUN", [8, 12]], ["se", "se", "PRON", [13, 15]], ["zlikviduje", "zlikvidovat", "VERB", [16, 26]], ["b\u00f6rdel", "b\u00f6rdle", "NOUN", [27, 33]], ["v", "v", "ADP", [34, 35]], ["arm\u00e1d\u011b", "arm\u00e1da", "NOUN", [36, 42]], [".", ".", "PUNCT", [42, 43]]]], ["calgarske-listy_2003_unor_ocr.txt", "V druh\u00e9 f\u00e1zi, se z pr\u00e1zdn\u00fdch kas\u00e1ren ud\u011bl\u00e1 b\u00f6rdel.", [["V", "v", "ADP", [0, 1]], ["druh\u00e9", "druh\u00fd", "ADJ", [2, 7]], ["f\u00e1zi", "f\u00e1ze", "NOUN", [8, 12]], [",", ",", "PUNCT", [12, 13]], ["se", "se", "PRON", [14, 16]], ["z", "z", "ADP", [17, 18]], ["pr\u00e1zdn\u00fdch", "pr\u00e1zdn\u00fd", "ADJ", [19, 28]], ["kas\u00e1ren", "kas\u00e1rna", "NOUN", [29, 36]], ["ud\u011bl\u00e1", "ud\u011blat", "VERB", [37, 42]], ["b\u00f6rdel", "b\u00f6rdle", "NOUN", [43, 49]], [".", ".", "PUNCT", [49, 50]]]], ["calgarske-listy_2003_unor_ocr.txt", "v CR je ochotna uzav\u0159\u00edt kapitolu zem\u011bd\u011blstv\u00ed, dostane-li v\u00edce krav.", [["v", "v", "ADP", [0, 1]], ["CR", "CR", "NOUN", [2, 4]], ["je", "b\u00fdt", "AUX", [5, 7]], ["ochotna", "ochotn\u00fd", "ADJ", [8, 15]], ["uzav\u0159\u00edt", "uzav\u0159\u00edt", "VERB", [16, 23]], ["kapitolu", "kapitola", "NOUN", [24, 32]], ["zem\u011bd\u011blstv\u00ed", "zem\u011bd\u011blstv\u00ed", "NOUN", [33, 44]], [",", ",", "PUNCT", [44, 45]], ["dostane", "dostat", "VERB", [46, 53]], ["-", "-", "PUNCT", [53, 54]], ["li", "li", "SCONJ", [54, 56]], ["v\u00edce", "v\u00edce", "ADV", [57, 61]], ["krav", "kr\u00e1va", "NOUN", [62, 66]], [".", ".", "PUNCT", [66, 67]]]], ["calgarske-listy_2003_unor_ocr.txt", "Nadbytek vol\u016f vl\u00e1d\u011b starosti zat\u00edm ned\u011bl\u00e1.", [["Nadbytek", "nadbytek", "NOUN", [0, 8]], ["vol\u016f", "v\u016fl", "NOUN", [9, 13]], ["vl\u00e1d\u011b", "vl\u00e1da", "NOUN", [14, 19]], ["starosti", "starost", "NOUN", [20, 28]], ["zat\u00edm", "zat\u00edm", "ADV", [29, 34]], ["ned\u011bl\u00e1", "d\u011blat", "VERB", [35, 41]], [".", ".", "PUNCT", [41, 42]]]], ["calgarske-listy_2003_unor_ocr.txt", "St\u00e1t chce ze dvou s\u00eddli\u0161\u0165 z 50-t\u00fdch.", [["St\u00e1t", "st\u00e1t", "NOUN", [0, 4]], ["chce", "cht\u00edt", "VERB", [5, 9]], ["ze", "z", "ADP", [10, 12]], ["dvou", "dva", "NUM", [13, 17]], ["s\u00eddli\u0161\u0165", "s\u00eddli\u0161t\u011b", "NOUN", [18, 25]], ["z", "z", "ADP", [26, 27]], ["50", "50", "NUM", [28, 30]], ["-", "-", "PUNCT", [30, 31]], ["t\u00fdch", "t\u00fd", "NOUN", [31, 35]], [".", ".", "PUNCT", [35, 36]]]], ["calgarske-listy_2003_unor_ocr.txt", "let u\u010dinit pam\u00e1tkov\u00e9 z\u00f3ny.", [["let", "l\u00e9ta", "NOUN", [0, 3]], ["u\u010dinit", "u\u010dinit", "VERB", [4, 10]], ["pam\u00e1tkov\u00e9", "pam\u00e1tkov\u00fd", "ADJ", [11, 20]], ["z\u00f3ny", "z\u00f3na", "NOUN", [21, 25]], [".", ".", "PUNCT", [25, 26]]]], ["calgarske-listy_2003_unor_ocr.txt", "Uchaze\u010dky o m\u00edsto pr\u016fvodkyn\u00ed turist\u016f, mus\u00ed m\u00edt v k\u00e1drov\u00e9m posudku nejm\u00e9n\u011b deset let \u010dinnosti jako domovn\u00ed d\u016fv\u011brnice, hmotnost nad sto kilogram\u016f a mus\u00ed b\u00fdt na Cibulkov\u00fdch seznamech agent\u016f STB.", [["Uchaze\u010dky", "uchaze\u010dka", "NOUN", [0, 9]], ["o", "o", "ADP", [10, 11]], ["m\u00edsto", "m\u00edsto", "NOUN", [12, 17]], ["pr\u016fvodkyn\u00ed", "pr\u016fvodkyn\u011b", "NOUN", [18, 28]], ["turist\u016f", "turista", "NOUN", [29, 36]], [",", ",", "PUNCT", [36, 37]], ["mus\u00ed", "muset", "VERB", [38, 42]], ["m\u00edt", "m\u00edt", "VERB", [43, 46]], ["v", "v", "ADP", [47, 48]], ["k\u00e1drov\u00e9m", "k\u00e1drov\u00fd", "ADJ", [49, 57]], ["posudku", "posudek", "NOUN", [58, 65]], ["nejm\u00e9n\u011b", "m\u00e9n\u011b", "ADV", [66, 73]], ["deset", "deset", "NUM", [74, 79]], ["let", "l\u00e9ta", "NOUN", [80, 83]], ["\u010dinnosti", "\u010dinnost", "NOUN", [84, 92]], ["jako", "jako", "SCONJ", [93, 97]], ["domovn\u00ed", "domovn\u00ed", "ADJ", [98, 105]], ["d\u016fv\u011brnice", "d\u016fv\u011brnice", "NOUN", [106, 115]], [",", ",", "PUNCT", [115, 116]], ["hmotnost", "hmotnost", "NOUN", [117, 125]], ["nad", "nad", "ADP", [126, 129]], ["sto", "sto", "NUM", [130, 133]], ["kilogram\u016f", "kilogram", "NOUN", [134, 143]], ["a", "a", "CCONJ", [144, 145]], ["mus\u00ed", "muset", "VERB", [146, 150]], ["b\u00fdt", "b\u00fdt", "AUX", [151, 154]], ["na", "na", "ADP", [155, 157]], ["Cibulkov\u00fdch", "Cibulk\u016fv", "ADJ", [158, 169]], ["seznamech", "seznam", "NOUN", [170, 179]], ["agent\u016f", "agent", "NOUN", [180, 186]], ["STB", "STB", "PROPN", [187, 190]], [".", ".", "PUNCT", [190, 191]]]], ["calgarske-listy_2003_unor_ocr.txt", "Hasi\u010di zlikvidovali po\u017e\u00e1r tov\u00e1rny na pap\u00edrov\u00e9 hygienick\u00e9 pot\u0159eby jedn\u00edm velk\u00fdm spl\u00e1chnut\u00edm.", [["Hasi\u010di", "hasi\u010d", "NOUN", [0, 6]], ["zlikvidovali", "zlikvidovat", "VERB", [7, 19]], ["po\u017e\u00e1r", "po\u017e\u00e1r", "NOUN", [20, 25]], ["tov\u00e1rny", "tov\u00e1rna", "NOUN", [26, 33]], ["na", "na", "ADP", [34, 36]], ["pap\u00edrov\u00e9", "pap\u00edrov\u00fd", "ADJ", [37, 45]], ["hygienick\u00e9", "hygienick\u00fd", "ADJ", [46, 56]], ["pot\u0159eby", "pot\u0159eba", "NOUN", [57, 64]], ["jedn\u00edm", "jeden", "NUM", [65, 71]], ["velk\u00fdm", "velk\u00fd", "ADJ", [72, 78]], ["spl\u00e1chnut\u00edm", "spl\u00e1chnut\u00ed", "NOUN", [79, 90]], [".", ".", "PUNCT", [90, 91]]]], ["calgarske-listy_2003_unor_ocr.txt", "Cheb ji\u017e dnes nav\u0161t\u011bvuj\u00ed pedofilov\u00e9 z cel\u00e9 EU.", [["Cheb", "Cheb", "PROPN", [0, 4]], ["ji\u017e", "ji\u017e", "ADV", [5, 8]], ["dnes", "dnes", "ADV", [9, 13]], ["nav\u0161t\u011bvuj\u00ed", "nav\u0161t\u011bvovat", "VERB", [14, 24]], ["pedofilov\u00e9", "pedofil", "NOUN", [25, 35]], ["z", "z", "ADP", [36, 37]], ["cel\u00e9", "cel\u00fd", "ADJ", [38, 42]], ["EU", "EU", "PROPN", [43, 45]], [".", ".", "PUNCT", [45, 46]]]], ["calgarske-listy_2003_unor_ocr.txt", "V d\u016fsledku toho, Lufthansa sn\u00ed\u017eila po\u010det let\u016f z Frankfurtu do Thajska o osmdes\u00e1t procent.", [["V", "v", "ADP", [0, 1]], ["d\u016fsledku", "d\u016fsledek", "NOUN", [2, 10]], ["toho", "ten", "DET", [11, 15]], [",", ",", "PUNCT", [15, 16]], ["Lufthansa", "Lufthansa", "PROPN", [17, 26]], ["sn\u00ed\u017eila", "sn\u00ed\u017eit", "VERB", [27, 34]], ["po\u010det", "po\u010det", "NOUN", [35, 40]], ["let\u016f", "let", "NOUN", [41, 45]], ["z", "z", "ADP", [46, 47]], ["Frankfurtu", "Frankfurt", "PROPN", [48, 58]], ["do", "do", "ADP", [59, 61]], ["Thajska", "Thajsko", "PROPN", [62, 69]], ["o", "o", "ADP", [70, 71]], ["osmdes\u00e1t", "osmdes\u00e1t", "NUM", [72, 80]], ["procent", "procento", "NOUN", [81, 88]], [".", ".", "PUNCT", [88, 89]]]], ["calgarske-listy_2003_unor_ocr.txt", "Kapitalismy m\u00e1te r\u016fzn\u00e9 - Studie p\u0159i\u0161la mejlem, autor nezn\u00e1m\u00fd, zaslal George \u0160vehla z Austr\u00e1lie.", [["Kapitalismy", "kapitalismus", "NOUN", [0, 11]], ["m\u00e1te", "m\u00edt", "VERB", [12, 16]], ["r\u016fzn\u00e9", "r\u016fzn\u00fd", "ADJ", [17, 22]], ["-", "-", "PUNCT", [23, 24]], ["Studie", "studie", "NOUN", [25, 31]], ["p\u0159i\u0161la", "p\u0159ij\u00edt", "VERB", [32, 38]], ["mejlem", "mejlo", "NOUN", [39, 45]], [",", ",", "PUNCT", [45, 46]], ["autor", "autor", "NOUN", [47, 52]], ["nezn\u00e1m\u00fd", "zn\u00e1m\u00fd", "ADJ", [53, 60]], [",", ",", "PUNCT", [60, 61]], ["zaslal", "zaslat", "VERB", [62, 68]], ["George", "George", "PROPN", [69, 75]], ["\u0160vehla", "\u0160vehla", "PROPN", [76, 82]], ["z", "z", "ADP", [83, 84]], ["Austr\u00e1lie", "Austr\u00e1lie", "PROPN", [85, 94]], [".", ".", "PUNCT", [94, 95]]]], ["calgarske-listy_2003_unor_ocr.txt", "TRADI\u010cN\u00cd KAPITALISMUS.", [["TRADI\u010cN\u00cd", "tradi\u010dn\u00ed", "ADJ", [0, 8]], ["KAPITALISMUS", "kapitalismus", "NOUN", [9, 21]], [".", ".", "PUNCT", [21, 22]]]], ["calgarske-listy_2003_unor_ocr.txt", "M\u00e1\u0161 dv\u011b kr\u00e1vy.", [["M\u00e1\u0161", "m\u00edt", "VERB", [0, 3]], ["dv\u011b", "dva", "NUM", [4, 7]], ["kr\u00e1vy", "kr\u00e1va", "NOUN", [8, 13]], [".", ".", "PUNCT", [13, 14]]]], ["calgarske-listy_2003_unor_ocr.txt", "Jednu prod\u00e1\u0161 a koup\u00ed\u0161 b\u00fdka.", [["Jednu", "jeden", "NUM", [0, 5]], ["prod\u00e1\u0161", "prod\u00e1\u0161", "NOUN", [6, 12]], ["a", "a", "CCONJ", [13, 14]], ["koup\u00ed\u0161", "koupit", "VERB", [15, 21]], ["b\u00fdka", "b\u00fdk", "NOUN", [22, 26]], [".", ".", "PUNCT", [26, 27]]]], ["calgarske-listy_2003_unor_ocr.txt", "Tv\u00e9 st\u00e1do krav postupn\u011b roste a ty pomalu bohatne\u0161.", [["Tv\u00e9", "tv\u016fj", "DET", [0, 3]], ["st\u00e1do", "st\u00e1do", "NOUN", [4, 9]], ["krav", "kr\u00e1va", "NOUN", [10, 14]], ["postupn\u011b", "postupn\u011b", "ADV", [15, 23]], ["roste", "r\u016fst", "VERB", [24, 29]], ["a", "a", "CCONJ", [30, 31]], ["ty", "ten", "DET", [32, 34]], ["pomalu", "pomalu", "ADV", [35, 41]], ["bohatne\u0161", "bohatnout", "VERB", [42, 50]], [".", ".", "PUNCT", [50, 51]]]], ["calgarske-listy_2003_unor_ocr.txt", "Nakonec st\u00e1do prod\u00e1\u0161 a \u017eije\u0161 a\u017e do smrti z utr\u017een\u00fdch pen\u011bz AMERICK\u00dd KAPITALISMUS.", [["Nakonec", "nakonec", "ADV", [0, 7]], ["st\u00e1do", "st\u00e1do", "NOUN", [8, 13]], ["prod\u00e1\u0161", "prodat", "VERB", [14, 20]], ["a", "a", "CCONJ", [21, 22]], ["\u017eije\u0161", "\u017e\u00edt", "VERB", [23, 28]], ["a\u017e", "a\u017e", "PART", [29, 31]], ["do", "do", "ADP", [32, 34]], ["smrti", "smrt", "NOUN", [35, 40]], ["z", "z", "ADP", [41, 42]], ["utr\u017een\u00fdch", "utr\u017een\u00fd", "ADJ", [43, 52]], ["pen\u011bz", "pen\u00edze", "NOUN", [53, 58]], ["AMERICK\u00dd", "americk\u00fd", "ADJ", [59, 67]], ["KAPITALISMUS", "kapitalismus", "NOUN", [68, 80]], [".", ".", "PUNCT", [80, 81]]]], ["calgarske-listy_2003_unor_ocr.txt", "M\u00e1\u0161 dv\u011b kr\u00e1vy.", [["M\u00e1\u0161", "m\u00edt", "VERB", [0, 3]], ["dv\u011b", "dva", "NUM", [4, 7]], ["kr\u00e1vy", "kr\u00e1va", "NOUN", [8, 13]], [".", ".", "PUNCT", [13, 14]]]], ["calgarske-listy_2003_unor_ocr.txt", "T\u0159i z nich prod\u00e1\u0161 sv\u00e9 ve\u0159ejn\u00e9 obchodovateln\u00e9 firm\u011b, p\u0159itom pou\u017e\u00edv\u00e1\u0161 kredit, kter\u00fd u banky zalo\u017eil tv\u016fj \u0161vagr.", [["T\u0159i", "t\u0159i", "NUM", [0, 3]], ["z", "z", "ADP", [4, 5]], ["nich", "on", "PRON", [6, 10]], ["prod\u00e1\u0161", "prodat", "VERB", [11, 17]], ["sv\u00e9", "sv\u016fj", "DET", [18, 21]], ["ve\u0159ejn\u00e9", "ve\u0159ejn\u00fd", "ADJ", [22, 29]], ["obchodovateln\u00e9", "obchodovateln\u00fd", "ADJ", [30, 44]], ["firm\u011b", "firma", "NOUN", [45, 50]], [",", ",", "PUNCT", [50, 51]], ["p\u0159itom", "p\u0159itom", "ADV", [52, 58]], ["pou\u017e\u00edv\u00e1\u0161", "pou\u017e\u00edvat", "VERB", [59, 67]], ["kredit", "kredit", "NOUN", [68, 74]], [",", ",", "PUNCT", [74, 75]], ["kter\u00fd", "kter\u00fd", "DET", [76, 81]], ["u", "u", "ADP", [82, 83]], ["banky", "banka", "NOUN", [84, 89]], ["zalo\u017eil", "zalo\u017eit", "VERB", [90, 97]], ["tv\u016fj", "tv\u016fj", "DET", [98, 102]], ["\u0161vagr", "\u0161vagr", "NOUN", [103, 108]], [".", ".", "PUNCT", [108, 109]]]], ["calgarske-listy_2003_unor_ocr.txt", "Pak provede\u0161 \"debt/equity swap\", tak\u017ee dostane\u0161 zp\u011bt v\u0161echny \u010dty\u0159i kr\u00e1vy i s da\u0148ov\u00fdmi \u00falevami pro p\u011bt krav.", [["Pak", "pak", "ADV", [0, 3]], ["provede\u0161", "prov\u00e9st", "VERB", [4, 12]], ["\"", "\"", "PUNCT", [13, 14]], ["debt", "debt", "X", [14, 18]], ["/", "/", "PUNCT", [18, 19]], ["equity", "equity", "X", [19, 25]], ["swap", "swap", "X", [26, 30]], ["\"", "\"", "PUNCT", [30, 31]], [",", ",", "PUNCT", [31, 32]], ["tak\u017ee", "tak\u017ee", "SCONJ", [33, 38]], ["dostane\u0161", "dostat", "VERB", [39, 47]], ["zp\u011bt", "zp\u011bt", "ADV", [48, 52]], ["v\u0161echny", "v\u0161echen", "DET", [53, 60]], ["\u010dty\u0159i", "\u010dty\u0159i", "NUM", [61, 66]], ["kr\u00e1vy", "kr\u00e1va", "NOUN", [67, 72]], ["i", "i", "CCONJ", [73, 74]], ["s", "s", "ADP", [75, 76]], ["da\u0148ov\u00fdmi", "da\u0148ov\u00fd", "ADJ", [77, 85]], ["\u00falevami", "\u00faleva", "NOUN", [86, 93]], ["pro", "pro", "ADP", [94, 97]], ["p\u011bt", "p\u011bt", "NUM", [98, 101]], ["krav", "kr\u00e1va", "NOUN", [102, 106]], [".", ".", "PUNCT", [106, 107]]]], ["calgarske-listy_2003_unor_ocr.txt", "Pr\u00e1va na dojen\u00ed \u0161esti krav p\u0159evede\u0161 p\u0159es prost\u0159edn\u00edka firm\u011b na Kajmansk\u00fdch ostrovech, kterou tajn\u011b vlastn\u00ed majoritn\u00ed akcion\u00e1\u0159.", [["Pr\u00e1va", "pr\u00e1vo", "NOUN", [0, 5]], ["na", "na", "ADP", [6, 8]], ["dojen\u00ed", "dojen\u00ed", "NOUN", [9, 15]], ["\u0161esti", "\u0161est", "NUM", [16, 21]], ["krav", "kr\u00e1va", "NOUN", [22, 26]], ["p\u0159evede\u0161", "p\u0159ev\u00e9st", "VERB", [27, 35]], ["p\u0159es", "p\u0159es", "ADP", [36, 40]], ["prost\u0159edn\u00edka", "prost\u0159edn\u00edk", "NOUN", [41, 53]], ["firm\u011b", "firma", "NOUN", [54, 59]], ["na", "na", "ADP", [60, 62]], ["Kajmansk\u00fdch", "kajmansk\u00fd", "ADJ", [63, 74]], ["ostrovech", "ostrov", "NOUN", [75, 84]], [",", ",", "PUNCT", [84, 85]], ["kterou", "kter\u00fd", "DET", [86, 92]], ["tajn\u011b", "tajn\u011b", "ADV", [93, 98]], ["vlastn\u00ed", "vlastnit", "VERB", [99, 106]], ["majoritn\u00ed", "majoritn\u00ed", "ADJ", [107, 116]], ["akcion\u00e1\u0159", "akcion\u00e1\u0159", "NOUN", [117, 125]], [".", ".", "PUNCT", [125, 126]]]], ["calgarske-listy_2003_unor_ocr.txt", "Ten prod\u00e1 pr\u00e1va na v\u0161ech sedm krav tv\u00e9 zapsan\u00e9 firm\u011b.", [["Ten", "ten", "DET", [0, 3]], ["prod\u00e1", "prodat", "VERB", [4, 9]], ["pr\u00e1va", "pr\u00e1vo", "NOUN", [10, 15]], ["na", "na", "ADP", [16, 18]], ["v\u0161ech", "v\u0161echen", "DET", [19, 24]], ["sedm", "sedm", "NUM", [25, 29]], ["krav", "kr\u00e1va", "NOUN", [30, 34]], ["tv\u00e9", "tv\u016fj", "DET", [35, 38]], ["zapsan\u00e9", "zapsan\u00fd", "ADJ", [39, 46]], ["firm\u011b", "firma", "NOUN", [47, 52]], [".", ".", "PUNCT", [52, 53]]]], ["calgarske-listy_2003_unor_ocr.txt", "Podle ro\u010dn\u00edho hl\u00e1\u0161en\u00ed Tv\u00e1 firma vlastn\u00ed osm krav s opc\u00ed na jednu dal\u0161\u00ed.", [["Podle", "podle", "ADP", [0, 5]], ["ro\u010dn\u00edho", "ro\u010dn\u00ed", "ADJ", [6, 13]], ["hl\u00e1\u0161en\u00ed", "hl\u00e1\u0161en\u00ed", "NOUN", [14, 21]], ["Tv\u00e1", "tv\u00fd", "ADJ", [22, 25]], ["firma", "firma", "NOUN", [26, 31]], ["vlastn\u00ed", "vlastnit", "VERB", [32, 39]], ["osm", "osm", "NUM", [40, 43]], ["krav", "kr\u00e1va", "NOUN", [44, 48]], ["s", "s", "ADP", [49, 50]], ["opc\u00ed", "opce", "NOUN", [51, 55]], ["na", "na", "ADP", [56, 58]], ["jednu", "jeden", "NUM", [59, 64]], ["dal\u0161\u00ed", "dal\u0161\u00ed", "ADJ", [65, 70]], [".", ".", "PUNCT", [70, 71]]]], ["calgarske-listy_2003_unor_ocr.txt", "Prod\u00e1\u0161 jednu kr\u00e1vu, tak\u017ee ti z\u016fst\u00e1v\u00e1 dev\u011bt krav, p\u0159i\u010dem\u017e za str\u017een\u00fd pen\u00edz koup\u00ed\u0161 nov\u00e9ho presidenta USA.", [["Prod\u00e1\u0161", "prodat", "VERB", [0, 6]], ["jednu", "jeden", "NUM", [7, 12]], ["kr\u00e1vu", "kr\u00e1va", "NOUN", [13, 18]], [",", ",", "PUNCT", [18, 19]], ["tak\u017ee", "tak\u017ee", "SCONJ", [20, 25]], ["ti", "ten", "DET", [26, 28]], ["z\u016fst\u00e1v\u00e1", "z\u016fst\u00e1vat", "VERB", [29, 36]], ["dev\u011bt", "dev\u011bt", "NUM", [37, 42]], ["krav", "kr\u00e1va", "NOUN", [43, 47]], [",", ",", "PUNCT", [47, 48]], ["p\u0159i\u010dem\u017e", "p\u0159i\u010dem\u017e", "ADV", [49, 56]], ["za", "za", "ADP", [57, 59]], ["str\u017een\u00fd", "str\u017een\u00fd", "ADJ", [60, 67]], ["pen\u00edz", "pen\u00edz", "NOUN", [68, 73]], ["koup\u00ed\u0161", "koupit", "VERB", [74, 80]], ["nov\u00e9ho", "nov\u00fd", "ADJ", [81, 87]], ["presidenta", "president", "NOUN", [88, 98]], ["USA", "USA", "PROPN", [99, 102]], [".", ".", "PUNCT", [102, 103]]]], ["calgarske-listy_2003_unor_ocr.txt", "Akcion\u00e1\u0159i odkoup\u00ed tv\u00e9ho b\u00fdka.", [["Akcion\u00e1\u0159i", "akcion\u00e1\u0159", "NOUN", [0, 9]], ["odkoup\u00ed", "odkoupit", "VERB", [10, 17]], ["tv\u00e9ho", "tv\u016fj", "DET", [18, 23]], ["b\u00fdka", "b\u00fdk", "NOUN", [24, 28]], [".", ".", "PUNCT", [28, 29]]]], ["calgarske-listy_2003_unor_ocr.txt", "AUSTRALSK\u00dd KAPITALISMUS M\u00e1\u0161 dv\u011b kr\u00e1vy.", [["AUSTRALSK\u00dd", "australsk\u00fd", "ADJ", [0, 10]], ["KAPITALISMUS", "kapitalismus", "NOUN", [11, 23]], ["M\u00e1\u0161", "m\u00edt", "VERB", [24, 27]], ["dv\u011b", "dva", "NUM", [28, 31]], ["kr\u00e1vy", "kr\u00e1va", "NOUN", [32, 37]], [".", ".", "PUNCT", [37, 38]]]], ["calgarske-listy_2003_unor_ocr.txt", "Jednu prod\u00e1\u0161 a tu zbylou nut\u00ed\u0161, aby d\u00e1vala ml\u00e9ko za \u010dty\u0159i.", [["Jednu", "jeden", "NUM", [0, 5]], ["prod\u00e1\u0161", "prod\u00e1\u0161", "NOUN", [6, 12]], ["a", "a", "CCONJ", [13, 14]], ["tu", "tu", "ADV", [15, 17]], ["zbylou", "zbyl\u00fd", "ADJ", [18, 24]], ["nut\u00ed\u0161", "nut\u00ed\u0161", "NOUN", [25, 30]], [",", ",", "PUNCT", [30, 31]], ["aby", "aby", "SCONJ", [-31257, -31257]], ["by", "b\u00fdt", "AUX", [-31257, -31257]], ["d\u00e1vala", "d\u00e1vat", "VERB", [36, 42]], ["ml\u00e9ko", "ml\u00e9ko", "NOUN", [43, 48]], ["za", "za", "ADP", [49, 51]], ["\u010dty\u0159i", "\u010dty\u0159i", "NUM", [52, 57]], [".", ".", "PUNCT", [57, 58]]]], ["calgarske-listy_2003_unor_ocr.txt", "Div\u00ed\u0161 se, kdy\u017e kr\u00e1va chc\u00edpne.", [["Div\u00ed\u0161", "Div\u00ed\u0161", "PROPN", [0, 5]], ["se", "se", "PRON", [6, 8]], [",", ",", "PUNCT", [8, 9]], ["kdy\u017e", "kdy\u017e", "SCONJ", [10, 14]], ["kr\u00e1va", "kr\u00e1va", "NOUN", [15, 20]], ["chc\u00edpne", "chc\u00edpnout", "VERB", [21, 28]], [".", ".", "PUNCT", [28, 29]]]], ["calgarske-listy_2003_unor_ocr.txt", "FRANCOUZSK\u00dd KAPITALISMUS....", [["FRANCOUZSK\u00dd", "francouzsk\u00fd", "ADJ", [0, 11]], ["KAPITALISMUS", "kapitalismus", "NOUN", [12, 24]], [".", ".", "PUNCT", [24, 25]], [".", ".", "PUNCT", [25, 26]], [".", ".", "PUNCT", [26, 27]], [".", ".", "PUNCT", [27, 28]]]], ["calgarske-listy_2003_unor_ocr.txt", "M\u00e1\u0161 dv\u011b kr\u00e1vy.", [["M\u00e1\u0161", "m\u00edt", "VERB", [0, 3]], ["dv\u011b", "dva", "NUM", [4, 7]], ["kr\u00e1vy", "kr\u00e1va", "NOUN", [8, 13]], [".", ".", "PUNCT", [13, 14]]]], ["calgarske-listy_2003_unor_ocr.txt", "Jde\u0161 do st\u00e1vky, proto\u017ee chce\u0161 kr\u00e1vy t\u0159i.", [["Jde\u0161", "j\u00edt", "VERB", [0, 4]], ["do", "do", "ADP", [5, 7]], ["st\u00e1vky", "st\u00e1vka", "NOUN", [8, 14]], [",", ",", "PUNCT", [14, 15]], ["proto\u017ee", "proto\u017ee", "SCONJ", [16, 23]], ["chce\u0161", "cht\u00edt", "VERB", [24, 29]], ["kr\u00e1vy", "kr\u00e1va", "NOUN", [30, 35]], ["t\u0159i", "t\u0159i", "NUM", [36, 39]], [".", ".", "PUNCT", [39, 40]]]], ["calgarske-listy_2003_unor_ocr.txt", "JAPONSK\u00dd KAPITALISMUS M\u00e1\u0161 dv\u011b kr\u00e1vy.", [["JAPONSK\u00dd", "japonsk\u00fd", "ADJ", [0, 8]], ["KAPITALISMUS", "kapitalismus", "NOUN", [9, 21]], ["M\u00e1\u0161", "m\u00edt", "VERB", [22, 25]], ["dv\u011b", "dva", "NUM", [26, 29]], ["kr\u00e1vy", "kr\u00e1va", "NOUN", [30, 35]], [".", ".", "PUNCT", [35, 36]]]], ["calgarske-listy_2003_unor_ocr.txt", "Slo\u017eitou p\u00e9\u010d\u00ed je zmen\u0161\u00ed\u0161 na velikost jedn\u00e9 desetiny norm\u00e1ln\u00ed kr\u00e1vy a p\u0159itom doj\u00ed dvacetkr\u00e1t tolik ml\u00e9ka.", [["Slo\u017eitou", "slo\u017eit\u00fd", "ADJ", [0, 8]], ["p\u00e9\u010d\u00ed", "p\u00e9\u010de", "NOUN", [9, 13]], ["je", "b\u00fdt", "AUX", [14, 16]], ["zmen\u0161\u00ed\u0161", "zmen\u0161it", "VERB", [17, 24]], ["na", "na", "ADP", [25, 27]], ["velikost", "velikost", "NOUN", [28, 36]], ["jedn\u00e9", "jeden", "NUM", [37, 42]], ["desetiny", "desetina", "NOUN", [43, 51]], ["norm\u00e1ln\u00ed", "norm\u00e1ln\u00ed", "ADJ", [52, 60]], ["kr\u00e1vy", "kr\u00e1va", "NOUN", [61, 66]], ["a", "a", "CCONJ", [67, 68]], ["p\u0159itom", "p\u0159itom", "ADV", [69, 75]], ["doj\u00ed", "dojit", "VERB", [76, 80]], ["dvacetkr\u00e1t", "dvacetkr\u00e1t", "ADV", [81, 91]], ["tolik", "tolik", "DET", [92, 97]], ["ml\u00e9ka", "ml\u00e9ko", "NOUN", [98, 103]], [".", ".", "PUNCT", [103, 104]]]], ["calgarske-listy_2003_unor_ocr.txt", "Pak podle nich vytvo\u0159\u00ed\u0161 hru Cowkimon, kterou pak prod\u00e1v\u00e1\u0161 po cel\u00e9m sv\u011bt\u011b.", [["Pak", "pak", "ADV", [0, 3]], ["podle", "podle", "ADP", [4, 9]], ["nich", "on", "PRON", [10, 14]], ["vytvo\u0159\u00ed\u0161", "vytvo\u0159it", "VERB", [15, 23]], ["hru", "hra", "NOUN", [24, 27]], ["Cowkimon", "Cowkimon", "PROPN", [28, 36]], [",", ",", "PUNCT", [36, 37]], ["kterou", "kter\u00fd", "DET", [38, 44]], ["pak", "pak", "ADV", [45, 48]], ["prod\u00e1v\u00e1\u0161", "prod\u00e1vat", "VERB", [49, 57]], ["po", "po", "ADP", [58, 60]], ["cel\u00e9m", "cel\u00fd", "ADJ", [61, 66]], ["sv\u011bt\u011b", "sv\u011bt", "NOUN", [67, 72]], [".", ".", "PUNCT", [72, 73]]]], ["calgarske-listy_2003_unor_ocr.txt", "N\u011aMECK\u00dd KAPITALISMUS M\u00e1\u0161 dv\u011b kr\u00e1vy.", [["N\u011aMECK\u00dd", "n\u011bmeck\u00fd", "ADJ", [0, 7]], ["KAPITALISMUS", "kapitalismus", "NOUN", [8, 20]], ["M\u00e1\u0161", "m\u00edt", "VERB", [21, 24]], ["dv\u011b", "dva", "NUM", [25, 28]], ["kr\u00e1vy", "kr\u00e1va", "NOUN", [29, 34]], [".", ".", "PUNCT", [34, 35]]]], ["calgarske-listy_2003_unor_ocr.txt", "In\u017een\u00fdrsk\u00fdmi \u00fapravami dos\u00e1hne\u0161 toho, \u017ee se kr\u00e1vy do\u017e\u00edvaj\u00ed sta let, \u017eerou jen jednou m\u011bs\u00ed\u010dn\u011b a doj\u00ed se samy.", [["In\u017een\u00fdrsk\u00fdmi", "in\u017een\u00fdrsk\u00fd", "ADJ", [0, 12]], ["\u00fapravami", "\u00faprava", "NOUN", [13, 21]], ["dos\u00e1hne\u0161", "dos\u00e1hnout", "VERB", [22, 30]], ["toho", "ten", "DET", [31, 35]], [",", ",", "PUNCT", [35, 36]], ["\u017ee", "\u017ee", "SCONJ", [37, 39]], ["se", "se", "PRON", [40, 42]], ["kr\u00e1vy", "kr\u00e1va", "NOUN", [43, 48]], ["do\u017e\u00edvaj\u00ed", "do\u017e\u00edvat", "VERB", [49, 57]], ["sta", "sto", "NUM", [58, 61]], ["let", "l\u00e9ta", "NOUN", [62, 65]], [",", ",", "PUNCT", [65, 66]], ["\u017eerou", "\u017er\u00e1t", "VERB", [67, 72]], ["jen", "jen", "PART", [73, 76]], ["jednou", "jednou", "ADV", [77, 83]], ["m\u011bs\u00ed\u010dn\u011b", "m\u011bs\u00ed\u010dn\u011b", "ADV", [84, 91]], ["a", "a", "CCONJ", [92, 93]], ["doj\u00ed", "dojit", "VERB", [94, 98]], ["se", "se", "PRON", [99, 101]], ["samy", "sam\u00fd", "DET", [102, 106]], [".", ".", "PUNCT", [106, 107]]]], ["calgarske-listy_2003_unor_ocr.txt", "BRITSK\u00dd KAPITALISMUS.", [["BRITSK\u00dd", "britsk\u00fd", "ADJ", [0, 7]], ["KAPITALISMUS", "kapitalismus", "NOUN", [8, 20]], [".", ".", "PUNCT", [20, 21]]]], ["calgarske-listy_2003_unor_ocr.txt", "M\u00e1\u0161 dv\u011b kr\u00e1vy.", [["M\u00e1\u0161", "m\u00edt", "VERB", [0, 3]], ["dv\u011b", "dva", "NUM", [4, 7]], ["kr\u00e1vy", "kr\u00e1va", "NOUN", [8, 13]], [".", ".", "PUNCT", [13, 14]]]], ["calgarske-listy_2003_unor_ocr.txt", "Ob\u011b jsou \u0161\u00edlen\u00e9.", [["Ob\u011b", "oba", "NUM", [0, 3]], ["jsou", "b\u00fdt", "AUX", [4, 8]], ["\u0161\u00edlen\u00e9", "\u0161\u00edlen\u00fd", "ADJ", [9, 15]], [".", ".", "PUNCT", [15, 16]]]], ["calgarske-listy_2003_unor_ocr.txt", "KANADSK\u00dd KAPITALISMUS M\u00e1\u0161 dv\u011b kr\u00e1vy.", [["KANADSK\u00dd", "kanadsk\u00fd", "ADJ", [0, 8]], ["KAPITALISMUS", "kapitalismus", "NOUN", [9, 21]], ["M\u00e1\u0161", "m\u00edt", "VERB", [22, 25]], ["dv\u011b", "dva", "NUM", [26, 29]], ["kr\u00e1vy", "kr\u00e1va", "NOUN", [30, 35]], [".", ".", "PUNCT", [35, 36]]]], ["calgarske-listy_2003_unor_ocr.txt", "Kdy\u017e na to p\u0159ijde, vypadaj\u00ed sp\u00ed\u0161 jak p\u00e1rek los\u016f a to doopravdy jsou.", [["Kdy\u017e", "kdy\u017e", "SCONJ", [0, 4]], ["na", "na", "ADP", [5, 7]], ["to", "ten", "DET", [8, 10]], ["p\u0159ijde", "p\u0159ij\u00edt", "VERB", [11, 17]], [",", ",", "PUNCT", [17, 18]], ["vypadaj\u00ed", "vypadat", "VERB", [19, 27]], ["sp\u00ed\u0161", "sp\u00ed\u0161", "PART", [28, 32]], ["jak", "jak", "ADV", [33, 36]], ["p\u00e1rek", "p\u00e1rek", "NOUN", [37, 42]], ["los\u016f", "los", "NOUN", [43, 47]], ["a", "a", "CCONJ", [48, 49]], ["to", "ten", "DET", [50, 52]], ["doopravdy", "doopravdy", "ADV", [53, 62]], ["jsou", "b\u00fdt", "AUX", [63, 67]], [".", ".", "PUNCT", [67, 68]]]], ["calgarske-listy_2003_unor_ocr.txt", "Jedna mluv\u00ed francouzsk\u00fd, druh\u00e1 anglicky.", [["Jedna", "jeden", "NUM", [0, 5]], ["mluv\u00ed", "mluvit", "VERB", [6, 11]], ["francouzsk\u00fd", "francouzsk\u00fd", "ADJ", [12, 23]], [",", ",", "PUNCT", [23, 24]], ["druh\u00e1", "druh\u00fd", "ADJ", [25, 30]], ["anglicky", "anglicky", "ADV", [31, 39]], [".", ".", "PUNCT", [39, 40]]]], ["calgarske-listy_2003_unor_ocr.txt", "Jedna bojuje za vytvo\u0159en\u00ed nov\u00e9 zem\u011b, druh\u00e1 se tomu br\u00e1n\u00ed.", [["Jedna", "jeden", "NUM", [0, 5]], ["bojuje", "bojovat", "VERB", [6, 12]], ["za", "za", "ADP", [13, 15]], ["vytvo\u0159en\u00ed", "vytvo\u0159en\u00ed", "NOUN", [16, 25]], ["nov\u00e9", "nov\u00fd", "ADJ", [26, 30]], ["zem\u011b", "zem\u011b", "NOUN", [31, 35]], [",", ",", "PUNCT", [35, 36]], ["druh\u00e1", "druh\u00fd", "ADJ", [37, 42]], ["se", "se", "PRON", [43, 45]], ["tomu", "ten", "DET", [46, 50]], ["br\u00e1n\u00ed", "br\u00e1nit", "VERB", [51, 56]], [".", ".", "PUNCT", [56, 57]]]], ["calgarske-listy_2003_unor_ocr.txt", "Ob\u011b hraj\u00ed docela slu\u0161n\u011b hokej.", [["Ob\u011b", "oba", "NUM", [0, 3]], ["hraj\u00ed", "hr\u00e1t", "VERB", [4, 9]], ["docela", "docela", "ADV", [10, 16]], ["slu\u0161n\u011b", "slu\u0161n\u011b", "ADV", [17, 23]], ["hokej", "hokej", "NOUN", [24, 29]], [".", ".", "PUNCT", [29, 30]]]], ["calgarske-listy_2003_unor_ocr.txt", "ITALSK\u00dd KAPITALISMUS", [["ITALSK\u00dd", "italsk\u00fd", "ADJ", [0, 7]], ["KAPITALISMUS", "kapitalismus", "NOUN", [8, 20]]]], ["calgarske-listy_2003_unor_ocr.txt", "M\u00e1\u0161 dv\u011b kr\u00e1vy, jen\u017ee nev\u00ed\u0161 kde.", [["M\u00e1\u0161", "m\u00edt", "VERB", [0, 3]], ["dv\u011b", "dva", "NUM", [4, 7]], ["kr\u00e1vy", "kr\u00e1va", "NOUN", [8, 13]], [",", ",", "PUNCT", [13, 14]], ["jen\u017ee", "jen\u017ee", "CCONJ", [15, 20]], ["nev\u00ed\u0161", "v\u011bd\u011bt", "VERB", [21, 26]], ["kde", "kde", "ADV", [27, 30]], [".", ".", "PUNCT", [30, 31]]]], ["calgarske-listy_2003_unor_ocr.txt", "Ud\u011bl\u00e1\u0161 si poledn\u00ed p\u0159est\u00e1vku a odejde\u0161 na ob\u011bd.", [["Ud\u011bl\u00e1\u0161", "ud\u011blat", "VERB", [0, 6]], ["si", "se", "PRON", [7, 9]], ["poledn\u00ed", "poledn\u00ed", "ADJ", [10, 17]], ["p\u0159est\u00e1vku", "p\u0159est\u00e1vka", "NOUN", [18, 27]], ["a", "a", "CCONJ", [28, 29]], ["odejde\u0161", "odej\u00edt", "VERB", [30, 37]], ["na", "na", "ADP", [38, 40]], ["ob\u011bd", "ob\u011bd", "NOUN", [41, 45]], [".", ".", "PUNCT", [45, 46]]]], ["calgarske-listy_2003_unor_ocr.txt", "RUSK\u00dd KAPITALISMUS M\u00e1\u0161 dv\u011b kr\u00e1vy.", [["RUSK\u00dd", "rusk\u00fd", "ADJ", [0, 5]], ["KAPITALISMUS", "kapitalismus", "NOUN", [6, 18]], ["M\u00e1\u0161", "m\u00edt", "VERB", [19, 22]], ["dv\u011b", "dva", "NUM", [23, 26]], ["kr\u00e1vy", "kr\u00e1va", "NOUN", [27, 32]], [".", ".", "PUNCT", [32, 33]]]], ["calgarske-listy_2003_unor_ocr.txt", "Za\u010dne\u0161 je po\u010d\u00edtat a napo\u010d\u00edt\u00e1\u0161 jich p\u011bt.", [["Za\u010dne\u0161", "za\u010d\u00edt", "VERB", [0, 6]], ["je", "on", "PRON", [7, 9]], ["po\u010d\u00edtat", "po\u010d\u00edtat", "VERB", [10, 17]], ["a", "a", "CCONJ", [18, 19]], ["napo\u010d\u00edt\u00e1\u0161", "napo\u010d\u00edtat", "VERB", [20, 29]], ["jich", "on", "PRON", [30, 34]], ["p\u011bt", "p\u011bt", "NUM", [35, 38]], [".", ".", "PUNCT", [38, 39]]]], ["calgarske-listy_2003_unor_ocr.txt", "Spo\u010d\u00edt\u00e1\u0161 je znova a napo\u010d\u00edt\u00e1\u0161 jich \u010dty\u0159icet dva.", [["Spo\u010d\u00edt\u00e1\u0161", "spo\u010d\u00edtat", "VERB", [0, 8]], ["je", "b\u00fdt", "AUX", [9, 11]], ["znova", "znova", "ADV", [12, 17]], ["a", "a", "CCONJ", [18, 19]], ["napo\u010d\u00edt\u00e1\u0161", "napo\u010d\u00edtat", "VERB", [20, 29]], ["jich", "on", "PRON", [30, 34]], ["\u010dty\u0159icet", "\u010dty\u0159icet", "NUM", [35, 43]], ["dva", "dva", "NUM", [44, 47]], [".", ".", "PUNCT", [47, 48]]]], ["calgarske-listy_2003_unor_ocr.txt", "P\u0159epo\u010d\u00edt\u00e1\u0161 je a napo\u010d\u00edt\u00e1\u0161 jich dvan\u00e1ct.", [["P\u0159epo\u010d\u00edt\u00e1\u0161", "p\u0159epo\u010d\u00edtat", "VERB", [0, 10]], ["je", "on", "PRON", [11, 13]], ["a", "a", "CCONJ", [14, 15]], ["napo\u010d\u00edt\u00e1\u0161", "napo\u010d\u00edtat", "VERB", [16, 25]], ["jich", "on", "PRON", [26, 30]], ["dvan\u00e1ct", "dvan\u00e1ct", "NUM", [31, 38]], [".", ".", "PUNCT", [38, 39]]]], ["calgarske-listy_2003_unor_ocr.txt", "P\u0159estane\u0161 po\u010d\u00edtat kr\u00e1vy a otev\u0159e\u0161 dal\u0161\u00ed l\u00e1hev vodky.", [["P\u0159estane\u0161", "p\u0159estat", "VERB", [0, 9]], ["po\u010d\u00edtat", "po\u010d\u00edtat", "VERB", [10, 17]], ["kr\u00e1vy", "kr\u00e1va", "NOUN", [18, 23]], ["a", "a", "CCONJ", [24, 25]], ["otev\u0159e\u0161", "otev\u0159\u00edt", "VERB", [26, 33]], ["dal\u0161\u00ed", "dal\u0161\u00ed", "ADJ", [34, 39]], ["l\u00e1hev", "l\u00e1hev", "NOUN", [40, 45]], ["vodky", "vodka", "NOUN", [46, 51]], [".", ".", "PUNCT", [51, 52]]]], ["calgarske-listy_2003_unor_ocr.txt", "\u0160V\u00ddCARSK\u00dd KAPITALISMUS", [["\u0160V\u00ddCARSK\u00dd", "\u0161v\u00fdcarsk\u00fd", "ADJ", [0, 9]], ["KAPITALISMUS", "kapitalismus", "NOUN", [10, 22]]]], ["calgarske-listy_2003_unor_ocr.txt", "M\u00e1\u0161 p\u011bt tis\u00edc krav a \u017e\u00e1dn\u00e1 ti nepat\u0159\u00ed.", [["M\u00e1\u0161", "m\u00edt", "VERB", [0, 3]], ["p\u011bt", "p\u011bt", "NUM", [4, 7]], ["tis\u00edc", "tis\u00edc", "NUM", [8, 13]], ["krav", "kr\u00e1va", "NOUN", [14, 18]], ["a", "a", "CCONJ", [19, 20]], ["\u017e\u00e1dn\u00e1", "\u017e\u00e1dn\u00fd", "DET", [21, 26]], ["ti", "ten", "DET", [27, 29]], ["nepat\u0159\u00ed", "pat\u0159it", "VERB", [30, 37]], [".", ".", "PUNCT", [37, 38]]]], ["calgarske-listy_2003_unor_ocr.txt", "Nech\u00e1\u0161 si platit neuv\u011b\u0159iteln\u00e9 poplatky za ust\u00e1jen\u00ed.", [["Nech\u00e1\u0161", "nechat", "VERB", [0, 6]], ["si", "se", "PRON", [7, 9]], ["platit", "platit", "VERB", [10, 16]], ["neuv\u011b\u0159iteln\u00e9", "uv\u011b\u0159iteln\u00fd", "ADJ", [17, 29]], ["poplatky", "poplatek", "NOUN", [30, 38]], ["za", "za", "ADP", [39, 41]], ["ust\u00e1jen\u00ed", "ust\u00e1jen\u00ed", "NOUN", [42, 50]], [".", ".", "PUNCT", [50, 51]]]], ["calgarske-listy_2003_unor_ocr.txt", "\u010c\u00cdNSK\u00dd KAPITALISMUS M\u00e1\u0161 dv\u011b kr\u00e1vy.", [["\u010c\u00cdNSK\u00dd", "\u010d\u00ednsk\u00fd", "ADJ", [0, 6]], ["KAPITALISMUS", "kapitalismus", "NOUN", [7, 19]], ["M\u00e1\u0161", "m\u00edt", "VERB", [20, 23]], ["dv\u011b", "dva", "NUM", [24, 27]], ["kr\u00e1vy", "kr\u00e1va", "NOUN", [28, 33]], [".", ".", "PUNCT", [33, 34]]]], ["calgarske-listy_2003_unor_ocr.txt", "M\u00e1\u0161 t\u0159i sta pracovn\u00edk\u016f, kte\u0159\u00ed kr\u00e1vy doj\u00ed.", [["M\u00e1\u0161", "m\u00edt", "VERB", [0, 3]], ["t\u0159i", "t\u0159i", "NUM", [4, 7]], ["sta", "sto", "NUM", [8, 11]], ["pracovn\u00edk\u016f", "pracovn\u00edk", "NOUN", [12, 22]], [",", ",", "PUNCT", [22, 23]], ["kte\u0159\u00ed", "kter\u00fd", "DET", [24, 29]], ["kr\u00e1vy", "kr\u00e1va", "NOUN", [30, 35]], ["doj\u00ed", "dojit", "VERB", [36, 40]], [".", ".", "PUNCT", [40, 41]]]], ["calgarske-listy_2003_unor_ocr.txt", "Ve\u0159ejn\u011b ozn\u00e1m\u00ed\u0161 plnou zam\u011bstnanost a vysokou produktivitu krav.", [["Ve\u0159ejn\u011b", "ve\u0159ejn\u011b", "ADV", [0, 7]], ["ozn\u00e1m\u00ed\u0161", "ozn\u00e1mit", "VERB", [8, 15]], ["plnou", "pln\u00fd", "ADJ", [16, 21]], ["zam\u011bstnanost", "zam\u011bstnanost", "NOUN", [22, 34]], ["a", "a", "CCONJ", [35, 36]], ["vysokou", "vysok\u00fd", "ADJ", [37, 44]], ["produktivitu", "produktivita", "NOUN", [45, 57]], ["krav", "kr\u00e1va", "NOUN", [58, 62]], [".", ".", "PUNCT", [62, 63]]]], ["calgarske-listy_2003_unor_ocr.txt", "Uv\u011bzn\u00ed\u0161 a pot\u00e9 bez soudu dr\u017e\u00ed\u0161 ve v\u011bzen\u00ed novin\u00e1\u0159e, kter\u00fd zve\u0159ejnil po\u010det NOVOZ\u00c9LANDSK\u00dd KAPITALISMUS M\u00e1\u0161 dv\u011b kr\u00e1vy.", [["Uv\u011bzn\u00ed\u0161", "uv\u011bzn\u00ed", "ADJ", [0, 7]], ["a", "a", "CCONJ", [8, 9]], ["pot\u00e9", "pot\u00e9", "ADV", [10, 14]], ["bez", "bez", "ADP", [15, 18]], ["soudu", "soud", "NOUN", [19, 24]], ["dr\u017e\u00ed\u0161", "dr\u017eet", "VERB", [25, 30]], ["ve", "v", "ADP", [31, 33]], ["v\u011bzen\u00ed", "v\u011bzen\u00ed", "NOUN", [34, 40]], ["novin\u00e1\u0159e", "novin\u00e1\u0159", "NOUN", [41, 49]], [",", ",", "PUNCT", [49, 50]], ["kter\u00fd", "kter\u00fd", "DET", [51, 56]], ["zve\u0159ejnil", "zve\u0159ejnit", "VERB", [57, 66]], ["po\u010det", "po\u010det", "NOUN", [67, 72]], ["NOVOZ\u00c9LANDSK\u00dd", "novoz\u00e9landsk\u00fd", "ADJ", [73, 86]], ["KAPITALISMUS", "kapitalismus", "NOUN", [87, 99]], ["M\u00e1\u0161", "m\u00edt", "VERB", [100, 103]], ["dv\u011b", "dva", "NUM", [104, 107]], ["kr\u00e1vy", "kr\u00e1va", "NOUN", [108, 113]], [".", ".", "PUNCT", [113, 114]]]], ["calgarske-listy_2003_unor_ocr.txt", "Ta vlevo je docela roztomil\u00e1...", [["Ta", "ten", "DET", [0, 2]], ["vlevo", "vlevo", "ADV", [3, 8]], ["je", "b\u00fdt", "AUX", [9, 11]], ["docela", "docela", "ADV", [12, 18]], ["roztomil\u00e1", "roztomil\u00fd", "ADJ", [19, 28]], [".", ".", "PUNCT", [28, 29]], [".", ".", "PUNCT", [29, 30]], [".", ".", "PUNCT", [30, 31]]]], ["calgarske-listy_2003_unor_ocr.txt", "\u010cESK\u00dd KAPITALISMUS, neetick\u00e1 forma.", [["\u010cESK\u00dd", "\u010desk\u00fd", "ADJ", [0, 5]], ["KAPITALISMUS", "kapitalismus", "NOUN", [6, 18]], [",", ",", "PUNCT", [18, 19]], ["neetick\u00e1", "etick\u00fd", "ADJ", [20, 28]], ["forma", "forma", "NOUN", [29, 34]], [".", ".", "PUNCT", [34, 35]]]], ["calgarske-listy_2003_unor_ocr.txt", "M\u00e1\u0161 dv\u011b kr\u00e1vy.", [["M\u00e1\u0161", "m\u00edt", "VERB", [0, 3]], ["dv\u011b", "dva", "NUM", [4, 7]], ["kr\u00e1vy", "kr\u00e1va", "NOUN", [8, 13]], [".", ".", "PUNCT", [13, 14]]]], ["calgarske-listy_2003_unor_ocr.txt", "Jednaje Tv\u00e1 \u017eena a druh\u00e1 je Tvoje tch\u00fdn\u011b.", [["Jednaje", "Jednaj", "PROPN", [0, 7]], ["Tv\u00e1", "tv\u00fd", "ADJ", [8, 11]], ["\u017eena", "\u017eena", "NOUN", [12, 16]], ["a", "a", "CCONJ", [17, 18]], ["druh\u00e1", "druh\u00fd", "ADJ", [19, 24]], ["je", "b\u00fdt", "AUX", [25, 27]], ["Tvoje", "tvoj\u00ed", "ADJ", [28, 33]], ["tch\u00fdn\u011b", "tch\u00fd\u0148", "NOUN", [34, 40]], [".", ".", "PUNCT", [40, 41]]]], ["calgarske-listy_2003_unor_ocr.txt", "\u010cESK\u00dd KAPITALISMUS, etick\u00e1 forma.", [["\u010cESK\u00dd", "\u010desk\u00fd", "ADJ", [0, 5]], ["KAPITALISMUS", "kapitalismus", "NOUN", [6, 18]], [",", ",", "PUNCT", [18, 19]], ["etick\u00e1", "etick\u00fd", "ADJ", [20, 26]], ["forma", "forma", "NOUN", [27, 32]], [".", ".", "PUNCT", [32, 33]]]], ["calgarske-listy_2003_unor_ocr.txt", "V restituci jsi dostal osv\u011bd\u010den\u00ed, \u017ee ti vr\u00e1tili to, co zbylo z d\u011bde\u010dkova st\u00e1da, ve skute\u010dnosti ti nevr\u00e1tili nic, proto\u017ee kr\u00e1vy pochc\u00edpaly, p\u0159esto st\u00e1t ti poslal da\u0148ov\u00fd v\u00fdm\u011br za v\u00fdt\u011b\u017eek z p\u016fvodn\u00edho d\u011bde\u010dkova st\u00e1da za deset let dozadu plus pen\u00e1le.", [["V", "v", "ADP", [0, 1]], ["restituci", "restituce", "NOUN", [2, 11]], ["jsi", "b\u00fdt", "AUX", [12, 15]], ["dostal", "dostat", "VERB", [16, 22]], ["osv\u011bd\u010den\u00ed", "osv\u011bd\u010den\u00ed", "NOUN", [23, 32]], [",", ",", "PUNCT", [32, 33]], ["\u017ee", "\u017ee", "SCONJ", [34, 36]], ["ti", "ten", "DET", [37, 39]], ["vr\u00e1tili", "vr\u00e1tit", "VERB", [40, 47]], ["to", "ten", "DET", [48, 50]], [",", ",", "PUNCT", [50, 51]], ["co", "co", "PRON", [52, 54]], ["zbylo", "zb\u00fdt", "VERB", [55, 60]], ["z", "z", "ADP", [61, 62]], ["d\u011bde\u010dkova", "d\u011bde\u010dk\u016fv", "ADJ", [63, 72]], ["st\u00e1da", "st\u00e1do", "NOUN", [73, 78]], [",", ",", "PUNCT", [78, 79]], ["ve", "v", "ADP", [80, 82]], ["skute\u010dnosti", "skute\u010dnost", "NOUN", [83, 94]], ["ti", "ten", "DET", [95, 97]], ["nevr\u00e1tili", "vr\u00e1tit", "VERB", [98, 107]], ["nic", "nic", "PRON", [108, 111]], [",", ",", "PUNCT", [111, 112]], ["proto\u017ee", "proto\u017ee", "SCONJ", [113, 120]], ["kr\u00e1vy", "kr\u00e1va", "NOUN", [121, 126]], ["pochc\u00edpaly", "pochc\u00edpat", "VERB", [127, 137]], [",", ",", "PUNCT", [137, 138]], ["p\u0159esto", "p\u0159esto", "CCONJ", [139, 145]], ["st\u00e1t", "st\u00e1t", "NOUN", [146, 150]], ["ti", "ten", "DET", [151, 153]], ["poslal", "poslat", "VERB", [154, 160]], ["da\u0148ov\u00fd", "da\u0148ov\u00fd", "ADJ", [161, 167]], ["v\u00fdm\u011br", "v\u00fdm\u011br", "NOUN", [168, 173]], ["za", "za", "ADP", [174, 176]], ["v\u00fdt\u011b\u017eek", "v\u00fdt\u011b\u017eek", "NOUN", [177, 184]], ["z", "z", "ADP", [185, 186]], ["p\u016fvodn\u00edho", "p\u016fvodn\u00ed", "ADJ", [187, 196]], ["d\u011bde\u010dkova", "d\u011bde\u010dk\u016fv", "ADJ", [197, 206]], ["st\u00e1da", "st\u00e1do", "NOUN", [207, 212]], ["za", "za", "ADP", [213, 215]], ["deset", "deset", "NUM", [216, 221]], ["let", "l\u00e9ta", "NOUN", [222, 225]], ["dozadu", "dozadu", "NOUN", [226, 232]], ["plus", "plus", "NOUN", [233, 237]], ["pen\u00e1le", "pen\u00e1le", "NOUN", [238, 244]], [".", ".", "PUNCT", [244, 245]]]], ["calgarske-listy_2003_unor_ocr.txt", "Zalo\u017eil jsi firmu na chov krav.", [["Zalo\u017eil", "zalo\u017eit", "VERB", [0, 7]], ["jsi", "b\u00fdt", "AUX", [8, 11]], ["firmu", "firma", "NOUN", [12, 17]], ["na", "na", "ADP", [18, 20]], ["chov", "chov", "NOUN", [21, 25]], ["krav", "kr\u00e1va", "NOUN", [26, 30]], [".", ".", "PUNCT", [30, 31]]]], ["calgarske-listy_2003_unor_ocr.txt", "Kolega est\u00e9b\u00e1k v bance ti na z\u00e1klad\u011b osv\u011bd\u010den\u00ed a odborn\u00e9ho posudku jin\u00e9ho est\u00e9b\u00e1ka, soudn\u00edho znalce poskytl p\u016fj\u010dku t\u0159i \u010dtvrt\u011b miliardy.", [["Kolega", "kolega", "NOUN", [0, 6]], ["est\u00e9b\u00e1k", "est\u00e9b\u00e1k", "NOUN", [7, 14]], ["v", "v", "ADP", [15, 16]], ["bance", "banka", "NOUN", [17, 22]], ["ti", "ten", "DET", [23, 25]], ["na", "na", "ADP", [26, 28]], ["z\u00e1klad\u011b", "z\u00e1klad", "NOUN", [29, 36]], ["osv\u011bd\u010den\u00ed", "osv\u011bd\u010den\u00ed", "NOUN", [37, 46]], ["a", "a", "CCONJ", [47, 48]], ["odborn\u00e9ho", "odborn\u00fd", "ADJ", [49, 58]], ["posudku", "posudek", "NOUN", [59, 66]], ["jin\u00e9ho", "jin\u00fd", "ADJ", [67, 73]], ["est\u00e9b\u00e1ka", "est\u00e9b\u00e1k", "NOUN", [74, 82]], [",", ",", "PUNCT", [82, 83]], ["soudn\u00edho", "soudn\u00ed", "ADJ", [84, 92]], ["znalce", "znalec", "NOUN", [93, 99]], ["poskytl", "poskytnout", "VERB", [100, 107]], ["p\u016fj\u010dku", "p\u016fj\u010dka", "NOUN", [108, 114]], ["t\u0159i", "t\u0159i", "NUM", [115, 118]], ["\u010dtvrt\u011b", "\u010dtvrt", "NUM", [119, 125]], ["miliardy", "miliarda", "NUM", [126, 134]], [".", ".", "PUNCT", [134, 135]]]], ["calgarske-listy_2003_unor_ocr.txt", "Tu jsi p\u0159evedl na jinou svoji firmu a vyhl\u00e1sil \u00fapadek.", [["Tu", "tu", "ADV", [0, 2]], ["jsi", "b\u00fdt", "AUX", [3, 6]], ["p\u0159evedl", "p\u0159ev\u00e9st", "VERB", [7, 14]], ["na", "na", "ADP", [15, 17]], ["jinou", "jin\u00fd", "ADJ", [18, 23]], ["svoji", "sv\u016fj", "DET", [24, 29]], ["firmu", "firma", "NOUN", [30, 35]], ["a", "a", "CCONJ", [36, 37]], ["vyhl\u00e1sil", "vyhl\u00e1sit", "VERB", [38, 46]], ["\u00fapadek", "\u00fapadek", "NOUN", [47, 53]], [".", ".", "PUNCT", [53, 54]]]], ["calgarske-listy_2003_unor_ocr.txt", "Nyn\u00ed jse\u0161 za vodou a pova\u017euje\u0161 ka\u017ed\u00e9ho kdo se star\u00e1 o kr\u00e1vy za vola.", [["Nyn\u00ed", "nyn\u00ed", "ADV", [0, 4]], ["jse\u0161", "j\u00edt", "VERB", [5, 9]], ["za", "za", "ADP", [10, 12]], ["vodou", "voda", "NOUN", [13, 18]], ["a", "a", "CCONJ", [19, 20]], ["pova\u017euje\u0161", "pova\u017eovat", "VERB", [21, 30]], ["ka\u017ed\u00e9ho", "ka\u017ed\u00fd", "DET", [31, 38]], ["kdo", "kdo", "PRON", [39, 42]], ["se", "se", "PRON", [43, 45]], ["star\u00e1", "star\u00fd", "ADJ", [46, 51]], ["o", "o", "ADP", [52, 53]], ["kr\u00e1vy", "kr\u00e1va", "NOUN", [54, 59]], ["za", "za", "ADP", [60, 62]], ["vola", "vola", "NOUN", [63, 67]], [".", ".", "PUNCT", [67, 68]]]], ["calgarske-listy_2003_unor_ocr.txt", "8  L\u00e1ska na cel\u00fd \u017eivot Rozvodovost v na\u0161ich zem\u00edch st\u00e1le stoup\u00e1 a tak\u00e9 p\u00e1ry bez oddac\u00edho listu na tom nejsou o mnoho l\u00e9pe.", [["8", "8", "NUM", [0, 1]], ["L\u00e1ska", "l\u00e1ska", "NOUN", [3, 8]], ["na", "na", "ADP", [9, 11]], ["cel\u00fd", "cel\u00fd", "ADJ", [12, 16]], ["\u017eivot", "\u017eivot", "NOUN", [17, 22]], ["Rozvodovost", "rozvodovost", "NOUN", [23, 34]], ["v", "v", "ADP", [35, 36]], ["na\u0161ich", "n\u00e1\u0161", "DET", [37, 43]], ["zem\u00edch", "zem\u011b", "NOUN", [44, 50]], ["st\u00e1le", "st\u00e1le", "ADV", [51, 56]], ["stoup\u00e1", "stoupat", "VERB", [57, 63]], ["a", "a", "CCONJ", [64, 65]], ["tak\u00e9", "tak\u00e9", "ADV", [66, 70]], ["p\u00e1ry", "p\u00e1r", "NOUN", [71, 75]], ["bez", "bez", "ADP", [76, 79]], ["oddac\u00edho", "oddac\u00ed", "ADJ", [80, 88]], ["listu", "list", "NOUN", [89, 94]], ["na", "na", "ADP", [95, 97]], ["tom", "ten", "DET", [98, 101]], ["nejsou", "b\u00fdt", "AUX", [102, 108]], ["o", "o", "ADP", [109, 110]], ["mnoho", "mnoho", "DET", [111, 116]], ["l\u00e9pe", "l\u00e9pe", "ADV", [117, 121]], [".", ".", "PUNCT", [121, 122]]]], ["calgarske-listy_2003_unor_ocr.txt", "Velk\u00e1 l\u00e1ska v\u0161ak existuje a m\u016f\u017ee trvat cel\u00e1 desetilet\u00ed.", [["Velk\u00e1", "velk\u00fd", "ADJ", [0, 5]], ["l\u00e1ska", "l\u00e1ska", "NOUN", [6, 11]], ["v\u0161ak", "v\u0161ak", "CCONJ", [12, 16]], ["existuje", "existovat", "VERB", [17, 25]], ["a", "a", "CCONJ", [26, 27]], ["m\u016f\u017ee", "moci", "VERB", [28, 32]], ["trvat", "trvat", "VERB", [33, 38]], ["cel\u00e1", "cel\u00fd", "ADJ", [39, 43]], ["desetilet\u00ed", "desetilet\u00ed", "NOUN", [44, 54]], [".", ".", "PUNCT", [54, 55]]]], ["calgarske-listy_2003_unor_ocr.txt", "Nepad\u00e1 sama z nebes.", [["Nepad\u00e1", "padat", "VERB", [0, 6]], ["sama", "sam\u00fd", "DET", [7, 11]], ["z", "z", "ADP", [12, 13]], ["nebes", "nebesa", "NOUN", [14, 19]], [".", ".", "PUNCT", [19, 20]]]], ["calgarske-listy_2003_unor_ocr.txt", "Sen o velk\u00e9 l\u00e1sce se vypln\u00ed teprve tehdy, kdy\u017e se oba partne\u0159i dr\u017e\u00ed ur\u010dit\u00fdch pravidel.", [["Sen", "sen", "NOUN", [0, 3]], ["o", "o", "ADP", [4, 5]], ["velk\u00e9", "velk\u00fd", "ADJ", [6, 11]], ["l\u00e1sce", "l\u00e1ska", "NOUN", [12, 17]], ["se", "se", "PRON", [18, 20]], ["vypln\u00ed", "vyplnit", "VERB", [21, 27]], ["teprve", "teprve", "ADV", [28, 34]], ["tehdy", "tehdy", "ADV", [35, 40]], [",", ",", "PUNCT", [40, 41]], ["kdy\u017e", "kdy\u017e", "SCONJ", [42, 46]], ["se", "se", "PRON", [47, 49]], ["oba", "oba", "NUM", [50, 53]], ["partne\u0159i", "partner", "NOUN", [54, 62]], ["dr\u017e\u00ed", "dr\u017eet", "VERB", [63, 67]], ["ur\u010dit\u00fdch", "ur\u010dit\u00fd", "ADJ", [68, 76]], ["pravidel", "pravidlo", "NOUN", [77, 85]], [".", ".", "PUNCT", [85, 86]]]], ["calgarske-listy_2003_unor_ocr.txt", "Z\u00e1kladn\u00ed hodnoty a p\u0159edstavy o \u017eivot\u011b se musej\u00ed shodovat.", [["Z\u00e1kladn\u00ed", "z\u00e1kladn\u00ed", "ADJ", [0, 8]], ["hodnoty", "hodnota", "NOUN", [9, 16]], ["a", "a", "CCONJ", [17, 18]], ["p\u0159edstavy", "p\u0159edstava", "NOUN", [19, 28]], ["o", "o", "ADP", [29, 30]], ["\u017eivot\u011b", "\u017eivot", "NOUN", [31, 37]], ["se", "se", "PRON", [38, 40]], ["musej\u00ed", "muset", "VERB", [41, 47]], ["shodovat", "shodovat", "VERB", [48, 56]], [".", ".", "PUNCT", [56, 57]]]], ["calgarske-listy_2003_unor_ocr.txt", "Rozd\u00edln\u00e9 n\u00e1zory na v\u00fdchovu d\u011bt\u00ed, hospoda\u0159en\u00ed s pen\u011bzi nebo zam\u011bstn\u00e1n\u00ed vztah pomalu ale jist\u011b ni\u010d\u00ed,\u201c \u0159\u00edk\u00e1 americk\u00e1 psycholo\u017eka Rhonda Pritchardov\u00e1.", [["Rozd\u00edln\u00e9", "rozd\u00edln\u00fd", "ADJ", [0, 8]], ["n\u00e1zory", "n\u00e1zor", "NOUN", [9, 15]], ["na", "na", "ADP", [16, 18]], ["v\u00fdchovu", "v\u00fdchova", "NOUN", [19, 26]], ["d\u011bt\u00ed", "d\u00edt\u011b", "NOUN", [27, 31]], [",", ",", "PUNCT", [31, 32]], ["hospoda\u0159en\u00ed", "hospoda\u0159en\u00ed", "NOUN", [33, 44]], ["s", "s", "ADP", [45, 46]], ["pen\u011bzi", "pen\u00edze", "NOUN", [47, 53]], ["nebo", "nebo", "CCONJ", [54, 58]], ["zam\u011bstn\u00e1n\u00ed", "zam\u011bstn\u00e1n\u00ed", "NOUN", [59, 69]], ["vztah", "vztah", "NOUN", [70, 75]], ["pomalu", "pomalu", "ADV", [76, 82]], ["ale", "ale", "CCONJ", [83, 86]], ["jist\u011b", "jist\u011b", "ADV", [87, 92]], ["ni\u010d\u00ed", "ni\u010dit", "VERB", [93, 97]], [",", ",", "PUNCT", [97, 98]], ["\u201c", "\"", "PUNCT", [98, 99]], ["\u0159\u00edk\u00e1", "\u0159\u00edkat", "VERB", [100, 104]], ["americk\u00e1", "americk\u00fd", "ADJ", [105, 113]], ["psycholo\u017eka", "psycholo\u017eka", "NOUN", [114, 125]], ["Rhonda", "Rhonda", "PROPN", [126, 132]], ["Pritchardov\u00e1", "Pritchardov\u00e1", "PROPN", [133, 145]], [".", ".", "PUNCT", [145, 146]]]], ["calgarske-listy_2003_unor_ocr.txt", "Ve vztahu se sice rozd\u00edly staraj\u00ed o rozmanitost, ale nesm\u011bj\u00ed b\u00fdt p\u0159\u00edli\u0161 velk\u00e9.", [["Ve", "v", "ADP", [0, 2]], ["vztahu", "vztah", "NOUN", [3, 9]], ["se", "se", "PRON", [10, 12]], ["sice", "sice", "CCONJ", [13, 17]], ["rozd\u00edly", "rozd\u00edl", "NOUN", [18, 25]], ["staraj\u00ed", "starat", "VERB", [26, 33]], ["o", "o", "ADP", [34, 35]], ["rozmanitost", "rozmanitost", "NOUN", [36, 47]], [",", ",", "PUNCT", [47, 48]], ["ale", "ale", "CCONJ", [49, 52]], ["nesm\u011bj\u00ed", "sm\u011bt", "VERB", [53, 60]], ["b\u00fdt", "b\u00fdt", "AUX", [61, 64]], ["p\u0159\u00edli\u0161", "p\u0159\u00edli\u0161", "ADV", [65, 71]], ["velk\u00e9", "velk\u00fd", "ADJ", [72, 77]], [".", ".", "PUNCT", [77, 78]]]], ["calgarske-listy_2003_unor_ocr.txt", "N\u00e1rodnost, soci\u00e1ln\u00ed p\u016fvod, vzd\u011bl\u00e1ni, v\u011bkov\u00fd rozd\u00edl a sv\u011btov\u00fd n\u00e1zor by nem\u011bly b\u00fdt p\u0159\u00edli\u0161 odli\u0161n\u00e9.", [["N\u00e1rodnost", "n\u00e1rodnost", "NOUN", [0, 9]], [",", ",", "PUNCT", [9, 10]], ["soci\u00e1ln\u00ed", "soci\u00e1ln\u00ed", "ADJ", [11, 19]], ["p\u016fvod", "p\u016fvod", "NOUN", [20, 25]], [",", ",", "PUNCT", [25, 26]], ["vzd\u011bl\u00e1ni", "vzd\u011blan\u00fd", "ADJ", [27, 35]], [",", ",", "PUNCT", [35, 36]], ["v\u011bkov\u00fd", "v\u011bkov\u00fd", "ADJ", [37, 43]], ["rozd\u00edl", "rozd\u00edl", "NOUN", [44, 50]], ["a", "a", "CCONJ", [51, 52]], ["sv\u011btov\u00fd", "sv\u011btov\u00fd", "ADJ", [53, 60]], ["n\u00e1zor", "n\u00e1zor", "NOUN", [61, 66]], ["by", "b\u00fdt", "AUX", [67, 69]], ["nem\u011bly", "m\u00edt", "VERB", [70, 76]], ["b\u00fdt", "b\u00fdt", "AUX", [77, 80]], ["p\u0159\u00edli\u0161", "p\u0159\u00edli\u0161", "ADV", [81, 87]], ["odli\u0161n\u00e9", "odli\u0161n\u00fd", "ADJ", [88, 95]], [".", ".", "PUNCT", [95, 96]]]], ["calgarske-listy_2003_unor_ocr.txt", "\u0160\u0165astn\u00e9 p\u00e1ry jsou schopny zvl\u00e1dnout men\u0161\u00ed odli\u0161nosti ve zvyc\u00edch a \u017eivotn\u00edm stylu, nebo\u0165 v z\u00e1sadn\u00edch ot\u00e1zk\u00e1ch jsou zajedno.", [["\u0160\u0165astn\u00e9", "\u0161\u0165astn\u00fd", "ADJ", [0, 7]], ["p\u00e1ry", "p\u00e1r", "NOUN", [8, 12]], ["jsou", "b\u00fdt", "AUX", [13, 17]], ["schopny", "schopn\u00fd", "ADJ", [18, 25]], ["zvl\u00e1dnout", "zvl\u00e1dnout", "VERB", [26, 35]], ["men\u0161\u00ed", "mal\u00fd", "ADJ", [36, 41]], ["odli\u0161nosti", "odli\u0161nost", "NOUN", [42, 52]], ["ve", "v", "ADP", [53, 55]], ["zvyc\u00edch", "zvyk", "NOUN", [56, 63]], ["a", "a", "CCONJ", [64, 65]], ["\u017eivotn\u00edm", "\u017eivotn\u00ed", "ADJ", [66, 74]], ["stylu", "styl", "NOUN", [75, 80]], [",", ",", "PUNCT", [80, 81]], ["nebo\u0165", "nebo\u0165", "CCONJ", [82, 87]], ["v", "v", "ADP", [88, 89]], ["z\u00e1sadn\u00edch", "z\u00e1sadn\u00ed", "ADJ", [90, 99]], ["ot\u00e1zk\u00e1ch", "ot\u00e1zka", "NOUN", [100, 108]], ["jsou", "b\u00fdt", "AUX", [109, 113]], ["zajedno", "zajedno", "ADJ", [114, 121]], [".", ".", "PUNCT", [121, 122]]]], ["calgarske-listy_2003_unor_ocr.txt", "V tomto p\u0159\u00edpad\u011b l\u00e1ska znamen\u00e1 schopnost uzav\u0159\u00edt kompromis a zanechat pokus\u016f vychovat toho druh\u00e9ho k obrazu sv\u00e9mu.", [["V", "v", "ADP", [0, 1]], ["tomto", "tento", "DET", [2, 7]], ["p\u0159\u00edpad\u011b", "p\u0159\u00edpad", "NOUN", [8, 15]], ["l\u00e1ska", "l\u00e1ska", "NOUN", [16, 21]], ["znamen\u00e1", "znamenat", "VERB", [22, 29]], ["schopnost", "schopnost", "NOUN", [30, 39]], ["uzav\u0159\u00edt", "uzav\u0159\u00edt", "VERB", [40, 47]], ["kompromis", "kompromis", "NOUN", [48, 57]], ["a", "a", "CCONJ", [58, 59]], ["zanechat", "zanechat", "VERB", [60, 68]], ["pokus\u016f", "pokus", "NOUN", [69, 75]], ["vychovat", "vychovat", "VERB", [76, 84]], ["toho", "ten", "DET", [85, 89]], ["druh\u00e9ho", "druh\u00fd", "ADJ", [90, 97]], ["k", "k", "ADP", [98, 99]], ["obrazu", "obraz", "NOUN", [100, 106]], ["sv\u00e9mu", "sv\u016fj", "DET", [107, 112]], [".", ".", "PUNCT", [112, 113]]]], ["calgarske-listy_2003_unor_ocr.txt", "P\u00e1r nemus\u00ed spole\u010dn\u011b sd\u00edlet v\u0161echny n\u00e1zory, aby byl \u0161\u0165astn\u00fd.", [["P\u00e1r", "p\u00e1r", "NOUN", [0, 3]], ["nemus\u00ed", "muset", "VERB", [4, 10]], ["spole\u010dn\u011b", "spole\u010dn\u011b", "ADV", [11, 19]], ["sd\u00edlet", "sd\u00edlet", "VERB", [20, 26]], ["v\u0161echny", "v\u0161echen", "DET", [27, 34]], ["n\u00e1zory", "n\u00e1zor", "NOUN", [35, 41]], [",", ",", "PUNCT", [41, 42]], ["aby", "aby", "SCONJ", [-34369, -34369]], ["by", "b\u00fdt", "AUX", [-34369, -34369]], ["byl", "b\u00fdt", "AUX", [47, 50]], ["\u0161\u0165astn\u00fd", "\u0161\u0165astn\u00fd", "ADJ", [51, 58]], [".", ".", "PUNCT", [58, 59]]]], ["calgarske-listy_2003_unor_ocr.txt", "Pr\u00e1v\u011b naopak: pokud existuje jednota v z\u00e1kladn\u00edch principech, mal\u00e9 rozd\u00edly jsou z\u00e1bavn\u00e9 a staraj\u00ed se o zpest\u0159eni oby\u010dejn\u00e9ho v\u0161edn\u00edho dne.", [["Pr\u00e1v\u011b", "pr\u00e1v\u011b", "ADV", [0, 5]], ["naopak", "naopak", "ADV", [6, 12]], [":", ":", "PUNCT", [12, 13]], ["pokud", "pokud", "SCONJ", [14, 19]], ["existuje", "existovat", "VERB", [20, 28]], ["jednota", "jednota", "NOUN", [29, 36]], ["v", "v", "ADP", [37, 38]], ["z\u00e1kladn\u00edch", "z\u00e1kladn\u00ed", "ADJ", [39, 49]], ["principech", "princip", "NOUN", [50, 60]], [",", ",", "PUNCT", [60, 61]], ["mal\u00e9", "mal\u00fd", "ADJ", [62, 66]], ["rozd\u00edly", "rozd\u00edl", "NOUN", [67, 74]], ["jsou", "b\u00fdt", "AUX", [75, 79]], ["z\u00e1bavn\u00e9", "z\u00e1bavn\u00fd", "ADJ", [80, 87]], ["a", "a", "CCONJ", [88, 89]], ["staraj\u00ed", "starat", "VERB", [90, 97]], ["se", "se", "PRON", [98, 100]], ["o", "o", "ADP", [101, 102]], ["zpest\u0159eni", "zpest\u0159en\u00fd", "ADJ", [103, 112]], ["oby\u010dejn\u00e9ho", "oby\u010dejn\u00fd", "ADJ", [113, 123]], ["v\u0161edn\u00edho", "v\u0161edn\u00ed", "ADJ", [124, 132]], ["dne", "den", "NOUN", [133, 136]], [".", ".", "PUNCT", [136, 137]]]], ["calgarske-listy_2003_unor_ocr.txt", "Krom\u011b tohoto v\u0161eobecn\u00e9ho p\u0159edpokladu existuj\u00ed je\u0161t\u011b tzv. recepty na \u0161t\u011bst\u00ed.", [["Krom\u011b", "krom\u011b", "ADP", [0, 5]], ["tohoto", "tento", "DET", [6, 12]], ["v\u0161eobecn\u00e9ho", "v\u0161eobecn\u00fd", "ADJ", [13, 24]], ["p\u0159edpokladu", "p\u0159edpoklad", "NOUN", [25, 36]], ["existuj\u00ed", "existovat", "VERB", [37, 45]], ["je\u0161t\u011b", "je\u0161t\u011b", "ADV", [46, 51]], ["tzv", "takzvan\u00fd", "ADJ", [52, 55]], [".", ".", "PUNCT", [55, 56]], ["recepty", "recept", "NOUN", [57, 64]], ["na", "na", "ADP", [65, 67]], ["\u0161t\u011bst\u00ed", "\u0161t\u011bst\u00ed", "NOUN", [68, 74]], [".", ".", "PUNCT", [74, 75]]]], ["calgarske-listy_2003_unor_ocr.txt", "Jak zjistili psychologov\u00e9, spokojen\u00e9 p\u00e1ry tyto recepty pou\u017e\u00edvaj\u00ed v\u011bt\u0161inou zcela intuitivn\u011b.", [["Jak", "jak", "ADV", [0, 3]], ["zjistili", "zjistit", "VERB", [4, 12]], ["psychologov\u00e9", "psycholog", "NOUN", [13, 25]], [",", ",", "PUNCT", [25, 26]], ["spokojen\u00e9", "spokojen\u00fd", "ADJ", [27, 36]], ["p\u00e1ry", "p\u00e1r", "NOUN", [37, 41]], ["tyto", "tento", "DET", [42, 46]], ["recepty", "recept", "NOUN", [47, 54]], ["pou\u017e\u00edvaj\u00ed", "pou\u017e\u00edvat", "VERB", [55, 64]], ["v\u011bt\u0161inou", "v\u011bt\u0161inou", "ADV", [65, 73]], ["zcela", "zcela", "ADV", [74, 79]], ["intuitivn\u011b", "intuitivn\u011b", "ADV", [80, 90]], [".", ".", "PUNCT", [90, 91]]]], ["calgarske-listy_2003_unor_ocr.txt", "Rovnopr\u00e1vnost \u2014 mocensk\u00e9 z\u00e1pasy jsou tabu!", [["Rovnopr\u00e1vnost", "rovnopr\u00e1vnost", "NOUN", [0, 13]], ["\u2014", "\u2014", "PUNCT", [14, 15]], ["mocensk\u00e9", "mocensk\u00fd", "ADJ", [16, 24]], ["z\u00e1pasy", "z\u00e1pas", "NOUN", [25, 31]], ["jsou", "b\u00fdt", "AUX", [32, 36]], ["tabu", "tabu", "NOUN", [37, 41]], ["!", "!", "PUNCT", [41, 42]]]], ["calgarske-listy_2003_unor_ocr.txt", "Existuj\u00ed-li mezi partnery z\u00e1sadn\u00ed rozd\u00edly, zapl\u00e9taj\u00ed se oba \u010dasto do nep\u0159\u00edjemn\u00e9ho mocensk\u00e9ho z\u00e1pasu.", [["Existuj\u00ed", "existovat", "VERB", [0, 8]], ["-", "-", "PUNCT", [8, 9]], ["li", "li", "SCONJ", [9, 11]], ["mezi", "mezi", "ADP", [12, 16]], ["partnery", "partner", "NOUN", [17, 25]], ["z\u00e1sadn\u00ed", "z\u00e1sadn\u00ed", "ADJ", [26, 33]], ["rozd\u00edly", "rozd\u00edl", "NOUN", [34, 41]], [",", ",", "PUNCT", [41, 42]], ["zapl\u00e9taj\u00ed", "zapl\u00e9tat", "VERB", [43, 52]], ["se", "se", "PRON", [53, 55]], ["oba", "oba", "NUM", [56, 59]], ["\u010dasto", "\u010dasto", "ADV", [60, 65]], ["do", "do", "ADP", [66, 68]], ["nep\u0159\u00edjemn\u00e9ho", "p\u0159\u00edjemn\u00fd", "ADJ", [69, 81]], ["mocensk\u00e9ho", "mocensk\u00fd", "ADJ", [82, 92]], ["z\u00e1pasu", "z\u00e1pas", "NOUN", [93, 99]], [".", ".", "PUNCT", [99, 100]]]], ["calgarske-listy_2003_unor_ocr.txt", "P\u00e1ry v\u0161ak spolu \u017eij\u00ed nejv\u00edce harmonick\u00fdm \u017eivotem, kdy\u017e mezi nimi nen\u00ed \u017e\u00e1dn\u00fd v\u00edt\u011bz ani pora\u017een\u00fd.", [["P\u00e1ry", "p\u00e1r", "NOUN", [0, 4]], ["v\u0161ak", "v\u0161ak", "CCONJ", [5, 9]], ["spolu", "spolu", "ADV", [10, 15]], ["\u017eij\u00ed", "\u017e\u00edt", "VERB", [16, 20]], ["nejv\u00edce", "v\u00edce", "ADV", [21, 28]], ["harmonick\u00fdm", "harmonick\u00fd", "ADJ", [29, 40]], ["\u017eivotem", "\u017eivot", "NOUN", [41, 48]], [",", ",", "PUNCT", [48, 49]], ["kdy\u017e", "kdy\u017e", "SCONJ", [50, 54]], ["mezi", "mezi", "ADP", [55, 59]], ["nimi", "on", "PRON", [60, 64]], ["nen\u00ed", "b\u00fdt", "AUX", [65, 69]], ["\u017e\u00e1dn\u00fd", "\u017e\u00e1dn\u00fd", "DET", [70, 75]], ["v\u00edt\u011bz", "v\u00edt\u011bz", "NOUN", [76, 81]], ["ani", "ani", "CCONJ", [82, 85]], ["pora\u017een\u00fd", "pora\u017een\u00fd", "ADJ", [86, 94]], [".", ".", "PUNCT", [94, 95]]]], ["calgarske-listy_2003_unor_ocr.txt", "Samoz\u0159ejm\u011b \u017e\u00e1dn\u00fd p\u00e1r nen\u00ed v\u016f\u010di moci imunn\u00ed.", [["Samoz\u0159ejm\u011b", "samoz\u0159ejm\u011b", "ADV", [0, 10]], ["\u017e\u00e1dn\u00fd", "\u017e\u00e1dn\u00fd", "DET", [11, 16]], ["p\u00e1r", "p\u00e1r", "NOUN", [17, 20]], ["nen\u00ed", "b\u00fdt", "AUX", [21, 25]], ["v\u016f\u010di", "v\u016f\u010di", "ADP", [26, 30]], ["moci", "moc", "NOUN", [31, 35]], ["imunn\u00ed", "imunn\u00ed", "ADJ", [36, 42]], [".", ".", "PUNCT", [42, 43]]]], ["calgarske-listy_2003_unor_ocr.txt", "Rozhoduj\u00edc\u00ed je, zda jsou oba partne\u0159i ochotn\u00ed st\u0159\u00eddat se - jednou ustoup\u00ed on, podruh\u00e9 ona.", [["Rozhoduj\u00edc\u00ed", "rozhoduj\u00edc\u00ed", "ADJ", [0, 11]], ["je", "b\u00fdt", "AUX", [12, 14]], [",", ",", "PUNCT", [14, 15]], ["zda", "zda", "SCONJ", [16, 19]], ["jsou", "b\u00fdt", "AUX", [20, 24]], ["oba", "oba", "NUM", [25, 28]], ["partne\u0159i", "partner", "NOUN", [29, 37]], ["ochotn\u00ed", "ochotn\u00fd", "ADJ", [38, 45]], ["st\u0159\u00eddat", "st\u0159\u00eddat", "VERB", [46, 53]], ["se", "se", "PRON", [54, 56]], ["-", "-", "PUNCT", [57, 58]], ["jednou", "jednou", "ADV", [59, 65]], ["ustoup\u00ed", "ustoupit", "VERB", [66, 73]], ["on", "on", "PRON", [74, 76]], [",", ",", "PUNCT", [76, 77]], ["podruh\u00e9", "podruh\u00e9", "ADV", [78, 85]], ["ona", "on", "PRON", [86, 89]], [".", ".", "PUNCT", [89, 90]]]], ["calgarske-listy_2003_unor_ocr.txt", "L\u00e1ska pot\u0159ebuje prostor k r\u016fstu \u2014 P\u00e1ry \u017eij\u00ed spolu, ani\u017e by se v\u0161ak partne\u0159i vzdali vlastn\u00ed identity.", [["L\u00e1ska", "l\u00e1ska", "NOUN", [0, 5]], ["pot\u0159ebuje", "pot\u0159ebovat", "VERB", [6, 15]], ["prostor", "prostor", "NOUN", [16, 23]], ["k", "k", "ADP", [24, 25]], ["r\u016fstu", "r\u016fst", "NOUN", [26, 31]], ["\u2014", "\u2014", "PUNCT", [32, 33]], ["P\u00e1ry", "p\u00e1r", "NOUN", [34, 38]], ["\u017eij\u00ed", "\u017e\u00edt", "VERB", [39, 43]], ["spolu", "spolu", "ADV", [44, 49]], [",", ",", "PUNCT", [49, 50]], ["ani\u017e", "ani\u017e", "SCONJ", [51, 55]], ["by", "b\u00fdt", "AUX", [56, 58]], ["se", "se", "PRON", [59, 61]], ["v\u0161ak", "v\u0161ak", "CCONJ", [62, 66]], ["partne\u0159i", "partner", "NOUN", [67, 75]], ["vzdali", "vzd\u00e1t", "VERB", [76, 82]], ["vlastn\u00ed", "vlastn\u00ed", "ADJ", [83, 90]], ["identity", "identita", "NOUN", [91, 99]], [".", ".", "PUNCT", [99, 100]]]], ["calgarske-listy_2003_unor_ocr.txt", "\u010casto m\u00e1 ka\u017ed\u00fd v byt\u011b sv\u00e9 \u201ekr\u00e1lovstv\u00ed\u201c, kam se m\u016f\u017ee st\u00e1hnout do \u00fastran\u00ed.", [["\u010casto", "\u010dasto", "ADV", [0, 5]], ["m\u00e1", "m\u00edt", "VERB", [6, 8]], ["ka\u017ed\u00fd", "ka\u017ed\u00fd", "DET", [9, 14]], ["v", "v", "ADP", [15, 16]], ["byt\u011b", "byt", "NOUN", [17, 21]], ["sv\u00e9", "sv\u016fj", "DET", [22, 25]], ["\u201e", "\"", "PUNCT", [26, 27]], ["kr\u00e1lovstv\u00ed", "kr\u00e1lovstv\u00ed", "NOUN", [27, 37]], ["\u201c", "\"", "PUNCT", [37, 38]], [",", ",", "PUNCT", [38, 39]], ["kam", "kam", "ADV", [40, 43]], ["se", "se", "PRON", [44, 46]], ["m\u016f\u017ee", "moci", "VERB", [47, 51]], ["st\u00e1hnout", "st\u00e1hnout", "VERB", [52, 60]], ["do", "do", "ADP", [61, 63]], ["\u00fastran\u00ed", "\u00fastran\u00ed", "NOUN", [64, 71]], [".", ".", "PUNCT", [71, 72]]]], ["calgarske-listy_2003_unor_ocr.txt", "Ka\u017ed\u00fd si ponech\u00e1v\u00e1 sv\u00e9 kon\u00ed\u010dky a kamar\u00e1dy.", [["Ka\u017ed\u00fd", "ka\u017ed\u00fd", "DET", [0, 5]], ["si", "se", "PRON", [6, 8]], ["ponech\u00e1v\u00e1", "ponech\u00e1vat", "VERB", [9, 18]], ["sv\u00e9", "sv\u016fj", "DET", [19, 22]], ["kon\u00ed\u010dky", "kon\u00ed\u010dek", "NOUN", [23, 30]], ["a", "a", "CCONJ", [31, 32]], ["kamar\u00e1dy", "kamar\u00e1d", "NOUN", [33, 41]], [".", ".", "PUNCT", [41, 42]]]], ["calgarske-listy_2003_unor_ocr.txt", "Oba v\u0161ak tak\u00e9 spole\u010dn\u011b podnikaj\u00ed spoustu akc\u00ed.", [["Oba", "oba", "NUM", [0, 3]], ["v\u0161ak", "v\u0161ak", "CCONJ", [4, 8]], ["tak\u00e9", "tak\u00e9", "ADV", [9, 13]], ["spole\u010dn\u011b", "spole\u010dn\u011b", "ADV", [14, 22]], ["podnikaj\u00ed", "podnikat", "VERB", [23, 32]], ["spoustu", "spousta", "NOUN", [33, 40]], ["akc\u00ed", "akce", "NOUN", [41, 45]], [".", ".", "PUNCT", [45, 46]]]], ["calgarske-listy_2003_unor_ocr.txt", "Tak dos\u00e1hnou p\u00e1ry zdrav\u00e9 rovnov\u00e1hy mezi d\u00e1v\u00e1n\u00edm a p\u0159ij\u00edm\u00e1n\u00edm.", [["Tak", "tak", "ADV", [0, 3]], ["dos\u00e1hnou", "dos\u00e1hnout", "VERB", [4, 12]], ["p\u00e1ry", "p\u00e1r", "NOUN", [13, 17]], ["zdrav\u00e9", "zdrav\u00fd", "ADJ", [18, 24]], ["rovnov\u00e1hy", "rovnov\u00e1ha", "NOUN", [25, 34]], ["mezi", "mezi", "ADP", [35, 39]], ["d\u00e1v\u00e1n\u00edm", "d\u00e1v\u00e1n\u00ed", "NOUN", [40, 47]], ["a", "a", "CCONJ", [48, 49]], ["p\u0159ij\u00edm\u00e1n\u00edm", "p\u0159ij\u00edm\u00e1n\u00ed", "NOUN", [50, 60]], [".", ".", "PUNCT", [60, 61]]]], ["calgarske-listy_2003_unor_ocr.txt", "\u0160\u0165astn\u00e9 p\u00e1ry nal\u00e9zaj\u00ed rovnov\u00e1hu mezi samostatnost\u00ed a soudr\u017enost\u00ed.", [["\u0160\u0165astn\u00e9", "\u0161\u0165astn\u00fd", "ADJ", [0, 7]], ["p\u00e1ry", "p\u00e1r", "NOUN", [8, 12]], ["nal\u00e9zaj\u00ed", "nal\u00e9zat", "VERB", [13, 21]], ["rovnov\u00e1hu", "rovnov\u00e1ha", "NOUN", [22, 31]], ["mezi", "mezi", "ADP", [32, 36]], ["samostatnost\u00ed", "samostatnost", "NOUN", [37, 50]], ["a", "a", "CCONJ", [51, 52]], ["soudr\u017enost\u00ed", "soudr\u017enost", "NOUN", [53, 64]], [".", ".", "PUNCT", [64, 65]]]], ["calgarske-listy_2003_unor_ocr.txt", "Spole\u010dn\u00e9 pl\u00e1ny posiluj\u00ed soudr\u017enost \u2014", [["Spole\u010dn\u00e9", "spole\u010dn\u00fd", "ADJ", [0, 8]], ["pl\u00e1ny", "pl\u00e1n", "NOUN", [9, 14]], ["posiluj\u00ed", "posilovat", "VERB", [15, 23]], ["soudr\u017enost", "soudr\u017enost", "NOUN", [24, 34]], ["\u2014", "\u2014", "PUNCT", [35, 36]]]], ["calgarske-listy_2003_unor_ocr.txt", "P\u0159i v\u0161\u00ed autonomii mus\u00ed existovat siln\u00fd pocit soudr\u017enosti.", [["P\u0159i", "p\u0159i", "ADP", [0, 3]], ["v\u0161\u00ed", "v\u0161echen", "DET", [4, 7]], ["autonomii", "autonomie", "NOUN", [8, 17]], ["mus\u00ed", "muset", "VERB", [18, 22]], ["existovat", "existovat", "VERB", [23, 32]], ["siln\u00fd", "siln\u00fd", "ADJ", [33, 38]], ["pocit", "pocit", "NOUN", [39, 44]], ["soudr\u017enosti", "soudr\u017enost", "NOUN", [45, 56]], [".", ".", "PUNCT", [56, 57]]]], ["calgarske-listy_2003_unor_ocr.txt", "Motorem pro tento pocit jsou spole\u010dn\u00e9 pl\u00e1ny.", [["Motorem", "motor", "NOUN", [0, 7]], ["pro", "pro", "ADP", [8, 11]], ["tento", "tento", "DET", [12, 17]], ["pocit", "pocit", "NOUN", [18, 23]], ["jsou", "b\u00fdt", "AUX", [24, 28]], ["spole\u010dn\u00e9", "spole\u010dn\u00fd", "ADJ", [29, 37]], ["pl\u00e1ny", "pl\u00e1n", "NOUN", [38, 43]], [".", ".", "PUNCT", [43, 44]]]], ["calgarske-listy_2003_unor_ocr.txt", "Pl\u00e1ny spojuj\u00ed dohromady a ukazuj\u00ed, \u017ee spole\u010dn\u00fdmi silami lze p\u0159ekonat nejednu obt\u00ed\u017e.", [["Pl\u00e1ny", "pl\u00e1n", "NOUN", [0, 5]], ["spojuj\u00ed", "spojovat", "VERB", [6, 13]], ["dohromady", "dohromady", "ADV", [14, 23]], ["a", "a", "CCONJ", [24, 25]], ["ukazuj\u00ed", "ukazovat", "VERB", [26, 33]], [",", ",", "PUNCT", [33, 34]], ["\u017ee", "\u017ee", "SCONJ", [35, 37]], ["spole\u010dn\u00fdmi", "spole\u010dn\u00fd", "ADJ", [38, 48]], ["silami", "s\u00edla", "NOUN", [49, 55]], ["lze", "lze", "VERB", [56, 59]], ["p\u0159ekonat", "p\u0159ekonat", "VERB", [60, 68]], ["nejednu", "jedno", "ADJ", [69, 76]], ["obt\u00ed\u017e", "obt\u00ed\u017e", "NOUN", [77, 82]], [".", ".", "PUNCT", [82, 83]]]], ["calgarske-listy_2003_unor_ocr.txt", "Erotika odstra\u0148uje rozpory \u2014", [["Erotika", "erotika", "NOUN", [0, 7]], ["odstra\u0148uje", "odstra\u0148ovat", "VERB", [8, 18]], ["rozpory", "rozpor", "NOUN", [19, 26]], ["\u2014", "\u2014", "PUNCT", [27, 28]]]], ["calgarske-listy_2003_unor_ocr.txt", "I po letech hraje uspokojuj\u00edc\u00ed sexualita v\u00fdznamnou roli.", [["I", "i", "CCONJ", [0, 1]], ["po", "po", "ADP", [2, 4]], ["letech", "l\u00e9ta", "NOUN", [5, 11]], ["hraje", "hr\u00e1t", "VERB", [12, 17]], ["uspokojuj\u00edc\u00ed", "uspokojuj\u00edc\u00ed", "ADJ", [18, 30]], ["sexualita", "sexualita", "NOUN", [31, 40]], ["v\u00fdznamnou", "v\u00fdznamn\u00fd", "ADJ", [41, 50]], ["roli", "role", "NOUN", [51, 55]], [".", ".", "PUNCT", [55, 56]]]], ["calgarske-listy_2003_unor_ocr.txt", "V sexu se spojuje t\u011blo a du\u0161e, rozd\u00edly miz\u00ed.", [["V", "v", "ADP", [0, 1]], ["sexu", "sex", "NOUN", [2, 6]], ["se", "se", "PRON", [7, 9]], ["spojuje", "spojovat", "VERB", [10, 17]], ["t\u011blo", "t\u011blo", "NOUN", [18, 22]], ["a", "a", "CCONJ", [23, 24]], ["du\u0161e", "du\u0161e", "NOUN", [25, 29]], [",", ",", "PUNCT", [29, 30]], ["rozd\u00edly", "rozd\u00edl", "NOUN", [31, 38]], ["miz\u00ed", "mizet", "VERB", [39, 43]], [".", ".", "PUNCT", [43, 44]]]], ["calgarske-listy_2003_unor_ocr.txt", "Dobr\u00fd sex je potvrzen\u00ed p\u00e1ru jako jednoty.", [["Dobr\u00fd", "dobr\u00fd", "ADJ", [0, 5]], ["sex", "sex", "NOUN", [6, 9]], ["je", "b\u00fdt", "AUX", [10, 12]], ["potvrzen\u00ed", "potvrzen\u00ed", "NOUN", [13, 22]], ["p\u00e1ru", "p\u00e1r", "NOUN", [23, 27]], ["jako", "jako", "SCONJ", [28, 32]], ["jednoty", "jednota", "NOUN", [33, 40]], [".", ".", "PUNCT", [40, 41]]]], ["calgarske-listy_2003_unor_ocr.txt", "Milostn\u00e9 ritu\u00e1ly proti b\u011bhu v\u0161edn\u00edho dne \u2014 Mnoh\u00e9 p\u00e1ry ka\u017ed\u00fd ve\u010der us\u00ednaj\u00ed v objet\u00ed, nebo se dr\u017e\u00ed za ruce.", [["Milostn\u00e9", "milostn\u00fd", "ADJ", [0, 8]], ["ritu\u00e1ly", "ritu\u00e1l", "NOUN", [9, 16]], ["proti", "proti", "ADP", [17, 22]], ["b\u011bhu", "b\u011bh", "NOUN", [23, 27]], ["v\u0161edn\u00edho", "v\u0161edn\u00ed", "ADJ", [28, 36]], ["dne", "den", "NOUN", [37, 40]], ["\u2014", "\u2014", "PUNCT", [41, 42]], ["Mnoh\u00e9", "mnoh\u00fd", "ADJ", [43, 48]], ["p\u00e1ry", "p\u00e1r", "NOUN", [49, 53]], ["ka\u017ed\u00fd", "ka\u017ed\u00fd", "DET", [54, 59]], ["ve\u010der", "ve\u010der", "ADV", [60, 65]], ["us\u00ednaj\u00ed", "us\u00ednat", "VERB", [66, 73]], ["v", "v", "ADP", [74, 75]], ["objet\u00ed", "objet\u00ed", "NOUN", [76, 82]], [",", ",", "PUNCT", [82, 83]], ["nebo", "nebo", "CCONJ", [84, 88]], ["se", "se", "PRON", [89, 91]], ["dr\u017e\u00ed", "dr\u017eet", "VERB", [92, 96]], ["za", "za", "ADP", [97, 99]], ["ruce", "ruka", "NOUN", [100, 104]], [".", ".", "PUNCT", [104, 105]]]], ["calgarske-listy_2003_unor_ocr.txt", "Jin\u00ed si zase p\u00ed\u0161\u00ed mal\u00e1 milostn\u00e1 psan\u00ed\u010dka \u010di pozdravy.", [["Jin\u00ed", "jin\u00fd", "ADJ", [0, 4]], ["si", "se", "PRON", [5, 7]], ["zase", "zase", "ADV", [8, 12]], ["p\u00ed\u0161\u00ed", "ps\u00e1t", "VERB", [13, 17]], ["mal\u00e1", "mal\u00fd", "ADJ", [18, 22]], ["milostn\u00e1", "milostn\u00fd", "ADJ", [23, 31]], ["psan\u00ed\u010dka", "psan\u00ed\u010dek", "NOUN", [32, 40]], ["\u010di", "\u010di", "CCONJ", [41, 43]], ["pozdravy", "pozdrav", "NOUN", [44, 52]], [".", ".", "PUNCT", [52, 53]]]], ["calgarske-listy_2003_unor_ocr.txt", "Takov\u00fdmi mal\u00fdmi gesty si \u0161\u0165astn\u00e9 p\u00e1ry potvrzuj\u00ed, \u017ee pat\u0159\u00ed k sob\u011b.", [["Takov\u00fdmi", "takov\u00fd", "DET", [0, 8]], ["mal\u00fdmi", "mal\u00fd", "ADJ", [9, 15]], ["gesty", "gesta", "NOUN", [16, 21]], ["si", "se", "PRON", [22, 24]], ["\u0161\u0165astn\u00e9", "\u0161\u0165astn\u00fd", "ADJ", [25, 32]], ["p\u00e1ry", "p\u00e1r", "NOUN", [33, 37]], ["potvrzuj\u00ed", "potvrzovat", "VERB", [38, 47]], [",", ",", "PUNCT", [47, 48]], ["\u017ee", "\u017ee", "SCONJ", [49, 51]], ["pat\u0159\u00ed", "pat\u0159it", "VERB", [52, 57]], ["k", "k", "ADP", [58, 59]], ["sob\u011b", "se", "PRON", [60, 64]], [".", ".", "PUNCT", [64, 65]]]], ["calgarske-listy_2003_unor_ocr.txt", "Soudr\u017enost \u2014 \u0160\u0165astn\u00e9 p\u00e1ry, kter\u00e9 spolu \u017eij\u00ed ji\u017e dlouhou dobu, jsou mist\u0159i v soudr\u017enosti, zejm\u00e9na v obdob\u00ed n\u011bjak\u00e9 krize.", [["Soudr\u017enost", "soudr\u017enost", "NOUN", [0, 10]], ["\u2014", "\u2014", "PUNCT", [11, 12]], ["\u0160\u0165astn\u00e9", "\u0161\u0165astn\u00fd", "ADJ", [13, 20]], ["p\u00e1ry", "p\u00e1r", "NOUN", [21, 25]], [",", ",", "PUNCT", [25, 26]], ["kter\u00e9", "kter\u00fd", "DET", [27, 32]], ["spolu", "spolu", "ADV", [33, 38]], ["\u017eij\u00ed", "\u017e\u00edt", "VERB", [39, 43]], ["ji\u017e", "ji\u017e", "ADV", [44, 47]], ["dlouhou", "dlouh\u00fd", "ADJ", [48, 55]], ["dobu", "doba", "NOUN", [56, 60]], [",", ",", "PUNCT", [60, 61]], ["jsou", "b\u00fdt", "AUX", [62, 66]], ["mist\u0159i", "mistr", "NOUN", [67, 73]], ["v", "v", "ADP", [74, 75]], ["soudr\u017enosti", "soudr\u017enost", "NOUN", [76, 87]], [",", ",", "PUNCT", [87, 88]], ["zejm\u00e9na", "zejm\u00e9na", "PART", [89, 96]], ["v", "v", "ADP", [97, 98]], ["obdob\u00ed", "obdob\u00ed", "NOUN", [99, 105]], ["n\u011bjak\u00e9", "n\u011bjak\u00fd", "DET", [106, 112]], ["krize", "krize", "NOUN", [113, 118]], [".", ".", "PUNCT", [118, 119]]]], ["calgarske-listy_2003_unor_ocr.txt", "Partne\u0159i si jsou t\u011bmi nejd\u016fle\u017eit\u011bj\u0161\u00edmi lidmi na sv\u011bt\u011b a vz\u00e1jemn\u011b se podporuj\u00ed.", [["Partne\u0159i", "partner", "NOUN", [0, 8]], ["si", "se", "PRON", [9, 11]], ["jsou", "b\u00fdt", "AUX", [12, 16]], ["t\u011bmi", "ten", "DET", [17, 21]], ["nejd\u016fle\u017eit\u011bj\u0161\u00edmi", "d\u016fle\u017eit\u00fd", "ADJ", [22, 38]], ["lidmi", "lid\u00e9", "NOUN", [39, 44]], ["na", "na", "ADP", [45, 47]], ["sv\u011bt\u011b", "sv\u011bt", "NOUN", [48, 53]], ["a", "a", "CCONJ", [54, 55]], ["vz\u00e1jemn\u011b", "vz\u00e1jemn\u011b", "ADV", [56, 64]], ["se", "se", "PRON", [65, 67]], ["podporuj\u00ed", "podporovat", "VERB", [68, 77]], [".", ".", "PUNCT", [77, 78]]]], ["calgarske-listy_2003_unor_ocr.txt", "Partnerovy probl\u00e9my berou v\u00e1\u017en\u011b a spole\u010dn\u011b pracuj\u00ed na jejich \u0159e\u0161en\u00ed.", [["Partnerovy", "Partner\u016fv", "ADJ", [0, 10]], ["probl\u00e9my", "probl\u00e9m", "NOUN", [11, 19]], ["berou", "br\u00e1t", "VERB", [20, 25]], ["v\u00e1\u017en\u011b", "v\u00e1\u017en\u011b", "ADV", [26, 31]], ["a", "a", "CCONJ", [32, 33]], ["spole\u010dn\u011b", "spole\u010dn\u011b", "ADV", [34, 42]], ["pracuj\u00ed", "pracovat", "VERB", [43, 50]], ["na", "na", "ADP", [51, 53]], ["jejich", "jeho", "DET", [54, 60]], ["\u0159e\u0161en\u00ed", "\u0159e\u0161en\u00ed", "NOUN", [61, 67]], [".", ".", "PUNCT", [67, 68]]]], ["calgarske-listy_2003_unor_ocr.txt", "F\u00e9rov\u011b veden\u00e9 spory udr\u017euj\u00ed partnerstv\u00ed - Mnoh\u00e9 nap\u011bt\u00ed vy\u0159e\u0161\u00ed jen po\u0159\u00e1dn\u00e1 h\u00e1dka: konflikty jsou v partnerstv\u00ed nevyhnuteln\u00e9 jako bou\u0159ky v l\u00e9t\u011b.", [["F\u00e9rov\u011b", "f\u00e9rov\u011b", "ADV", [0, 6]], ["veden\u00e9", "veden\u00fd", "ADJ", [7, 13]], ["spory", "spor", "NOUN", [14, 19]], ["udr\u017euj\u00ed", "udr\u017eovat", "VERB", [20, 27]], ["partnerstv\u00ed", "partnerstv\u00ed", "NOUN", [28, 39]], ["-", "-", "PUNCT", [40, 41]], ["Mnoh\u00e9", "mnoh\u00fd", "ADJ", [42, 47]], ["nap\u011bt\u00ed", "nap\u011bt\u00ed", "NOUN", [48, 54]], ["vy\u0159e\u0161\u00ed", "vy\u0159e\u0161it", "VERB", [55, 61]], ["jen", "jen", "PART", [62, 65]], ["po\u0159\u00e1dn\u00e1", "po\u0159\u00e1dn\u00fd", "ADJ", [66, 73]], ["h\u00e1dka", "h\u00e1dka", "NOUN", [74, 79]], [":", ":", "PUNCT", [79, 80]], ["konflikty", "konflikt", "NOUN", [81, 90]], ["jsou", "b\u00fdt", "AUX", [91, 95]], ["v", "v", "ADP", [96, 97]], ["partnerstv\u00ed", "partnerstv\u00ed", "NOUN", [98, 109]], ["nevyhnuteln\u00e9", "vyhnuteln\u00fd", "ADJ", [110, 122]], ["jako", "jako", "SCONJ", [123, 127]], ["bou\u0159ky", "bou\u0159ka", "NOUN", [128, 134]], ["v", "v", "ADP", [135, 136]], ["l\u00e9t\u011b", "l\u00e9to", "NOUN", [137, 141]], [".", ".", "PUNCT", [141, 142]]]], ["calgarske-listy_2003_unor_ocr.txt", "Spor ohro\u017euje vztah jen v p\u0159\u00edpad\u011b, kdy\u017e kon\u010d\u00ed mocensk\u00fdm bojem a p\u0159i\u0159knut\u00edm viny.", [["Spor", "spor", "NOUN", [0, 4]], ["ohro\u017euje", "ohro\u017eovat", "VERB", [5, 13]], ["vztah", "vztah", "NOUN", [14, 19]], ["jen", "jen", "PART", [20, 23]], ["v", "v", "ADP", [24, 25]], ["p\u0159\u00edpad\u011b", "p\u0159\u00edpad", "NOUN", [26, 33]], [",", ",", "PUNCT", [33, 34]], ["kdy\u017e", "kdy\u017e", "SCONJ", [35, 39]], ["kon\u010d\u00ed", "kon\u010dit", "VERB", [40, 45]], ["mocensk\u00fdm", "mocensk\u00fd", "ADJ", [46, 55]], ["bojem", "boj", "NOUN", [56, 61]], ["a", "a", "CCONJ", [62, 63]], ["p\u0159i\u0159knut\u00edm", "p\u0159i\u0159knut\u00ed", "NOUN", [64, 74]], ["viny", "vina", "NOUN", [75, 79]], [".", ".", "PUNCT", [79, 80]]]], ["calgarske-listy_2003_unor_ocr.txt", "Dva lid\u00e9 nemus\u00ed b\u00fdt t\u00e9ho\u017e n\u00e1zoru, ale m\u011bli by um\u011bt f\u00e9rov\u011b diskutovat.", [["Dva", "dva", "NUM", [0, 3]], ["lid\u00e9", "lid\u00e9", "NOUN", [4, 8]], ["nemus\u00ed", "muset", "VERB", [9, 15]], ["b\u00fdt", "b\u00fdt", "AUX", [16, 19]], ["t\u00e9ho\u017e", "t\u00fd\u017e", "DET", [20, 25]], ["n\u00e1zoru", "n\u00e1zor", "NOUN", [26, 32]], [",", ",", "PUNCT", [32, 33]], ["ale", "ale", "CCONJ", [34, 37]], ["m\u011bli", "m\u00edt", "VERB", [38, 42]], ["by", "b\u00fdt", "AUX", [43, 45]], ["um\u011bt", "um\u011bt", "VERB", [46, 50]], ["f\u00e9rov\u011b", "f\u00e9rov\u011b", "ADV", [51, 57]], ["diskutovat", "diskutovat", "VERB", [58, 68]], [".", ".", "PUNCT", [68, 69]]]], ["calgarske-listy_2003_unor_ocr.txt", "Tato schopnost pat\u0159\u00ed podle jedn\u00e9 ankety v USA k deseti nejd\u016fle\u017eit\u011bj\u0161\u00edm vlastnostem \u0161\u0165astn\u00e9ho man\u017eelstv\u00ed.", [["Tato", "tento", "DET", [0, 4]], ["schopnost", "schopnost", "NOUN", [5, 14]], ["pat\u0159\u00ed", "pat\u0159it", "VERB", [15, 20]], ["podle", "podle", "ADP", [21, 26]], ["jedn\u00e9", "jeden", "NUM", [27, 32]], ["ankety", "anketa", "NOUN", [33, 39]], ["v", "v", "ADP", [40, 41]], ["USA", "USA", "PROPN", [42, 45]], ["k", "k", "ADP", [46, 47]], ["deseti", "deset", "NUM", [48, 54]], ["nejd\u016fle\u017eit\u011bj\u0161\u00edm", "d\u016fle\u017eit\u00fd", "ADJ", [55, 70]], ["vlastnostem", "vlastnost", "NOUN", [71, 82]], ["\u0161\u0165astn\u00e9ho", "\u0161\u0165astn\u00fd", "ADJ", [83, 92]], ["man\u017eelstv\u00ed", "man\u017eelstv\u00ed", "NOUN", [93, 103]], [".", ".", "PUNCT", [103, 104]]]], ["calgarske-listy_2003_unor_ocr.txt", "Spory se nevy\u0159e\u0161\u00ed samy od sebe.", [["Spory", "spor", "NOUN", [0, 5]], ["se", "se", "PRON", [6, 8]], ["nevy\u0159e\u0161\u00ed", "vy\u0159e\u0161it", "VERB", [9, 17]], ["samy", "sam\u00fd", "DET", [18, 22]], ["od", "od", "ADP", [23, 25]], ["sebe", "se", "PRON", [26, 30]], [".", ".", "PUNCT", [30, 31]]]], ["calgarske-listy_2003_unor_ocr.txt", "Pokud se jeden z partneni nebo dokonce oba vyh\u00fdbaj\u00ed probl\u00e9m\u016fm, nap\u011bt\u00ed se vyhrot\u00ed ve velmi z\u00e1va\u017en\u00fd st\u0159et, kter\u00fd tak\u00e9 nemusej\u00ed partne\u0159i v\u017edy ust\u00e1t.", [["Pokud", "pokud", "SCONJ", [0, 5]], ["se", "se", "PRON", [6, 8]], ["jeden", "jeden", "NUM", [9, 14]], ["z", "z", "ADP", [15, 16]], ["partneni", "partne\u0148", "NOUN", [17, 25]], ["nebo", "nebo", "CCONJ", [26, 30]], ["dokonce", "dokonce", "ADV", [31, 38]], ["oba", "oba", "NUM", [39, 42]], ["vyh\u00fdbaj\u00ed", "vyh\u00fdbat", "VERB", [43, 51]], ["probl\u00e9m\u016fm", "probl\u00e9m", "NOUN", [52, 61]], [",", ",", "PUNCT", [61, 62]], ["nap\u011bt\u00ed", "nap\u011bt\u00ed", "NOUN", [63, 69]], ["se", "se", "PRON", [70, 72]], ["vyhrot\u00ed", "vyhrotit", "VERB", [73, 80]], ["ve", "v", "ADP", [81, 83]], ["velmi", "velmi", "ADV", [84, 89]], ["z\u00e1va\u017en\u00fd", "z\u00e1va\u017en\u00fd", "ADJ", [90, 97]], ["st\u0159et", "st\u0159et", "NOUN", [98, 103]], [",", ",", "PUNCT", [103, 104]], ["kter\u00fd", "kter\u00fd", "DET", [105, 110]], ["tak\u00e9", "tak\u00e9", "ADV", [111, 115]], ["nemusej\u00ed", "muset", "VERB", [116, 124]], ["partne\u0159i", "partner", "NOUN", [125, 133]], ["v\u017edy", "v\u017edy", "ADV", [134, 138]], ["ust\u00e1t", "ust\u00e1t", "VERB", [139, 144]], [".", ".", "PUNCT", [144, 145]]]], ["calgarske-listy_2003_unor_ocr.txt", "Spor v\u0161ak tak\u00e9 nab\u00edz\u00ed novou \u0161anci.", [["Spor", "spor", "NOUN", [0, 4]], ["v\u0161ak", "v\u0161ak", "CCONJ", [5, 9]], ["tak\u00e9", "tak\u00e9", "ADV", [10, 14]], ["nab\u00edz\u00ed", "nab\u00edzet", "VERB", [15, 21]], ["novou", "nov\u00fd", "ADJ", [22, 27]], ["\u0161anci", "\u0161ance", "NOUN", [28, 33]], [".", ".", "PUNCT", [33, 34]]]], ["calgarske-listy_2003_unor_ocr.txt", "\u010casto je jedinou p\u0159\u00edle\u017eitost\u00ed, jak vy\u0159e\u0161it dlouhotrvaj\u00edc\u00ed bolestn\u00fd probl\u00e9m.", [["\u010casto", "\u010dasto", "ADV", [0, 5]], ["je", "b\u00fdt", "AUX", [6, 8]], ["jedinou", "jedin\u00fd", "ADJ", [9, 16]], ["p\u0159\u00edle\u017eitost\u00ed", "p\u0159\u00edle\u017eitost", "NOUN", [17, 29]], [",", ",", "PUNCT", [29, 30]], ["jak", "jak", "ADV", [31, 34]], ["vy\u0159e\u0161it", "vy\u0159e\u0161it", "VERB", [35, 42]], ["dlouhotrvaj\u00edc\u00ed", "dlouhotrvaj\u00edc\u00ed", "ADJ", [43, 57]], ["bolestn\u00fd", "bolestn\u00fd", "ADJ", [58, 66]], ["probl\u00e9m", "probl\u00e9m", "NOUN", [67, 74]], [".", ".", "PUNCT", [74, 75]]]], ["calgarske-listy_2003_unor_ocr.txt", "Spor \u010dasto vznik\u00e1 kv\u016fli mali\u010dkostem jako t\u0159eba vysok\u00e9mu telefonn\u00edmu \u00fa\u010dtu, pozdn\u00edmu p\u0159\u00edchodu z pr\u00e1ce, barv\u011b koberce.", [["Spor", "spor", "NOUN", [0, 4]], ["\u010dasto", "\u010dasto", "ADV", [5, 10]], ["vznik\u00e1", "vznikat", "VERB", [11, 17]], ["kv\u016fli", "kv\u016fli", "ADP", [18, 23]], ["mali\u010dkostem", "mali\u010dkost", "NOUN", [24, 35]], ["jako", "jako", "SCONJ", [36, 40]], ["t\u0159eba", "t\u0159eba", "ADV", [41, 46]], ["vysok\u00e9mu", "vysok\u00fd", "ADJ", [47, 55]], ["telefonn\u00edmu", "telefonn\u00ed", "ADJ", [56, 67]], ["\u00fa\u010dtu", "\u00fa\u010det", "NOUN", [68, 72]], [",", ",", "PUNCT", [72, 73]], ["pozdn\u00edmu", "pozdn\u00ed", "ADJ", [74, 82]], ["p\u0159\u00edchodu", "p\u0159\u00edchod", "NOUN", [83, 91]], ["z", "z", "ADP", [92, 93]], ["pr\u00e1ce", "pr\u00e1ce", "NOUN", [94, 99]], [",", ",", "PUNCT", [99, 100]], ["barv\u011b", "barva", "NOUN", [101, 106]], ["koberce", "koberec", "NOUN", [107, 114]], [".", ".", "PUNCT", [114, 115]]]], ["calgarske-listy_2003_unor_ocr.txt", "Ve skute\u010dnosti jde o to, \u017ee partne\u0159i maj\u00ed pocit nenapln\u011bn\u00ed sv\u00fdch p\u0159\u00e1n\u00ed a pot\u0159eb.", [["Ve", "v", "ADP", [0, 2]], ["skute\u010dnosti", "skute\u010dnost", "NOUN", [3, 14]], ["jde", "j\u00edt", "VERB", [15, 18]], ["o", "o", "ADP", [19, 20]], ["to", "ten", "DET", [21, 23]], [",", ",", "PUNCT", [23, 24]], ["\u017ee", "\u017ee", "SCONJ", [25, 27]], ["partne\u0159i", "partner", "NOUN", [28, 36]], ["maj\u00ed", "m\u00edt", "VERB", [37, 41]], ["pocit", "pocit", "NOUN", [42, 47]], ["nenapln\u011bn\u00ed", "nenapln\u011bn\u00ed", "NOUN", [48, 58]], ["sv\u00fdch", "sv\u016fj", "DET", [59, 64]], ["p\u0159\u00e1n\u00ed", "p\u0159\u00e1n\u00ed", "NOUN", [65, 70]], ["a", "a", "CCONJ", [71, 72]], ["pot\u0159eb", "pot\u0159eba", "NOUN", [73, 79]], [".", ".", "PUNCT", [79, 80]]]], ["calgarske-listy_2003_unor_ocr.txt", "Jde o \u010dastou chybu: o sv\u00fdch p\u0159\u00e1n\u00edch a tu\u017eb\u00e1ch v\u016fbec nemluv\u00edme, a chceme, aby na n\u011b p\u0159i\u0161el partner s\u00e1m.", [["Jde", "j\u00edt", "VERB", [0, 3]], ["o", "o", "ADP", [4, 5]], ["\u010dastou", "\u010dast\u00fd", "ADJ", [6, 12]], ["chybu", "chyba", "NOUN", [13, 18]], [":", ":", "PUNCT", [18, 19]], ["o", "o", "ADP", [20, 21]], ["sv\u00fdch", "sv\u016fj", "DET", [22, 27]], ["p\u0159\u00e1n\u00edch", "p\u0159\u00e1n\u00ed", "NOUN", [28, 35]], ["a", "a", "CCONJ", [36, 37]], ["tu\u017eb\u00e1ch", "tu\u017eba", "NOUN", [38, 45]], ["v\u016fbec", "v\u016fbec", "PART", [46, 51]], ["nemluv\u00edme", "mluvit", "VERB", [52, 61]], [",", ",", "PUNCT", [61, 62]], ["a", "a", "CCONJ", [63, 64]], ["chceme", "cht\u00edt", "VERB", [65, 71]], [",", ",", "PUNCT", [71, 72]], ["aby", "aby", "SCONJ", [-37278, -37278]], ["by", "b\u00fdt", "AUX", [-37278, -37278]], ["na", "na", "ADP", [77, 79]], ["n\u011b", "on", "PRON", [80, 82]], ["p\u0159i\u0161el", "p\u0159ij\u00edt", "VERB", [83, 89]], ["partner", "partner", "NOUN", [90, 97]], ["s\u00e1m", "sam\u00fd", "DET", [98, 101]], [".", ".", "PUNCT", [101, 102]]]], ["calgarske-listy_2003_unor_ocr.txt", "To se v\u0161ak v\u011bt\u0161inou ned\u011bje, a tak jsme zklaman\u00ed a vy\u010d\u00edt\u00e1me: \u201eNen\u00ed na tebe spolehnut\u00ed!", [["To", "ten", "DET", [0, 2]], ["se", "se", "PRON", [3, 5]], ["v\u0161ak", "v\u0161ak", "CCONJ", [6, 10]], ["v\u011bt\u0161inou", "v\u011bt\u0161inou", "ADV", [11, 19]], ["ned\u011bje", "d\u00edt", "VERB", [20, 26]], [",", ",", "PUNCT", [26, 27]], ["a", "a", "CCONJ", [28, 29]], ["tak", "tak", "ADV", [30, 33]], ["jsme", "b\u00fdt", "AUX", [34, 38]], ["zklaman\u00ed", "zklaman\u00fd", "ADJ", [39, 47]], ["a", "a", "CCONJ", [48, 49]], ["vy\u010d\u00edt\u00e1me", "vy\u010d\u00edtat", "VERB", [50, 58]], [":", ":", "PUNCT", [58, 59]], ["\u201e", "\"", "PUNCT", [60, 61]], ["Nen\u00ed", "b\u00fdt", "AUX", [61, 65]], ["na", "na", "ADP", [66, 68]], ["tebe", "ty", "PRON", [69, 73]], ["spolehnut\u00ed", "spolehnut\u00ed", "NOUN", [74, 84]], ["!", "!", "PUNCT", [84, 85]]]], ["calgarske-listy_2003_unor_ocr.txt", "Tvoje pr\u00e1ce ti je p\u0159edn\u011bj\u0161\u00ed ne\u017e j\u00e1!\u201c", [["Tvoje", "tvoj\u00ed", "ADJ", [0, 5]], ["pr\u00e1ce", "pr\u00e1ce", "NOUN", [6, 11]], ["ti", "ten", "DET", [12, 14]], ["je", "b\u00fdt", "AUX", [15, 17]], ["p\u0159edn\u011bj\u0161\u00ed", "p\u0159edn\u00fd", "ADJ", [18, 27]], ["ne\u017e", "ne\u017e", "SCONJ", [28, 31]], ["j\u00e1", "j\u00e1", "PRON", [32, 34]], ["!", "!", "PUNCT", [34, 35]], ["\u201c", "\"", "PUNCT", [35, 36]]]], ["calgarske-listy_2003_unor_ocr.txt", "Ov\u0161em tyto v\u00fd\u010ditky jen p\u0159il\u00e9vaj\u00ed olej do ohn\u011b.", [["Ov\u0161em", "ov\u0161em", "PART", [0, 5]], ["tyto", "tento", "DET", [6, 10]], ["v\u00fd\u010ditky", "v\u00fd\u010ditka", "NOUN", [11, 18]], ["jen", "jen", "PART", [19, 22]], ["p\u0159il\u00e9vaj\u00ed", "p\u0159il\u00e9vat", "VERB", [23, 32]], ["olej", "olej", "NOUN", [33, 37]], ["do", "do", "ADP", [38, 40]], ["ohn\u011b", "ohe\u0148", "NOUN", [41, 45]], [".", ".", "PUNCT", [45, 46]]]], ["calgarske-listy_2003_unor_ocr.txt", "Kdo by si nechal r\u00e1d n\u011bco vy\u010d\u00edtat?", [["Kdo", "kdo", "PRON", [0, 3]], ["by", "b\u00fdt", "AUX", [4, 6]], ["si", "se", "PRON", [7, 9]], ["nechal", "nechat", "VERB", [10, 16]], ["r\u00e1d", "r\u00e1d", "ADJ", [17, 20]], ["n\u011bco", "n\u011bco", "PRON", [21, 25]], ["vy\u010d\u00edtat", "vy\u010d\u00edtat", "VERB", [26, 33]], ["?", "?", "PUNCT", [33, 34]]]], ["calgarske-listy_2003_unor_ocr.txt", "M\u00edsto v\u00fd\u010ditek zkuste t\u0159eba: \u201eCht\u011bl/a bych s tebou tr\u00e1vit v\u00edce \u010dasu,\u201c \u010d\u00edm\u017e vyj\u00e1d\u0159\u00edte vlastn\u00ed p\u0159\u00e1n\u00ed, ani\u017e byste se sni\u017eovali k lacin\u00fdm a kontraproduktivn\u00edm v\u00fd\u010ditk\u00e1m.", [["M\u00edsto", "m\u00edsto", "ADP", [0, 5]], ["v\u00fd\u010ditek", "v\u00fd\u010ditek", "NOUN", [6, 13]], ["zkuste", "zkusit", "VERB", [14, 20]], ["t\u0159eba", "t\u0159eba", "PART", [21, 26]], [":", ":", "PUNCT", [26, 27]], ["\u201e", "\"", "PUNCT", [28, 29]], ["Cht\u011bl", "cht\u00edt", "VERB", [29, 34]], ["/", "/", "PUNCT", [34, 35]], ["a", "a", "CCONJ", [35, 36]], ["bych", "b\u00fdt", "AUX", [37, 41]], ["s", "s", "ADP", [42, 43]], ["tebou", "teba", "NOUN", [44, 49]], ["tr\u00e1vit", "tr\u00e1vit", "VERB", [50, 56]], ["v\u00edce", "v\u00edce", "ADV", [57, 61]], ["\u010dasu", "\u010das", "NOUN", [62, 66]], [",", ",", "PUNCT", [66, 67]], ["\u201c", "\"", "PUNCT", [67, 68]], ["\u010d\u00edm\u017e", "co\u017e", "PRON", [69, 73]], ["vyj\u00e1d\u0159\u00edte", "vyj\u00e1d\u0159it", "VERB", [74, 83]], ["vlastn\u00ed", "vlastn\u00ed", "ADJ", [84, 91]], ["p\u0159\u00e1n\u00ed", "p\u0159\u00e1n\u00ed", "NOUN", [92, 97]], [",", ",", "PUNCT", [97, 98]], ["ani\u017e", "ani\u017e", "SCONJ", [99, 103]], ["byste", "b\u00fdt", "AUX", [104, 109]], ["se", "se", "PRON", [110, 112]], ["sni\u017eovali", "sni\u017eovat", "VERB", [113, 122]], ["k", "k", "ADP", [123, 124]], ["lacin\u00fdm", "lacin\u00fd", "ADJ", [125, 132]], ["a", "a", "CCONJ", [133, 134]], ["kontraproduktivn\u00edm", "kontraproduktivn\u00ed", "ADJ", [135, 153]], ["v\u00fd\u010ditk\u00e1m", "v\u00fd\u010ditka", "NOUN", [154, 162]], [".", ".", "PUNCT", [162, 163]]]], ["calgarske-listy_2003_unor_ocr.txt", "Vyj\u00e1d\u0159ete sv\u00e1 p\u0159\u00e1n\u00ed - Kouzeln\u00e1 formulka b\u011bhem prob\u00edhaj\u00edc\u00edho sporu je hovo\u0159it o sob\u011b samotn\u00e9m, o sv\u00fdch pocitech.", [["Vyj\u00e1d\u0159ete", "vyj\u00e1d\u0159at", "VERB", [0, 9]], ["sv\u00e1", "sv\u016fj", "DET", [10, 13]], ["p\u0159\u00e1n\u00ed", "p\u0159\u00e1n\u00ed", "NOUN", [14, 19]], ["-", "-", "PUNCT", [20, 21]], ["Kouzeln\u00e1", "kouzeln\u00fd", "ADJ", [22, 30]], ["formulka", "formulka", "NOUN", [31, 39]], ["b\u011bhem", "b\u011bhem", "ADP", [40, 45]], ["prob\u00edhaj\u00edc\u00edho", "prob\u00edhaj\u00edc\u00ed", "ADJ", [46, 59]], ["sporu", "spor", "NOUN", [60, 65]], ["je", "b\u00fdt", "AUX", [66, 68]], ["hovo\u0159it", "hovo\u0159it", "VERB", [69, 76]], ["o", "o", "ADP", [77, 78]], ["sob\u011b", "se", "PRON", [79, 83]], ["samotn\u00e9m", "samotn\u00fd", "ADJ", [84, 92]], [",", ",", "PUNCT", [92, 93]], ["o", "o", "ADP", [94, 95]], ["sv\u00fdch", "sv\u016fj", "DET", [96, 101]], ["pocitech", "pocit", "NOUN", [102, 110]], [".", ".", "PUNCT", [110, 111]]]], ["calgarske-listy_2003_unor_ocr.txt", "Proto\u017ee n\u00e1s to zra\u0148uje, ned\u011bl\u00e1me to r\u00e1di.", [["Proto\u017ee", "proto\u017ee", "SCONJ", [0, 7]], ["n\u00e1s", "my", "PRON", [8, 11]], ["to", "ten", "DET", [12, 14]], ["zra\u0148uje", "zra\u0148ovat", "VERB", [15, 22]], [",", ",", "PUNCT", [22, 23]], ["ned\u011bl\u00e1me", "d\u011blat", "VERB", [24, 32]], ["to", "ten", "DET", [33, 35]], ["r\u00e1di", "r\u00e1d", "ADJ", [36, 40]], [".", ".", "PUNCT", [40, 41]]]], ["calgarske-listy_2003_unor_ocr.txt", "Av\u0161ak komu jin\u00e9mu bychom to m\u011bli \u0159\u00edct ne\u017e sv\u00e9mu partnerovi?", [["Av\u0161ak", "av\u0161ak", "CCONJ", [0, 5]], ["komu", "kdo", "PRON", [6, 10]], ["jin\u00e9mu", "jin\u00fd", "ADJ", [11, 17]], ["bychom", "b\u00fdt", "AUX", [18, 24]], ["to", "ten", "DET", [25, 27]], ["m\u011bli", "m\u00edt", "VERB", [28, 32]], ["\u0159\u00edct", "\u0159\u00edci", "VERB", [33, 37]], ["ne\u017e", "ne\u017e", "SCONJ", [38, 41]], ["sv\u00e9mu", "sv\u016fj", "DET", [42, 47]], ["partnerovi", "partner", "NOUN", [48, 58]], ["?", "?", "PUNCT", [58, 59]]]], ["calgarske-listy_2003_unor_ocr.txt", "D\u016fle\u017eit\u00e9 je nepodlehnout zlosti a ve vzteku nezranit partnera.", [["D\u016fle\u017eit\u00e9", "d\u016fle\u017eit\u00fd", "ADJ", [0, 8]], ["je", "b\u00fdt", "AUX", [9, 11]], ["nepodlehnout", "podlehnout", "VERB", [12, 24]], ["zlosti", "zlost", "NOUN", [25, 31]], ["a", "a", "CCONJ", [32, 33]], ["ve", "v", "ADP", [34, 36]], ["vzteku", "vztek", "NOUN", [37, 43]], ["nezranit", "zranit", "VERB", [44, 52]], ["partnera", "partner", "NOUN", [53, 61]], [".", ".", "PUNCT", [61, 62]]]], ["calgarske-listy_2003_unor_ocr.txt", "\u010casto si v z\u00e1palu boje neuv\u011bdomujeme t\u00f3n na\u0161eho hlasu, co\u017e je samoz\u0159ejm\u011b chyba.", [["\u010casto", "\u010dasto", "ADV", [0, 5]], ["si", "se", "PRON", [6, 8]], ["v", "v", "ADP", [9, 10]], ["z\u00e1palu", "z\u00e1pal", "NOUN", [11, 17]], ["boje", "boj", "NOUN", [18, 22]], ["neuv\u011bdomujeme", "uv\u011bdomovat", "VERB", [23, 36]], ["t\u00f3n", "t\u00f3n", "NOUN", [37, 40]], ["na\u0161eho", "n\u00e1\u0161", "DET", [41, 47]], ["hlasu", "hlas", "NOUN", [48, 53]], [",", ",", "PUNCT", [53, 54]], ["co\u017e", "co\u017e", "PRON", [55, 58]], ["je", "b\u00fdt", "AUX", [59, 61]], ["samoz\u0159ejm\u011b", "samoz\u0159ejm\u011b", "ADV", [62, 72]], ["chyba", "chyba", "NOUN", [73, 78]], [".", ".", "PUNCT", [78, 79]]]], ["calgarske-listy_2003_unor_ocr.txt", "Na takovou razantn\u00ed \u0159e\u010d je pot\u0159eba reagovat klidn\u011b, abychom dali partnerovi p\u0159\u00edle\u017eitost uklidnit se.", [["Na", "na", "ADP", [0, 2]], ["takovou", "takov\u00fd", "DET", [3, 10]], ["razantn\u00ed", "razantn\u00ed", "ADJ", [11, 19]], ["\u0159e\u010d", "\u0159e\u010d", "NOUN", [20, 23]], ["je", "b\u00fdt", "AUX", [24, 26]], ["pot\u0159eba", "pot\u0159eba", "NOUN", [27, 34]], ["reagovat", "reagovat", "VERB", [35, 43]], ["klidn\u011b", "klidn\u011b", "ADV", [44, 50]], [",", ",", "PUNCT", [50, 51]], ["aby", "aby", "SCONJ", [-38107, -38107]], ["bychom", "b\u00fdt", "AUX", [-38107, -38107]], ["dali", "d\u00e1t", "VERB", [60, 64]], ["partnerovi", "partner", "NOUN", [65, 75]], ["p\u0159\u00edle\u017eitost", "p\u0159\u00edle\u017eitost", "NOUN", [76, 87]], ["uklidnit", "uklidnit", "VERB", [88, 96]], ["se", "se", "PRON", [97, 99]], [".", ".", "PUNCT", [99, 100]]]], ["calgarske-listy_2003_unor_ocr.txt", "Pak teprve vyjde najevo prav\u00e1 p\u0159\u00ed\u010dina partnerova roz\u010d\u00edlen\u00ed.", [["Pak", "pak", "ADV", [0, 3]], ["teprve", "teprve", "ADV", [4, 10]], ["vyjde", "vyj\u00edt", "VERB", [11, 16]], ["najevo", "najevo", "ADV", [17, 23]], ["prav\u00e1", "prav\u00fd", "ADJ", [24, 29]], ["p\u0159\u00ed\u010dina", "p\u0159\u00ed\u010dina", "NOUN", [30, 37]], ["partnerova", "partner\u016fv", "ADJ", [38, 48]], ["roz\u010d\u00edlen\u00ed", "roz\u010d\u00edlen\u00ed", "NOUN", [49, 58]], [".", ".", "PUNCT", [58, 59]]]], ["calgarske-listy_2003_unor_ocr.txt", "Existuje v\u00edce \u0159e\u0161en\u00ed.", [["Existuje", "existovat", "VERB", [0, 8]], ["v\u00edce", "v\u00edce", "ADV", [9, 13]], ["\u0159e\u0161en\u00ed", "\u0159e\u0161en\u00ed", "NOUN", [14, 20]], [".", ".", "PUNCT", [20, 21]]]], ["calgarske-listy_2003_unor_ocr.txt", "A\u017e zlost odezn\u00ed, m\u016f\u017ee doj\u00edt k v\u00fdm\u011bn\u011b n\u00e1zor\u016f.", [["A\u017e", "a\u017e", "PART", [0, 2]], ["zlost", "zlost", "NOUN", [3, 8]], ["odezn\u00ed", "odezn\u00edt", "VERB", [9, 15]], [",", ",", "PUNCT", [15, 16]], ["m\u016f\u017ee", "moci", "VERB", [17, 21]], ["doj\u00edt", "doj\u00edt", "VERB", [22, 27]], ["k", "k", "ADP", [28, 29]], ["v\u00fdm\u011bn\u011b", "v\u00fdm\u011bna", "NOUN", [30, 36]], ["n\u00e1zor\u016f", "n\u00e1zor", "NOUN", [37, 43]], [".", ".", "PUNCT", [43, 44]]]], ["calgarske-listy_2003_unor_ocr.txt", "Casto existuje v\u00edcero \u0159e\u0161en\u00ed - mnohdy zcela ne\u010dekan\u00e1.", [["Casto", "Casto", "PROPN", [0, 5]], ["existuje", "existovat", "VERB", [6, 14]], ["v\u00edcero", "v\u00edcero", "DET", [15, 21]], ["\u0159e\u0161en\u00ed", "\u0159e\u0161en\u00ed", "NOUN", [22, 28]], ["-", "-", "PUNCT", [29, 30]], ["mnohdy", "mnohdy", "ADV", [31, 37]], ["zcela", "zcela", "ADV", [38, 43]], ["ne\u010dekan\u00e1", "\u010dekan\u00fd", "ADJ", [44, 52]], [".", ".", "PUNCT", [52, 53]]]], ["calgarske-listy_2003_unor_ocr.txt", "Pokud se t\u0159eba p\u00e1r nen\u00ed schopen dohodnout na m\u00edst\u011b dovolen\u00e9, m\u016f\u017ee jet ka\u017ed\u00fd s\u00e1m, nebo jet dvakr\u00e1t.", [["Pokud", "pokud", "SCONJ", [0, 5]], ["se", "se", "PRON", [6, 8]], ["t\u0159eba", "t\u0159eba", "PART", [9, 14]], ["p\u00e1r", "p\u00e1r", "NOUN", [15, 18]], ["nen\u00ed", "b\u00fdt", "AUX", [19, 23]], ["schopen", "schopn\u00fd", "ADJ", [24, 31]], ["dohodnout", "dohodnout", "VERB", [32, 41]], ["na", "na", "ADP", [42, 44]], ["m\u00edst\u011b", "m\u00edsto", "NOUN", [45, 50]], ["dovolen\u00e9", "dovolen\u00e1", "NOUN", [51, 59]], [",", ",", "PUNCT", [59, 60]], ["m\u016f\u017ee", "moci", "VERB", [61, 65]], ["jet", "jet", "VERB", [66, 69]], ["ka\u017ed\u00fd", "ka\u017ed\u00fd", "DET", [70, 75]], ["s\u00e1m", "sam\u00fd", "DET", [76, 79]], [",", ",", "PUNCT", [79, 80]], ["nebo", "nebo", "CCONJ", [81, 85]], ["jet", "jet", "VERB", [86, 89]], ["dvakr\u00e1t", "dvakr\u00e1t", "ADV", [90, 97]], [".", ".", "PUNCT", [97, 98]]]], ["calgarske-listy_2003_unor_ocr.txt", "Dohoda znamen\u00e1 tak\u00e9 akceptovat rozd\u00edly.", [["Dohoda", "dohoda", "NOUN", [0, 6]], ["znamen\u00e1", "znamenat", "VERB", [7, 14]], ["tak\u00e9", "tak\u00e9", "ADV", [15, 19]], ["akceptovat", "akceptovat", "VERB", [20, 30]], ["rozd\u00edly", "rozd\u00edl", "NOUN", [31, 38]], [".", ".", "PUNCT", [38, 39]]]], ["calgarske-listy_2003_unor_ocr.txt", "Nav\u00edc m\u016f\u017ee b\u00fdt usmi\u0159ov\u00e1n\u00ed nanejv\u00fd\u0161 p\u0159\u00edjemn\u00e9 a z\u00e1bavn\u00e9 \u2014 a\u0165 u\u017e klasicky kv\u011btinou, p\u0159i spole\u010dn\u00e9 ve\u010de\u0159i nebo dokonce v posteli.", [["Nav\u00edc", "nav\u00edc", "ADV", [0, 5]], ["m\u016f\u017ee", "moci", "VERB", [6, 10]], ["b\u00fdt", "b\u00fdt", "AUX", [11, 14]], ["usmi\u0159ov\u00e1n\u00ed", "usmi\u0159ov\u00e1n\u00ed", "NOUN", [15, 25]], ["nanejv\u00fd\u0161", "nanejv\u00fd\u0161", "ADV", [26, 34]], ["p\u0159\u00edjemn\u00e9", "p\u0159\u00edjemn\u00fd", "ADJ", [35, 43]], ["a", "a", "CCONJ", [44, 45]], ["z\u00e1bavn\u00e9", "z\u00e1bavn\u00fd", "ADJ", [46, 53]], ["\u2014", "\u2014", "PUNCT", [54, 55]], ["a\u0165", "a\u0165", "SCONJ", [56, 58]], ["u\u017e", "u\u017e", "ADV", [59, 61]], ["klasicky", "klasicky", "ADV", [62, 70]], ["kv\u011btinou", "kv\u011btina", "NOUN", [71, 79]], [",", ",", "PUNCT", [79, 80]], ["p\u0159i", "p\u0159i", "ADP", [81, 84]], ["spole\u010dn\u00e9", "spole\u010dn\u00fd", "ADJ", [85, 93]], ["ve\u010de\u0159i", "ve\u010de\u0159e", "NOUN", [94, 100]], ["nebo", "nebo", "CCONJ", [101, 105]], ["dokonce", "dokonce", "ADV", [106, 113]], ["v", "v", "ADP", [114, 115]], ["posteli", "postel", "NOUN", [116, 123]], [".", ".", "PUNCT", [123, 124]]]], ["calgarske-listy_2003_unor_ocr.txt", "Nakonec \u2014 protiklady se p\u0159itahuj\u00ed.", [["Nakonec", "nakonec", "ADV", [0, 7]], ["\u2014", "\u2014", "PUNCT", [8, 9]], ["protiklady", "protiklad", "NOUN", [10, 20]], ["se", "se", "PRON", [21, 23]], ["p\u0159itahuj\u00ed", "p\u0159itahovat", "VERB", [24, 33]], [".", ".", "PUNCT", [33, 34]]]], ["calgarske-listy_2003_unor_ocr.txt", "Zaru\u010den\u00fd recept na dlouholet\u00fd spokojen\u00fd svazek neexistuje.", [["Zaru\u010den\u00fd", "zaru\u010den\u00fd", "ADJ", [0, 8]], ["recept", "recept", "NOUN", [9, 15]], ["na", "na", "ADP", [16, 18]], ["dlouholet\u00fd", "dlouholet\u00fd", "ADJ", [19, 29]], ["spokojen\u00fd", "spokojen\u00fd", "ADJ", [30, 39]], ["svazek", "svazek", "NOUN", [40, 46]], ["neexistuje", "existovat", "VERB", [47, 57]], [".", ".", "PUNCT", [57, 58]]]], ["calgarske-listy_2003_unor_ocr.txt", "Mnoho p\u00e1r\u016f spolu \u017eije ji\u017e jen ze zvyku nebo kv\u016fli d\u011btem.", [["Mnoho", "mnoho", "DET", [0, 5]], ["p\u00e1r\u016f", "p\u00e1r", "NOUN", [6, 10]], ["spolu", "spolu", "ADV", [11, 16]], ["\u017eije", "\u017e\u00edt", "VERB", [17, 21]], ["ji\u017e", "ji\u017e", "ADV", [22, 25]], ["jen", "jen", "PART", [26, 29]], ["ze", "z", "ADP", [30, 32]], ["zvyku", "zvyk", "NOUN", [33, 38]], ["nebo", "nebo", "CCONJ", [39, 43]], ["kv\u016fli", "kv\u016fli", "ADP", [44, 49]], ["d\u011btem", "d\u00edt\u011b", "NOUN", [50, 55]], [".", ".", "PUNCT", [55, 56]]]], ["calgarske-listy_2003_unor_ocr.txt", "Intenzivn\u00ed pocit odcizen\u00ed se st\u00e1le prohlubuje a jen zvy\u0161uje u partner\u016f frustraci z neuspokojiv\u00e9ho vztahu.", [["Intenzivn\u00ed", "intenzivn\u00ed", "ADJ", [0, 10]], ["pocit", "pocit", "NOUN", [11, 16]], ["odcizen\u00ed", "odcizen\u00ed", "NOUN", [17, 25]], ["se", "se", "PRON", [26, 28]], ["st\u00e1le", "st\u00e1le", "ADV", [29, 34]], ["prohlubuje", "prohlubovat", "VERB", [35, 45]], ["a", "a", "CCONJ", [46, 47]], ["jen", "jen", "ADV", [48, 51]], ["zvy\u0161uje", "zvy\u0161ovat", "VERB", [52, 59]], ["u", "u", "ADP", [60, 61]], ["partner\u016f", "partner", "NOUN", [62, 70]], ["frustraci", "frustrace", "NOUN", [71, 80]], ["z", "z", "ADP", [81, 82]], ["neuspokojiv\u00e9ho", "uspokojiv\u00fd", "ADJ", [83, 97]], ["vztahu", "vztah", "NOUN", [98, 104]], [".", ".", "PUNCT", [104, 105]]]], ["calgarske-listy_2003_unor_ocr.txt", "V\u00fd\u0161e uveden\u00e9 tipy snad dopomohou k tomu, aby se v\u00e1\u0161 vztah do takov\u00e9ho st\u00e1dia nedostal.", [["V\u00fd\u0161e", "vysoko", "ADV", [0, 4]], ["uveden\u00e9", "uveden\u00fd", "ADJ", [5, 12]], ["tipy", "tip", "NOUN", [13, 17]], ["snad", "snad", "PART", [18, 22]], ["dopomohou", "dopomoci", "VERB", [23, 32]], ["k", "k", "ADP", [33, 34]], ["tomu", "ten", "DET", [35, 39]], [",", ",", "PUNCT", [39, 40]], ["aby", "aby", "SCONJ", [-38910, -38910]], ["by", "b\u00fdt", "AUX", [-38910, -38910]], ["se", "se", "PRON", [45, 47]], ["v\u00e1\u0161", "v\u00e1\u0161", "DET", [48, 51]], ["vztah", "vztah", "NOUN", [52, 57]], ["do", "do", "ADP", [58, 60]], ["takov\u00e9ho", "takov\u00fd", "DET", [61, 69]], ["st\u00e1dia", "st\u00e1dium", "NOUN", [70, 76]], ["nedostal", "dostat", "VERB", [77, 85]], [".", ".", "PUNCT", [85, 86]]]], ["calgarske-listy_2003_unor_ocr.txt", "9  Dvan\u00e1ct dobr\u00fdch d\u016fvod\u016f pro sex Marek Li\u0161ka (Checht\u00e1vej tygr) 15.10. 2002. 1. / MILOV\u00c1N\u00cd M\u00c1 POZITIVN\u00cd VLIV NA KREATIVITU A BYST\u0158\u00cd ROZUM.", [["9", "9", "NUM", [0, 1]], ["Dvan\u00e1ct", "dvan\u00e1ct", "NUM", [3, 10]], ["dobr\u00fdch", "dobr\u00fd", "ADJ", [11, 18]], ["d\u016fvod\u016f", "d\u016fvod", "NOUN", [19, 25]], ["pro", "pro", "ADP", [26, 29]], ["sex", "sex", "NOUN", [30, 33]], ["Marek", "Marek", "PROPN", [34, 39]], ["Li\u0161ka", "Li\u0161ka", "PROPN", [40, 45]], ["(", "(", "PUNCT", [46, 47]], ["Checht\u00e1vej", "Checht\u00e1vej", "PROPN", [47, 57]], ["tygr", "tygr", "NOUN", [58, 62]], [")", ")", "PUNCT", [62, 63]], ["15.10", "15.10", "NUM", [64, 69]], [".", ".", "PUNCT", [69, 70]], ["2002", "2002", "NUM", [71, 75]], [".", ".", "PUNCT", [75, 76]], ["1", "1", "NUM", [77, 78]], [".", ".", "PUNCT", [78, 79]], ["/", "/", "PUNCT", [80, 81]], ["MILOV\u00c1N\u00cd", "milov\u00e1n\u00ed", "NOUN", [82, 90]], ["M\u00c1", "m\u00edt", "VERB", [91, 93]], ["POZITIVN\u00cd", "pozitivn\u00ed", "ADJ", [94, 103]], ["VLIV", "VLIV", "NOUN", [104, 108]], ["NA", "na", "ADP", [109, 111]], ["KREATIVITU", "kreativita", "NOUN", [112, 122]], ["A", "a", "CCONJ", [123, 124]], ["BYST\u0158\u00cd", "byst\u0159\u00ed", "ADJ", [125, 131]], ["ROZUM", "rozum", "NOUN", [132, 137]], [".", ".", "PUNCT", [137, 138]]]], ["calgarske-listy_2003_unor_ocr.txt", "To je zp\u016fsobeno t\u00edm, \u017ee b\u011bhem pro\u017e\u00edv\u00e1n\u00ed sexu\u00e1ln\u00ed ext\u00e1ze jsou stimulov\u00e1ny mozkov\u00e9 bu\u0148ky.", [["To", "ten", "DET", [0, 2]], ["je", "b\u00fdt", "AUX", [3, 5]], ["zp\u016fsobeno", "zp\u016fsoben\u00fd", "ADJ", [6, 15]], ["t\u00edm", "ten", "DET", [16, 19]], [",", ",", "PUNCT", [19, 20]], ["\u017ee", "\u017ee", "SCONJ", [21, 23]], ["b\u011bhem", "b\u011bhem", "ADP", [24, 29]], ["pro\u017e\u00edv\u00e1n\u00ed", "pro\u017e\u00edv\u00e1n\u00ed", "NOUN", [30, 39]], ["sexu\u00e1ln\u00ed", "sexu\u00e1ln\u00ed", "ADJ", [40, 48]], ["ext\u00e1ze", "ext\u00e1ze", "NOUN", [49, 55]], ["jsou", "b\u00fdt", "AUX", [56, 60]], ["stimulov\u00e1ny", "stimulovan\u00fd", "ADJ", [61, 72]], ["mozkov\u00e9", "mozkov\u00fd", "ADJ", [73, 80]], ["bu\u0148ky", "bu\u0148ka", "NOUN", [81, 86]], [".", ".", "PUNCT", [86, 87]]]], ["calgarske-listy_2003_unor_ocr.txt", "O\u017eivte proto sv\u016fj intelekt sexem.", [["O\u017eivte", "o\u017eivit", "VERB", [0, 6]], ["proto", "proto", "CCONJ", [7, 12]], ["sv\u016fj", "sv\u016fj", "DET", [13, 17]], ["intelekt", "intelekt", "NOUN", [18, 26]], ["sexem", "sex", "NOUN", [27, 32]], [".", ".", "PUNCT", [32, 33]]]], ["calgarske-listy_2003_unor_ocr.txt", "Odborn\u00edci doporu\u010duj\u00ed osmou hodinu r\u00e1no.", [["Odborn\u00edci", "odborn\u00edk", "NOUN", [0, 9]], ["doporu\u010duj\u00ed", "doporu\u010dovat", "VERB", [10, 20]], ["osmou", "osm\u00fd", "ADJ", [21, 26]], ["hodinu", "hodina", "NOUN", [27, 33]], ["r\u00e1no", "r\u00e1no", "ADV", [34, 38]], [".", ".", "PUNCT", [38, 39]]]], ["calgarske-listy_2003_unor_ocr.txt", "Podle proveden\u00fdch v\u00fdzkum\u016f pom\u00e1h\u00e1 student\u016fm spr\u00e1vn\u011b na\u010dasovan\u00e1 masturbace k lep\u0161\u00edmu zvl\u00e1dnut\u00ed zkou\u0161ek.", [["Podle", "podle", "ADP", [0, 5]], ["proveden\u00fdch", "proveden\u00fd", "ADJ", [6, 17]], ["v\u00fdzkum\u016f", "v\u00fdzkum", "NOUN", [18, 25]], ["pom\u00e1h\u00e1", "pom\u00e1hat", "VERB", [26, 32]], ["student\u016fm", "student", "NOUN", [33, 42]], ["spr\u00e1vn\u011b", "spr\u00e1vn\u011b", "ADV", [43, 50]], ["na\u010dasovan\u00e1", "na\u010dasovan\u00fd", "ADJ", [51, 61]], ["masturbace", "masturbace", "NOUN", [62, 72]], ["k", "k", "ADP", [73, 74]], ["lep\u0161\u00edmu", "lep\u0161\u00ed", "ADJ", [75, 82]], ["zvl\u00e1dnut\u00ed", "zvl\u00e1dnut\u00ed", "NOUN", [83, 92]], ["zkou\u0161ek", "zkou\u0161ka", "NOUN", [93, 100]], [".", ".", "PUNCT", [100, 101]]]], ["calgarske-listy_2003_unor_ocr.txt", "2. / SEX D\u011aL\u00c1 SVALY.", [["2", "2", "NUM", [0, 1]], [".", ".", "PUNCT", [1, 2]], ["/", "/", "PUNCT", [3, 4]], ["SEX", "Sex", "NOUN", [5, 8]], ["D\u011aL\u00c1", "d\u011blat", "VERB", [9, 13]], ["SVALY", "sval", "NOUN", [14, 19]], [".", ".", "PUNCT", [19, 20]]]], ["calgarske-listy_2003_unor_ocr.txt", "P\u0159i zv\u00fd\u0161en\u00e9 frekvenci d\u00fdch\u00e1n\u00ed se br\u00e1nice stahuje a stimuluje b\u0159i\u0161n\u00ed svaly.", [["P\u0159i", "p\u0159i", "ADP", [0, 3]], ["zv\u00fd\u0161en\u00e9", "zv\u00fd\u0161en\u00fd", "ADJ", [4, 11]], ["frekvenci", "frekvence", "NOUN", [12, 21]], ["d\u00fdch\u00e1n\u00ed", "d\u00fdch\u00e1n\u00ed", "NOUN", [22, 29]], ["se", "se", "PRON", [30, 32]], ["br\u00e1nice", "br\u00e1nice", "NOUN", [33, 40]], ["stahuje", "stahovat", "VERB", [41, 48]], ["a", "a", "CCONJ", [49, 50]], ["stimuluje", "stimulovat", "VERB", [51, 60]], ["b\u0159i\u0161n\u00ed", "b\u0159i\u0161n\u00ed", "ADJ", [61, 67]], ["svaly", "sval", "NOUN", [68, 73]], [".", ".", "PUNCT", [73, 74]]]], ["calgarske-listy_2003_unor_ocr.txt", "U mu\u017e\u016f se krom\u011b toho zesiluje vyplavov\u00e1n\u00ed testosteronu.", [["U", "u", "ADP", [0, 1]], ["mu\u017e\u016f", "mu\u017e", "NOUN", [2, 6]], ["se", "se", "PRON", [7, 9]], ["krom\u011b", "krom\u011b", "ADP", [10, 15]], ["toho", "ten", "DET", [16, 20]], ["zesiluje", "zesilovat", "VERB", [21, 29]], ["vyplavov\u00e1n\u00ed", "vyplavov\u00e1n\u00ed", "NOUN", [30, 41]], ["testosteronu", "testosteron", "NOUN", [42, 54]], [".", ".", "PUNCT", [54, 55]]]], ["calgarske-listy_2003_unor_ocr.txt", "Toto anabolikum pom\u00e1h\u00e1 nastartovat tvorbu b\u00edlkovin, kter\u00e9 jsou d\u016fle\u017eit\u00e9 pro r\u016fst sval\u016f a tvorbu kost\u00ed.", [["Toto", "tento", "DET", [0, 4]], ["anabolikum", "anabolikum", "NOUN", [5, 15]], ["pom\u00e1h\u00e1", "pom\u00e1hat", "VERB", [16, 22]], ["nastartovat", "nastartovat", "VERB", [23, 34]], ["tvorbu", "tvorba", "NOUN", [35, 41]], ["b\u00edlkovin", "b\u00edlkovina", "NOUN", [42, 50]], [",", ",", "PUNCT", [50, 51]], ["kter\u00e9", "kter\u00fd", "DET", [52, 57]], ["jsou", "b\u00fdt", "AUX", [58, 62]], ["d\u016fle\u017eit\u00e9", "d\u016fle\u017eit\u00fd", "ADJ", [63, 71]], ["pro", "pro", "ADP", [72, 75]], ["r\u016fst", "r\u016fst", "NOUN", [76, 80]], ["sval\u016f", "sval", "NOUN", [81, 86]], ["a", "a", "CCONJ", [87, 88]], ["tvorbu", "tvorba", "NOUN", [89, 95]], ["kost\u00ed", "kost", "NOUN", [96, 101]], [".", ".", "PUNCT", [101, 102]]]], ["calgarske-listy_2003_unor_ocr.txt", "3. / SEX UVOL\u0147UJE .", [["3", "3", "NUM", [0, 1]], [".", ".", "PUNCT", [1, 2]], ["/", "/", "PUNCT", [3, 4]], ["SEX", "Sex", "NOUN", [5, 8]], ["UVOL\u0147UJE", "uvolat", "VERB", [9, 17]], [".", ".", "PUNCT", [18, 19]]]], ["calgarske-listy_2003_unor_ocr.txt", "Vydatn\u00e1 soulo\u017e posiluje z kancel\u00e1\u0159e unaven\u00e9 z\u00e1dov\u00e9 svalstvo a odstra\u0148uje migr\u00e9nu a p\u0159eta\u017een\u00ed \u0161\u00edje.", [["Vydatn\u00e1", "vydatn\u00fd", "ADJ", [0, 7]], ["soulo\u017e", "soulo\u017e", "NOUN", [8, 14]], ["posiluje", "posilovat", "VERB", [15, 23]], ["z", "z", "ADP", [24, 25]], ["kancel\u00e1\u0159e", "kancel\u00e1\u0159", "NOUN", [26, 35]], ["unaven\u00e9", "unaven\u00fd", "ADJ", [36, 43]], ["z\u00e1dov\u00e9", "z\u00e1dov\u00fd", "ADJ", [44, 50]], ["svalstvo", "svalstvo", "NOUN", [51, 59]], ["a", "a", "CCONJ", [60, 61]], ["odstra\u0148uje", "odstra\u0148ovat", "VERB", [62, 72]], ["migr\u00e9nu", "migr\u00e9n", "NOUN", [73, 80]], ["a", "a", "CCONJ", [81, 82]], ["p\u0159eta\u017een\u00ed", "p\u0159eta\u017een\u00ed", "NOUN", [83, 92]], ["\u0161\u00edje", "\u0161\u00edje", "NOUN", [93, 97]], [".", ".", "PUNCT", [97, 98]]]], ["calgarske-listy_2003_unor_ocr.txt", "Dr. Reed Moskowitz z americk\u00e9ho Stress Disorders Medical Service tvrd\u00ed, \u017ee p\u0159i sexu zv\u00fd\u0161en\u00e1 hladina adrenalinu sni\u017euje \u0161kodliv\u00e9 psychick\u00e9 vyp\u011bt\u00ed.", [["Dr", "Dr", "NOUN", [0, 2]], [".", ".", "PUNCT", [2, 3]], ["Reed", "Reed", "PROPN", [4, 8]], ["Moskowitz", "Moskowitz", "PROPN", [9, 18]], ["z", "z", "ADP", [19, 20]], ["americk\u00e9ho", "americk\u00fd", "ADJ", [21, 31]], ["Stress", "Stress", "X", [32, 38]], ["Disorders", "Disorders", "X", [39, 48]], ["Medical", "Medical", "X", [49, 56]], ["Service", "Service", "X", [57, 64]], ["tvrd\u00ed", "tvrdit", "VERB", [65, 70]], [",", ",", "PUNCT", [70, 71]], ["\u017ee", "\u017ee", "SCONJ", [72, 74]], ["p\u0159i", "p\u0159i", "ADP", [75, 78]], ["sexu", "sex", "NOUN", [79, 83]], ["zv\u00fd\u0161en\u00e1", "zv\u00fd\u0161en\u00fd", "ADJ", [84, 91]], ["hladina", "hladina", "NOUN", [92, 99]], ["adrenalinu", "adrenalin", "NOUN", [100, 110]], ["sni\u017euje", "sni\u017eovat", "VERB", [111, 118]], ["\u0161kodliv\u00e9", "\u0161kodliv\u00fd", "ADJ", [119, 127]], ["psychick\u00e9", "psychick\u00fd", "ADJ", [128, 137]], ["vyp\u011bt\u00ed", "vyp\u011bt\u00ed", "NOUN", [138, 144]], [".", ".", "PUNCT", [144, 145]]]], ["calgarske-listy_2003_unor_ocr.txt", "4. / SEX ZAH\u00c1N\u00cd BOLEST.", [["4", "4", "NUM", [0, 1]], [".", ".", "PUNCT", [1, 2]], ["/", "/", "PUNCT", [3, 4]], ["SEX", "Sex", "NOUN", [5, 8]], ["ZAH\u00c1N\u00cd", "zah\u00e1n\u00ed", "NOUN", [9, 15]], ["BOLEST", "bolest", "NOUN", [16, 22]], [".", ".", "PUNCT", [22, 23]]]], ["calgarske-listy_2003_unor_ocr.txt", "Kdy\u017e hormon\u00e1ln\u00ed \u017el\u00e1zy b\u011b\u017e\u00ed na pln\u00e9 ot\u00e1\u010dky, jsou v\u0161echny smysly om\u00e1men\u00e9 jako po d\u00e1vce morfia.", [["Kdy\u017e", "kdy\u017e", "SCONJ", [0, 4]], ["hormon\u00e1ln\u00ed", "hormon\u00e1ln\u00ed", "ADJ", [5, 15]], ["\u017el\u00e1zy", "\u017el\u00e1za", "NOUN", [16, 21]], ["b\u011b\u017e\u00ed", "b\u011b\u017eet", "VERB", [22, 26]], ["na", "na", "ADP", [27, 29]], ["pln\u00e9", "pln\u00fd", "ADJ", [30, 34]], ["ot\u00e1\u010dky", "ot\u00e1\u010dka", "NOUN", [35, 41]], [",", ",", "PUNCT", [41, 42]], ["jsou", "b\u00fdt", "AUX", [43, 47]], ["v\u0161echny", "v\u0161echen", "DET", [48, 55]], ["smysly", "smysl", "NOUN", [56, 62]], ["om\u00e1men\u00e9", "om\u00e1men\u00fd", "ADJ", [63, 70]], ["jako", "jako", "SCONJ", [71, 75]], ["po", "po", "ADP", [76, 78]], ["d\u00e1vce", "d\u00e1vka", "NOUN", [79, 84]], ["morfia", "morfium", "NOUN", [85, 91]], [".", ".", "PUNCT", [91, 92]]]], ["calgarske-listy_2003_unor_ocr.txt", "Ka\u017ed\u00fd dotek uvol\u0148uje svaly, ka\u017ed\u00e1 pohlavn\u00ed stimulace blokuje bolest.", [["Ka\u017ed\u00fd", "ka\u017ed\u00fd", "DET", [0, 5]], ["dotek", "dotek", "NOUN", [6, 11]], ["uvol\u0148uje", "uvol\u0148ovat", "VERB", [12, 20]], ["svaly", "sval", "NOUN", [21, 26]], [",", ",", "PUNCT", [26, 27]], ["ka\u017ed\u00e1", "ka\u017ed\u00fd", "DET", [28, 33]], ["pohlavn\u00ed", "pohlavn\u00ed", "ADJ", [34, 42]], ["stimulace", "stimulace", "NOUN", [43, 52]], ["blokuje", "blokovat", "VERB", [53, 60]], ["bolest", "bolest", "NOUN", [61, 67]], [".", ".", "PUNCT", [67, 68]]]], ["calgarske-listy_2003_unor_ocr.txt", "Prov\u00e1d\u011bn\u00e1 pozorov\u00e1n\u00ed u \u017een prok\u00e1zala, \u017ee p\u0159i orgasmu je mez bolesti vy\u0161\u0161\u00ed o 70 procent.", [["Prov\u00e1d\u011bn\u00e1", "prov\u00e1d\u011bn\u00fd", "ADJ", [0, 9]], ["pozorov\u00e1n\u00ed", "pozorov\u00e1n\u00ed", "NOUN", [10, 20]], ["u", "u", "ADP", [21, 22]], ["\u017een", "\u017eena", "NOUN", [23, 26]], ["prok\u00e1zala", "prok\u00e1zat", "VERB", [27, 36]], [",", ",", "PUNCT", [36, 37]], ["\u017ee", "\u017ee", "SCONJ", [38, 40]], ["p\u0159i", "p\u0159i", "ADP", [41, 44]], ["orgasmu", "orgasmus", "NOUN", [45, 52]], ["je", "b\u00fdt", "AUX", [53, 55]], ["mez", "mez", "NOUN", [56, 59]], ["bolesti", "bolest", "NOUN", [60, 67]], ["vy\u0161\u0161\u00ed", "vysok\u00fd", "ADJ", [68, 73]], ["o", "o", "ADP", [74, 75]], ["70", "70", "NUM", [76, 78]], ["procent", "procento", "NOUN", [79, 86]], [".", ".", "PUNCT", [86, 87]]]], ["calgarske-listy_2003_unor_ocr.txt", "Americk\u00fd l\u00e9ka\u0159 Dr. James Couch proto dokonce doporu\u010duje pacientk\u00e1m l\u00e9\u010dit migr\u00e9nu kvalitn\u00edm sexem.", [["Americk\u00fd", "americk\u00fd", "ADJ", [0, 8]], ["l\u00e9ka\u0159", "l\u00e9ka\u0159", "NOUN", [9, 14]], ["Dr", "Dr", "NOUN", [15, 17]], [".", ".", "PUNCT", [17, 18]], ["James", "James", "PROPN", [19, 24]], ["Couch", "Couch", "PROPN", [25, 30]], ["proto", "proto", "CCONJ", [31, 36]], ["dokonce", "dokonce", "ADV", [37, 44]], ["doporu\u010duje", "doporu\u010dovat", "VERB", [45, 55]], ["pacientk\u00e1m", "pacientka", "NOUN", [56, 66]], ["l\u00e9\u010dit", "l\u00e9\u010dit", "VERB", [67, 72]], ["migr\u00e9nu", "migr\u00e9n", "NOUN", [73, 80]], ["kvalitn\u00edm", "kvalitn\u00ed", "ADJ", [81, 90]], ["sexem", "sex", "NOUN", [91, 96]], [".", ".", "PUNCT", [96, 97]]]], ["calgarske-listy_2003_unor_ocr.txt", "5. / SEX UPEV\u0147UJE VZTAH.", [["5", "5", "NUM", [0, 1]], [".", ".", "PUNCT", [1, 2]], ["/", "/", "PUNCT", [3, 4]], ["SEX", "Sex", "NOUN", [5, 8]], ["UPEV\u0147UJE", "upev\u011bovat", "VERB", [9, 17]], ["VZTAH", "vztah", "NOUN", [18, 23]], [".", ".", "PUNCT", [23, 24]]]], ["calgarske-listy_2003_unor_ocr.txt", "\u017dhav\u00fd sex sice nem\u016f\u017ee zachr\u00e1nit mizern\u00fd vztah, ale v\u00fdzkumy ukazuj\u00ed, \u017ee sex je v\u00fdznamn\u00fdm p\u0159edpokladem pro \u0161\u0165astn\u00fd pom\u011br.", [["\u017dhav\u00fd", "\u017ehav\u00fd", "ADJ", [0, 5]], ["sex", "sex", "NOUN", [6, 9]], ["sice", "sice", "CCONJ", [10, 14]], ["nem\u016f\u017ee", "moci", "VERB", [15, 21]], ["zachr\u00e1nit", "zachr\u00e1nit", "VERB", [22, 31]], ["mizern\u00fd", "mizern\u00fd", "ADJ", [32, 39]], ["vztah", "vztah", "NOUN", [40, 45]], [",", ",", "PUNCT", [45, 46]], ["ale", "ale", "CCONJ", [47, 50]], ["v\u00fdzkumy", "v\u00fdzkum", "NOUN", [51, 58]], ["ukazuj\u00ed", "ukazovat", "VERB", [59, 66]], [",", ",", "PUNCT", [66, 67]], ["\u017ee", "\u017ee", "SCONJ", [68, 70]], ["sex", "sex", "NOUN", [71, 74]], ["je", "b\u00fdt", "AUX", [75, 77]], ["v\u00fdznamn\u00fdm", "v\u00fdznamn\u00fd", "ADJ", [78, 87]], ["p\u0159edpokladem", "p\u0159edpoklad", "NOUN", [88, 100]], ["pro", "pro", "ADP", [101, 104]], ["\u0161\u0165astn\u00fd", "\u0161\u0165astn\u00fd", "ADJ", [105, 112]], ["pom\u011br", "pom\u011br", "NOUN", [113, 118]], [".", ".", "PUNCT", [118, 119]]]], ["calgarske-listy_2003_unor_ocr.txt", "Hormon oxytocin prohlubuje t\u011blesn\u00fd svazek mezi partnery.", [["Hormon", "hormon", "NOUN", [0, 6]], ["oxytocin", "oxytocin", "NOUN", [7, 15]], ["prohlubuje", "prohlubovat", "VERB", [16, 26]], ["t\u011blesn\u00fd", "t\u011blesn\u00fd", "ADJ", [27, 34]], ["svazek", "svazek", "NOUN", [35, 41]], ["mezi", "mezi", "ADP", [42, 46]], ["partnery", "partner", "NOUN", [47, 55]], [".", ".", "PUNCT", [55, 56]]]], ["calgarske-listy_2003_unor_ocr.txt", "6. / SEX = ZDRAV\u00c9 ZUBY.", [["6", "6", "NUM", [0, 1]], [".", ".", "PUNCT", [1, 2]], ["/", "/", "PUNCT", [3, 4]], ["SEX", "Sex", "NOUN", [5, 8]], ["=", "=", "SYM", [9, 10]], ["ZDRAV\u00c9", "zdrav\u00fd", "ADJ", [11, 17]], ["ZUBY", "ZUBA", "NOUN", [18, 22]], [".", ".", "PUNCT", [22, 23]]]], ["calgarske-listy_2003_unor_ocr.txt", "\u010c\u00edm siln\u011bj\u0161\u00ed je vym\u011b\u0161ov\u00e1n\u00ed slin, t\u00edm men\u0161\u00ed jsou \u0161kody, kter\u00e9 mohou na zubech zp\u016fsobit kyseliny.", [["\u010c\u00edm", "co", "PRON", [0, 3]], ["siln\u011bj\u0161\u00ed", "siln\u00fd", "ADJ", [4, 12]], ["je", "b\u00fdt", "AUX", [13, 15]], ["vym\u011b\u0161ov\u00e1n\u00ed", "vym\u011b\u0161ov\u00e1n\u00ed", "NOUN", [16, 26]], ["slin", "slina", "NOUN", [27, 31]], [",", ",", "PUNCT", [31, 32]], ["t\u00edm", "ten", "DET", [33, 36]], ["men\u0161\u00ed", "mal\u00fd", "ADJ", [37, 42]], ["jsou", "b\u00fdt", "AUX", [43, 47]], ["\u0161kody", "\u0161koda", "NOUN", [48, 53]], [",", ",", "PUNCT", [53, 54]], ["kter\u00e9", "kter\u00fd", "DET", [55, 60]], ["mohou", "moci", "VERB", [61, 66]], ["na", "na", "ADP", [67, 69]], ["zubech", "zub", "NOUN", [70, 76]], ["zp\u016fsobit", "zp\u016fsobit", "VERB", [77, 85]], ["kyseliny", "kyselina", "NOUN", [86, 94]], [".", ".", "PUNCT", [94, 95]]]], ["calgarske-listy_2003_unor_ocr.txt", "Proto se l\u00edbejte a r\u016fzn\u011b \"olizujte\", jak jen to nejv\u00edc p\u016fjde.", [["Proto", "proto", "CCONJ", [0, 5]], ["se", "se", "PRON", [6, 8]], ["l\u00edbejte", "l\u00edbat", "VERB", [9, 16]], ["a", "a", "CCONJ", [17, 18]], ["r\u016fzn\u011b", "r\u016fzn\u011b", "ADV", [19, 24]], ["\"", "\"", "PUNCT", [25, 26]], ["olizujte", "olizovat", "VERB", [26, 34]], ["\"", "\"", "PUNCT", [34, 35]], [",", ",", "PUNCT", [35, 36]], ["jak", "jak", "ADV", [37, 40]], ["jen", "jen", "PART", [41, 44]], ["to", "ten", "DET", [45, 47]], ["nejv\u00edc", "v\u00edce", "ADV", [48, 54]], ["p\u016fjde", "j\u00edt", "VERB", [55, 60]], [".", ".", "PUNCT", [60, 61]]]], ["calgarske-listy_2003_unor_ocr.txt", "Zubn\u00ed l\u00e9ka\u0159i mnichovsk\u00e9 univerzity toti\u017e zjistili, \u017ee nedostatek sexu napom\u00e1h\u00e1 \"Cracked Tooth Syndrome\", kter\u00fd negativn\u011b p\u016fsob\u00ed na zubn\u00ed sklovinu.", [["Zubn\u00ed", "zubn\u00ed", "ADJ", [0, 5]], ["l\u00e9ka\u0159i", "l\u00e9ka\u0159", "NOUN", [6, 12]], ["mnichovsk\u00e9", "mnichovsk\u00fd", "ADJ", [13, 23]], ["univerzity", "univerzita", "NOUN", [24, 34]], ["toti\u017e", "toti\u017e", "CCONJ", [35, 40]], ["zjistili", "zjistit", "VERB", [41, 49]], [",", ",", "PUNCT", [49, 50]], ["\u017ee", "\u017ee", "SCONJ", [51, 53]], ["nedostatek", "nedostatek", "NOUN", [54, 64]], ["sexu", "sex", "NOUN", [65, 69]], ["napom\u00e1h\u00e1", "napom\u00e1hat", "VERB", [70, 78]], ["\"", "\"", "PUNCT", [79, 80]], ["Cracked", "Cracked", "X", [80, 87]], ["Tooth", "Tooth", "X", [88, 93]], ["Syndrome", "Syndrome", "X", [94, 102]], ["\"", "\"", "PUNCT", [102, 103]], [",", ",", "PUNCT", [103, 104]], ["kter\u00fd", "kter\u00fd", "DET", [105, 110]], ["negativn\u011b", "negativn\u011b", "ADV", [111, 120]], ["p\u016fsob\u00ed", "p\u016fsobit", "VERB", [121, 127]], ["na", "na", "ADP", [128, 130]], ["zubn\u00ed", "zubn\u00ed", "ADJ", [131, 136]], ["sklovinu", "sklovina", "NOUN", [137, 145]], [".", ".", "PUNCT", [145, 146]]]], ["calgarske-listy_2003_unor_ocr.txt", "7./ SEX ZACHRA\u0147UJE \u017dIVOT.", [["7", "7", "NUM", [0, 1]], [".", ".", "PUNCT", [1, 2]], ["/", "/", "PUNCT", [2, 3]], ["SEX", "Sex", "NOUN", [4, 7]], ["ZACHRA\u0147UJE", "zachranovat", "VERB", [8, 18]], ["\u017dIVOT", "\u017eivot", "NOUN", [19, 24]], [".", ".", "PUNCT", [24, 25]]]], ["calgarske-listy_2003_unor_ocr.txt", "Dlouhodob\u00e9 studie z Velk\u00e9 Britanie dokazuj\u00ed, \u017ee u mu\u017e\u016f, kte\u0159\u00ed za\u017e\u00edvaj\u00ed nejm\u00e9n\u011b dvakr\u00e1t t\u00fddn\u011b orgasmus, je \u00famrtnost jen polovi\u010dn\u00ed ve srovn\u00e1n\u00ed s jedinci, kte\u0159\u00ed jsou pohlavn\u011b aktivn\u00ed pouze jednou za m\u011bs\u00edc.", [["Dlouhodob\u00e9", "dlouhodob\u00fd", "ADJ", [0, 10]], ["studie", "studie", "NOUN", [11, 17]], ["z", "z", "ADP", [18, 19]], ["Velk\u00e9", "velk\u00fd", "ADJ", [20, 25]], ["Britanie", "Britanie", "PROPN", [26, 34]], ["dokazuj\u00ed", "dokazovat", "VERB", [35, 43]], [",", ",", "PUNCT", [43, 44]], ["\u017ee", "\u017ee", "SCONJ", [45, 47]], ["u", "u", "ADP", [48, 49]], ["mu\u017e\u016f", "mu\u017e", "NOUN", [50, 54]], [",", ",", "PUNCT", [54, 55]], ["kte\u0159\u00ed", "kter\u00fd", "DET", [56, 61]], ["za\u017e\u00edvaj\u00ed", "za\u017e\u00edvat", "VERB", [62, 70]], ["nejm\u00e9n\u011b", "m\u00e9n\u011b", "ADV", [71, 78]], ["dvakr\u00e1t", "dvakr\u00e1t", "ADV", [79, 86]], ["t\u00fddn\u011b", "t\u00fddn\u011b", "ADV", [87, 92]], ["orgasmus", "orgasmus", "NOUN", [93, 101]], [",", ",", "PUNCT", [101, 102]], ["je", "b\u00fdt", "AUX", [103, 105]], ["\u00famrtnost", "\u00famrtnost", "NOUN", [106, 114]], ["jen", "jen", "PART", [115, 118]], ["polovi\u010dn\u00ed", "polovi\u010dn\u00ed", "ADJ", [119, 128]], ["ve", "v", "ADP", [129, 131]], ["srovn\u00e1n\u00ed", "srovn\u00e1n\u00ed", "NOUN", [132, 140]], ["s", "s", "ADP", [141, 142]], ["jedinci", "jedinec", "NOUN", [143, 150]], [",", ",", "PUNCT", [150, 151]], ["kte\u0159\u00ed", "kter\u00fd", "DET", [152, 157]], ["jsou", "b\u00fdt", "AUX", [158, 162]], ["pohlavn\u011b", "pohlavn\u011b", "ADV", [163, 171]], ["aktivn\u00ed", "aktivn\u00ed", "ADJ", [172, 179]], ["pouze", "pouze", "ADV", [180, 185]], ["jednou", "jednou", "ADV", [186, 192]], ["za", "za", "ADP", [193, 195]], ["m\u011bs\u00edc", "m\u011bs\u00edc", "NOUN", [196, 201]], [".", ".", "PUNCT", [201, 202]]]], ["calgarske-listy_2003_unor_ocr.txt", "8 / SEX UDR\u017dUJE SV\u011a\u017dEST.", [["8", "8", "NUM", [0, 1]], ["/", "/", "PUNCT", [2, 3]], ["SEX", "Sex", "NOUN", [4, 7]], ["UDR\u017dUJE", "udr\u017eovat", "VERB", [8, 15]], ["SV\u011a\u017dEST", "sv\u011b\u017eest", "NOUN", [16, 23]], [".", ".", "PUNCT", [23, 24]]]], ["calgarske-listy_2003_unor_ocr.txt", "D\u00edky pravideln\u00fdm orgasm\u016fm z\u016fst\u00e1v\u00e1 prostata elastick\u00e1 a zabra\u0148uje se tak typick\u00fdm mu\u017esk\u00fdm probl\u00e9m\u016fm s prostatou.", [["D\u00edky", "d\u00edky", "ADP", [0, 4]], ["pravideln\u00fdm", "pravideln\u00fd", "ADJ", [5, 16]], ["orgasm\u016fm", "orgasmus", "NOUN", [17, 25]], ["z\u016fst\u00e1v\u00e1", "z\u016fst\u00e1vat", "VERB", [26, 33]], ["prostata", "prostata", "NOUN", [34, 42]], ["elastick\u00e1", "elastick\u00fd", "ADJ", [43, 52]], ["a", "a", "CCONJ", [53, 54]], ["zabra\u0148uje", "zabra\u0148ovat", "VERB", [55, 64]], ["se", "se", "PRON", [65, 67]], ["tak", "tak", "ADV", [68, 71]], ["typick\u00fdm", "typick\u00fd", "ADJ", [72, 80]], ["mu\u017esk\u00fdm", "mu\u017esk\u00fd", "ADJ", [81, 88]], ["probl\u00e9m\u016fm", "probl\u00e9m", "NOUN", [89, 98]], ["s", "s", "ADP", [99, 100]], ["prostatou", "prostata", "NOUN", [101, 110]], [".", ".", "PUNCT", [110, 111]]]], ["calgarske-listy_2003_unor_ocr.txt", "Studie potvrzuj\u00ed, \u017ee lid\u00e9 s \u010dil\u00fdm sexu\u00e1ln\u00edm \u017eivotem vypadaj\u00ed a\u017e o deset let mlad\u0161\u00ed, ne\u017e jejich l\u00edn\u011bj\u0161\u00ed vrstevn\u00edci.", [["Studie", "studie", "NOUN", [0, 6]], ["potvrzuj\u00ed", "potvrzovat", "VERB", [7, 16]], [",", ",", "PUNCT", [16, 17]], ["\u017ee", "\u017ee", "SCONJ", [18, 20]], ["lid\u00e9", "lid\u00e9", "NOUN", [21, 25]], ["s", "s", "ADP", [26, 27]], ["\u010dil\u00fdm", "\u010dil\u00fd", "ADJ", [28, 33]], ["sexu\u00e1ln\u00edm", "sexu\u00e1ln\u00ed", "ADJ", [34, 43]], ["\u017eivotem", "\u017eivot", "NOUN", [44, 51]], ["vypadaj\u00ed", "vypadat", "VERB", [52, 60]], ["a\u017e", "a\u017e", "PART", [61, 63]], ["o", "o", "ADP", [64, 65]], ["deset", "deset", "NUM", [66, 71]], ["let", "l\u00e9ta", "NOUN", [72, 75]], ["mlad\u0161\u00ed", "mlad\u00fd", "ADJ", [76, 82]], [",", ",", "PUNCT", [82, 83]], ["ne\u017e", "ne\u017e", "SCONJ", [84, 87]], ["jejich", "jeho", "DET", [88, 94]], ["l\u00edn\u011bj\u0161\u00ed", "l\u00edn\u011bj\u0161\u00ed", "ADJ", [95, 102]], ["vrstevn\u00edci", "vrstevn\u00edk", "NOUN", [103, 113]], [".", ".", "PUNCT", [113, 114]]]], ["calgarske-listy_2003_unor_ocr.txt", "Krom\u011b toho sex podporuje udr\u017eov\u00e1n\u00ed hormon\u00e1ln\u00ed rovnov\u00e1hy, n\u00e1sledkem \u010deho\u017e nast\u00e1v\u00e1 u \u017een pozd\u011bji menopauza.", [["Krom\u011b", "krom\u011b", "ADP", [0, 5]], ["toho", "ten", "DET", [6, 10]], ["sex", "sex", "NOUN", [11, 14]], ["podporuje", "podporovat", "VERB", [15, 24]], ["udr\u017eov\u00e1n\u00ed", "udr\u017eov\u00e1n\u00ed", "NOUN", [25, 34]], ["hormon\u00e1ln\u00ed", "hormon\u00e1ln\u00ed", "ADJ", [35, 45]], ["rovnov\u00e1hy", "rovnov\u00e1ha", "NOUN", [46, 55]], [",", ",", "PUNCT", [55, 56]], ["n\u00e1sledkem", "n\u00e1sledek", "NOUN", [57, 66]], ["\u010deho\u017e", "co\u017e", "PRON", [67, 72]], ["nast\u00e1v\u00e1", "nast\u00e1vat", "VERB", [73, 80]], ["u", "u", "ADP", [81, 82]], ["\u017een", "\u017eena", "NOUN", [83, 86]], ["pozd\u011bji", "pozd\u011b", "ADV", [87, 94]], ["menopauza", "menopauzo", "NOUN", [95, 104]], [".", ".", "PUNCT", [104, 105]]]], ["calgarske-listy_2003_unor_ocr.txt", "9. / SEX D\u011aL\u00c1 DOBROU POSTAVU.", [["9", "9", "NUM", [0, 1]], [".", ".", "PUNCT", [1, 2]], ["/", "/", "PUNCT", [3, 4]], ["SEX", "Sex", "NOUN", [5, 8]], ["D\u011aL\u00c1", "d\u011blat", "VERB", [9, 13]], ["DOBROU", "dobr\u00fd", "ADJ", [14, 20]], ["POSTAVU", "postava", "NOUN", [21, 28]], [".", ".", "PUNCT", [28, 29]]]], ["calgarske-listy_2003_unor_ocr.txt", "Na \u017eeb\u0159\u00ed\u010dku p\u0159\u00edpravk\u016f na hubnut\u00ed se sex nach\u00e1z\u00ed zcela na vrcholu: p\u0159\u00edjemn\u011bj\u0161\u00edm zp\u016fsobem se 200 kalori\u00ed za 20 minut snad ani ned\u00e1 sp\u00e1lit.", [["Na", "na", "ADP", [0, 2]], ["\u017eeb\u0159\u00ed\u010dku", "\u017eeb\u0159\u00ed\u010dek", "NOUN", [3, 11]], ["p\u0159\u00edpravk\u016f", "p\u0159\u00edpravek", "NOUN", [12, 21]], ["na", "na", "ADP", [22, 24]], ["hubnut\u00ed", "hubnut\u00ed", "NOUN", [25, 32]], ["se", "se", "PRON", [33, 35]], ["sex", "sex", "NOUN", [36, 39]], ["nach\u00e1z\u00ed", "nach\u00e1zet", "VERB", [40, 47]], ["zcela", "zcela", "ADV", [48, 53]], ["na", "na", "ADP", [54, 56]], ["vrcholu", "vrchol", "NOUN", [57, 64]], [":", ":", "PUNCT", [64, 65]], ["p\u0159\u00edjemn\u011bj\u0161\u00edm", "p\u0159\u00edjemn\u00fd", "ADJ", [66, 78]], ["zp\u016fsobem", "zp\u016fsob", "NOUN", [79, 87]], ["se", "se", "PRON", [88, 90]], ["200", "200", "NUM", [91, 94]], ["kalori\u00ed", "kalorie", "NOUN", [95, 102]], ["za", "za", "ADP", [103, 105]], ["20", "20", "NUM", [106, 108]], ["minut", "minuta", "NOUN", [109, 114]], ["snad", "snad", "PART", [115, 119]], ["ani", "ani", "CCONJ", [120, 123]], ["ned\u00e1", "d\u00e1t", "VERB", [124, 128]], ["sp\u00e1lit", "sp\u00e1lit", "VERB", [129, 135]], [".", ".", "PUNCT", [135, 136]]]], ["calgarske-listy_2003_unor_ocr.txt", "Ale to nen\u00ed v\u0161echno!", [["Ale", "ale", "CCONJ", [0, 3]], ["to", "ten", "DET", [4, 6]], ["nen\u00ed", "b\u00fdt", "AUX", [7, 11]], ["v\u0161echno", "v\u0161echen", "DET", [12, 19]], ["!", "!", "PUNCT", [19, 20]]]], ["calgarske-listy_2003_unor_ocr.txt", "Pokud se \u017eena dostane do opravdov\u00e9 ext\u00e1ze, zv\u011bt\u0161\u00ed se j\u00ed objem nad\u011br a\u017e o \u010dtvrtinu.", [["Pokud", "pokud", "SCONJ", [0, 5]], ["se", "se", "PRON", [6, 8]], ["\u017eena", "\u017eena", "NOUN", [9, 13]], ["dostane", "dostat", "VERB", [14, 21]], ["do", "do", "ADP", [22, 24]], ["opravdov\u00e9", "opravdov\u00fd", "ADJ", [25, 34]], ["ext\u00e1ze", "ext\u00e1ze", "NOUN", [35, 41]], [",", ",", "PUNCT", [41, 42]], ["zv\u011bt\u0161\u00ed", "zv\u011bt", "VERB", [43, 49]], ["se", "se", "PRON", [50, 52]], ["j\u00ed", "on", "PRON", [53, 55]], ["objem", "objem", "NOUN", [56, 61]], ["nad\u011br", "nad\u011br", "NOUN", [62, 67]], ["a\u017e", "a\u017e", "PART", [68, 70]], ["o", "o", "ADP", [71, 72]], ["\u010dtvrtinu", "\u010dtvrtina", "NOUN", [73, 81]], [".", ".", "PUNCT", [81, 82]]]], ["calgarske-listy_2003_unor_ocr.txt", "P\u0159\u00edsun estrogenu udr\u017euje poko\u017eku hladkou a elastickou.", [["P\u0159\u00edsun", "p\u0159\u00edsun", "NOUN", [0, 6]], ["estrogenu", "estrogen", "NOUN", [7, 16]], ["udr\u017euje", "udr\u017eovat", "VERB", [17, 24]], ["poko\u017eku", "poko\u017eek", "NOUN", [25, 32]], ["hladkou", "hladk\u00fd", "ADJ", [33, 40]], ["a", "a", "CCONJ", [41, 42]], ["elastickou", "elastick\u00fd", "ADJ", [43, 53]], [".", ".", "PUNCT", [53, 54]]]], ["calgarske-listy_2003_unor_ocr.txt", "Krom\u011b toho sex p\u016fsob\u00ed jako z\u00e1zra\u010dn\u00e9 preventivn\u00ed opat\u0159en\u00ed proti k\u0159e\u010dov\u00fdm \u017eil\u00e1m a celulitid\u011b.", [["Krom\u011b", "krom\u011b", "ADP", [0, 5]], ["toho", "ten", "DET", [6, 10]], ["sex", "sex", "NOUN", [11, 14]], ["p\u016fsob\u00ed", "p\u016fsobit", "VERB", [15, 21]], ["jako", "jako", "SCONJ", [22, 26]], ["z\u00e1zra\u010dn\u00e9", "z\u00e1zra\u010dn\u00fd", "ADJ", [27, 35]], ["preventivn\u00ed", "preventivn\u00ed", "ADJ", [36, 47]], ["opat\u0159en\u00ed", "opat\u0159en\u00ed", "NOUN", [48, 56]], ["proti", "proti", "ADP", [57, 62]], ["k\u0159e\u010dov\u00fdm", "k\u0159e\u010dov\u00fd", "ADJ", [63, 71]], ["\u017eil\u00e1m", "\u017eila", "NOUN", [72, 77]], ["a", "a", "CCONJ", [78, 79]], ["celulitid\u011b", "celulitida", "NOUN", [80, 90]], [".", ".", "PUNCT", [90, 91]]]], ["calgarske-listy_2003_unor_ocr.txt", "10. / SEX ZAH\u00c1N\u00cd STRAST.", [["10", "10", "NUM", [0, 2]], [".", ".", "PUNCT", [2, 3]], ["/", "/", "PUNCT", [4, 5]], ["SEX", "Sex", "NOUN", [6, 9]], ["ZAH\u00c1N\u00cd", "zah\u00e1n\u00ed", "NOUN", [10, 16]], ["STRAST", "strast", "NOUN", [17, 23]], [".", ".", "PUNCT", [23, 24]]]], ["calgarske-listy_2003_unor_ocr.txt", "Rozko\u0161 vh\u00e1n\u00ed do t\u011bla \"pocit \u0161t\u011bst\u00ed\" p\u0159in\u00e1\u0161ej\u00edc l\u00e1tky serotonin a dopamin.", [["Rozko\u0161", "rozko\u0161", "NOUN", [0, 6]], ["vh\u00e1n\u00ed", "vh\u00e1n\u011bt", "VERB", [7, 12]], ["do", "do", "ADP", [13, 15]], ["t\u011bla", "t\u011blo", "NOUN", [16, 20]], ["\"", "\"", "PUNCT", [21, 22]], ["pocit", "pocit", "NOUN", [22, 27]], ["\u0161t\u011bst\u00ed", "\u0161t\u011bst\u00ed", "NOUN", [28, 34]], ["\"", "\"", "PUNCT", [34, 35]], ["p\u0159in\u00e1\u0161ej\u00edc", "p\u0159in\u00e1\u0161et", "VERB", [36, 46]], ["l\u00e1tky", "l\u00e1tka", "NOUN", [47, 52]], ["serotonin", "serotonina", "NOUN", [53, 62]], ["a", "a", "CCONJ", [63, 64]], ["dopamin", "dopamina", "NOUN", [65, 72]], [".", ".", "PUNCT", [72, 73]]]], ["calgarske-listy_2003_unor_ocr.txt", "Ty potla\u010duj\u00ed \u0161patnou n\u00e1ladu a beznad\u011bj.", [["Ty", "ten", "DET", [0, 2]], ["potla\u010duj\u00ed", "potla\u010dovat", "VERB", [3, 12]], ["\u0161patnou", "\u0161patn\u00fd", "ADJ", [13, 20]], ["n\u00e1ladu", "n\u00e1lada", "NOUN", [21, 27]], ["a", "a", "CCONJ", [28, 29]], ["beznad\u011bj", "beznad\u011bj", "NOUN", [30, 38]], [".", ".", "PUNCT", [38, 39]]]], ["calgarske-listy_2003_unor_ocr.txt", "Promilovan\u00e1 noc u\u010din\u00ed konec otravn\u00fdm v\u0161edn\u00edm probl\u00e9m\u016fm.", [["Promilovan\u00e1", "promilovan\u00fd", "ADJ", [0, 11]], ["noc", "noc", "NOUN", [12, 15]], ["u\u010din\u00ed", "u\u010dinit", "VERB", [16, 21]], ["konec", "konec", "NOUN", [22, 27]], ["otravn\u00fdm", "otravn\u00fd", "ADJ", [28, 36]], ["v\u0161edn\u00edm", "v\u0161edn\u00ed", "ADJ", [37, 44]], ["probl\u00e9m\u016fm", "probl\u00e9m", "NOUN", [45, 54]], [".", ".", "PUNCT", [54, 55]]]], ["calgarske-listy_2003_unor_ocr.txt", "11. / SEX U\u0160ET\u0158\u00cd VITAMINOV\u00c9 TABLETY.", [["11", "11", "NUM", [0, 2]], [".", ".", "PUNCT", [2, 3]], ["/", "/", "PUNCT", [4, 5]], ["SEX", "Sex", "NOUN", [6, 9]], ["U\u0160ET\u0158\u00cd", "u\u0161et\u0159it", "VERB", [10, 16]], ["VITAMINOV\u00c9", "vitaminov\u00fd", "ADJ", [17, 27]], ["TABLETY", "tablet", "NOUN", [28, 35]], [".", ".", "PUNCT", [35, 36]]]], ["calgarske-listy_2003_unor_ocr.txt", "Noc pln\u00e1 sexu m\u00e1 dlouhodob\u00fd efekt, kter\u00fd se projev\u00ed pos\u00edlen\u00edm imunitn\u00edho syst\u00e9mu.", [["Noc", "noc", "NOUN", [0, 3]], ["pln\u00e1", "pln\u00fd", "ADJ", [4, 8]], ["sexu", "sex", "NOUN", [9, 13]], ["m\u00e1", "m\u00edt", "VERB", [14, 16]], ["dlouhodob\u00fd", "dlouhodob\u00fd", "ADJ", [17, 27]], ["efekt", "efekt", "NOUN", [28, 33]], [",", ",", "PUNCT", [33, 34]], ["kter\u00fd", "kter\u00fd", "DET", [35, 40]], ["se", "se", "PRON", [41, 43]], ["projev\u00ed", "projevit", "VERB", [44, 51]], ["pos\u00edlen\u00edm", "pos\u00edlen\u00ed", "NOUN", [52, 61]], ["imunitn\u00edho", "imunitn\u00ed", "ADJ", [62, 72]], ["syst\u00e9mu", "syst\u00e9m", "NOUN", [73, 80]], [".", ".", "PUNCT", [80, 81]]]], ["calgarske-listy_2003_unor_ocr.txt", "Oxytocin omezuje p\u016fsoben\u00ed stresov\u00e9ho hormonu kortizolu.", [["Oxytocin", "oxytocin", "NOUN", [0, 8]], ["omezuje", "omezovat", "VERB", [9, 16]], ["p\u016fsoben\u00ed", "p\u016fsoben\u00ed", "NOUN", [17, 25]], ["stresov\u00e9ho", "stresov\u00fd", "ADJ", [26, 36]], ["hormonu", "hormon", "NOUN", [37, 44]], ["kortizolu", "kortizol", "NOUN", [45, 54]], [".", ".", "PUNCT", [54, 55]]]], ["calgarske-listy_2003_unor_ocr.txt", "T\u011blo vytv\u00e1\u0159\u00ed v\u00edce b\u00edl\u00fdch krvinek.", [["T\u011blo", "t\u011blo", "NOUN", [0, 4]], ["vytv\u00e1\u0159\u00ed", "vytv\u00e1\u0159et", "VERB", [5, 12]], ["v\u00edce", "v\u00edce", "ADV", [13, 17]], ["b\u00edl\u00fdch", "b\u00edl\u00fd", "ADJ", [18, 24]], ["krvinek", "krvinka", "NOUN", [25, 32]], [".", ".", "PUNCT", [32, 33]]]], ["calgarske-listy_2003_unor_ocr.txt", "Ameri\u010dt\u00ed v\u011bdci doporu\u010duj\u00ed sex dvakr\u00e1t t\u00fddn\u011b, \u010d\u00edm\u017e se u\u0161et\u0159\u00ed na p\u0159\u00edpadn\u00e9m u\u017e\u00edv\u00e1n\u00ed vitaminov\u00fdch tabletek.", [["Ameri\u010dt\u00ed", "americk\u00fd", "ADJ", [0, 8]], ["v\u011bdci", "v\u011bdec", "NOUN", [9, 14]], ["doporu\u010duj\u00ed", "doporu\u010dovat", "VERB", [15, 25]], ["sex", "sex", "NOUN", [26, 29]], ["dvakr\u00e1t", "dvakr\u00e1t", "ADV", [30, 37]], ["t\u00fddn\u011b", "t\u00fddn\u011b", "ADV", [38, 43]], [",", ",", "PUNCT", [43, 44]], ["\u010d\u00edm\u017e", "co\u017e", "PRON", [45, 49]], ["se", "se", "PRON", [50, 52]], ["u\u0161et\u0159\u00ed", "u\u0161et\u0159it", "VERB", [53, 59]], ["na", "na", "ADP", [60, 62]], ["p\u0159\u00edpadn\u00e9m", "p\u0159\u00edpadn\u00fd", "ADJ", [63, 72]], ["u\u017e\u00edv\u00e1n\u00ed", "u\u017e\u00edv\u00e1n\u00ed", "NOUN", [73, 80]], ["vitaminov\u00fdch", "vitaminov\u00fd", "ADJ", [81, 93]], ["tabletek", "tabletka", "NOUN", [94, 102]], [".", ".", "PUNCT", [102, 103]]]], ["calgarske-listy_2003_unor_ocr.txt", "12. / SEX D\u011aL\u00c1 SEXY.", [["12", "12", "NUM", [0, 2]], [".", ".", "PUNCT", [2, 3]], ["/", "/", "PUNCT", [4, 5]], ["SEX", "Sex", "NOUN", [6, 9]], ["D\u011aL\u00c1", "d\u011blat", "VERB", [10, 14]], ["SEXY", "Sexa", "PROPN", [15, 19]], [".", ".", "PUNCT", [19, 20]]]], ["calgarske-listy_2003_unor_ocr.txt", "Sex d\u011bl\u00e1 sv\u016fdn\u00fdm!", [["Sex", "sex", "NOUN", [0, 3]], ["d\u011bl\u00e1", "d\u011blat", "VERB", [4, 8]], ["sv\u016fdn\u00fdm", "sv\u016fdn\u00fd", "ADJ", [9, 16]], ["!", "!", "PUNCT", [16, 17]]]], ["calgarske-listy_2003_unor_ocr.txt", "Erotick\u00fd \u0161arm toti\u017e poch\u00e1z\u00ed z pro\u017eit\u00e9 ext\u00e1ze a nikoliv z kosmetick\u00fdch salon\u016f.", [["Erotick\u00fd", "erotick\u00fd", "ADJ", [0, 8]], ["\u0161arm", "\u0161arm", "NOUN", [9, 13]], ["toti\u017e", "toti\u017e", "CCONJ", [14, 19]], ["poch\u00e1z\u00ed", "poch\u00e1zet", "VERB", [20, 27]], ["z", "z", "ADP", [28, 29]], ["pro\u017eit\u00e9", "pro\u017eit\u00fd", "ADJ", [30, 37]], ["ext\u00e1ze", "ext\u00e1ze", "NOUN", [38, 44]], ["a", "a", "CCONJ", [45, 46]], ["nikoliv", "nikoliv", "PART", [47, 54]], ["z", "z", "ADP", [55, 56]], ["kosmetick\u00fdch", "kosmetick\u00fd", "ADJ", [57, 69]], ["salon\u016f", "salon", "NOUN", [70, 76]], [".", ".", "PUNCT", [76, 77]]]], ["calgarske-listy_2003_unor_ocr.txt", "Osmn\u00e1ctkr\u00e1t siln\u011bj\u0161\u00ed prokrven\u00ed odstra\u0148uje ne\u010distoty na k\u016f\u017ei a vyhlazuje vr\u00e1sky.", [["Osmn\u00e1ctkr\u00e1t", "osmn\u00e1ctkr\u00e1t", "ADJ", [0, 11]], ["siln\u011bj\u0161\u00ed", "siln\u00fd", "ADJ", [12, 20]], ["prokrven\u00ed", "prokrven\u00ed", "NOUN", [21, 30]], ["odstra\u0148uje", "odstra\u0148ovat", "VERB", [31, 41]], ["ne\u010distoty", "ne\u010distota", "NOUN", [42, 51]], ["na", "na", "ADP", [52, 54]], ["k\u016f\u017ei", "k\u016f\u017ee", "NOUN", [55, 59]], ["a", "a", "CCONJ", [60, 61]], ["vyhlazuje", "vyhlazovat", "VERB", [62, 71]], ["vr\u00e1sky", "vr\u00e1ska", "NOUN", [72, 78]], [".", ".", "PUNCT", [78, 79]]]], ["calgarske-listy_2003_unor_ocr.txt", "tak sakra, co tu je\u0161t\u011b d\u011bl\u00e1te u toho \u010dten\u00ed ?????????????", [["tak", "tak", "ADV", [0, 3]], ["sakra", "sakra", "INTJ", [4, 9]], [",", ",", "PUNCT", [9, 10]], ["co", "co", "PRON", [11, 13]], ["tu", "tu", "ADV", [14, 16]], ["je\u0161t\u011b", "je\u0161t\u011b", "ADV", [17, 22]], ["d\u011bl\u00e1te", "d\u011blat", "VERB", [23, 29]], ["u", "u", "ADP", [30, 31]], ["toho", "ten", "DET", [32, 36]], ["\u010dten\u00ed", "\u010dten\u00ed", "NOUN", [37, 42]], ["?", "?", "PUNCT", [43, 44]], ["?", "?", "PUNCT", [44, 45]], ["?", "?", "PUNCT", [45, 46]], ["?", "?", "PUNCT", [46, 47]], ["?", "?", "PUNCT", [47, 48]], ["?", "?", "PUNCT", [48, 49]], ["?", "?", "PUNCT", [49, 50]], ["?", "?", "PUNCT", [50, 51]], ["?", "?", "PUNCT", [51, 52]], ["?", "?", "PUNCT", [52, 53]], ["?", "?", "PUNCT", [53, 54]], ["?", "?", "PUNCT", [54, 55]], ["?", "?", "PUNCT", [55, 56]]]], ["calgarske-listy_2003_unor_ocr.txt", "Zjistil jsem, jak nejl\u00e9pe nau\u010dit svoji \u017eenu opatrn\u011bji \u0159\u00eddit auto.", [["Zjistil", "zjistit", "VERB", [0, 7]], ["jsem", "b\u00fdt", "AUX", [8, 12]], [",", ",", "PUNCT", [12, 13]], ["jak", "jak", "ADV", [14, 17]], ["nejl\u00e9pe", "l\u00e9pe", "ADV", [18, 25]], ["nau\u010dit", "nau\u010dit", "VERB", [26, 32]], ["svoji", "sv\u016fj", "DET", [33, 38]], ["\u017eenu", "\u017eena", "NOUN", [39, 43]], ["opatrn\u011bji", "opatrn\u011b", "ADV", [44, 53]], ["\u0159\u00eddit", "\u0159\u00eddit", "VERB", [54, 59]], ["auto", "auto", "NOUN", [60, 64]], [".", ".", "PUNCT", [64, 65]]]], ["calgarske-listy_2003_unor_ocr.txt", "\u0158ekl jsem j\u00ed, \u017ee kdyby se n\u011bkdy stala \u00fa\u010dastnic\u00ed nehody, tak v novin\u00e1ch nap\u00ed\u0161ou jej\u00ed skute\u010dn\u00fd v\u011bk.", [["\u0158ekl", "\u0159\u00edci", "VERB", [0, 4]], ["jsem", "b\u00fdt", "AUX", [5, 9]], ["j\u00ed", "on", "PRON", [10, 12]], [",", ",", "PUNCT", [12, 13]], ["\u017ee", "\u017ee", "SCONJ", [14, 16]], ["kdy\u017e", "kdy\u017e", "SCONJ", [-42655, -42655]], ["by", "b\u00fdt", "AUX", [-42655, -42655]], ["se", "se", "PRON", [23, 25]], ["n\u011bkdy", "n\u011bkdy", "ADV", [26, 31]], ["stala", "st\u00e1t", "VERB", [32, 37]], ["\u00fa\u010dastnic\u00ed", "\u00fa\u010dastnice", "NOUN", [38, 47]], ["nehody", "nehoda", "NOUN", [48, 54]], [",", ",", "PUNCT", [54, 55]], ["tak", "tak", "ADV", [56, 59]], ["v", "v", "ADP", [60, 61]], ["novin\u00e1ch", "noviny", "NOUN", [62, 70]], ["nap\u00ed\u0161ou", "napsat", "VERB", [71, 78]], ["jej\u00ed", "jeho", "DET", [79, 83]], ["skute\u010dn\u00fd", "skute\u010dn\u00fd", "ADJ", [84, 92]], ["v\u011bk", "v\u011bk", "NOUN", [93, 96]], [".", ".", "PUNCT", [96, 97]]]], ["calgarske-listy_2003_unor_ocr.txt", "Mal\u00fd Kenny, kter\u00fd se p\u0159ist\u011bhoval na venkov si koupil od star\u00e9ho farm\u00e1\u0159e osl\u00edka za 100 $.", [["Mal\u00fd", "mal\u00fd", "ADJ", [0, 4]], ["Kenny", "Kenny", "PROPN", [5, 10]], [",", ",", "PUNCT", [10, 11]], ["kter\u00fd", "kter\u00fd", "DET", [12, 17]], ["se", "se", "PRON", [18, 20]], ["p\u0159ist\u011bhoval", "p\u0159ist\u011bhovat", "VERB", [21, 32]], ["na", "na", "ADP", [33, 35]], ["venkov", "venkov", "NOUN", [36, 42]], ["si", "se", "PRON", [43, 45]], ["koupil", "koupit", "VERB", [46, 52]], ["od", "od", "ADP", [53, 55]], ["star\u00e9ho", "star\u00fd", "ADJ", [56, 63]], ["farm\u00e1\u0159e", "farm\u00e1\u0159", "NOUN", [64, 71]], ["osl\u00edka", "osl\u00edk", "NOUN", [72, 78]], ["za", "za", "ADP", [79, 81]], ["100", "100", "NUM", [82, 85]], ["$", "$", "NOUN", [86, 87]], [".", ".", "PUNCT", [87, 88]]]], ["calgarske-listy_2003_unor_ocr.txt", "Farm\u00e1\u0159 sl\u00edbil, \u017ee p\u0159ivede osl\u00edka p\u0159\u00ed\u0161t\u00ed den.", [["Farm\u00e1\u0159", "farm\u00e1\u0159", "NOUN", [0, 6]], ["sl\u00edbil", "sl\u00edbit", "VERB", [7, 13]], [",", ",", "PUNCT", [13, 14]], ["\u017ee", "\u017ee", "SCONJ", [15, 17]], ["p\u0159ivede", "p\u0159iv\u00e9st", "VERB", [18, 25]], ["osl\u00edka", "osl\u00edk", "NOUN", [26, 32]], ["p\u0159\u00ed\u0161t\u00ed", "p\u0159\u00ed\u0161t\u00ed", "ADJ", [33, 39]], ["den", "den", "NOUN", [40, 43]], [".", ".", "PUNCT", [43, 44]]]], ["calgarske-listy_2003_unor_ocr.txt", "Na druh\u00fd den farm\u00e1\u0159 p\u0159ijel a pov\u00edd\u00e1 mal\u00e9mu Kennovi.", [["Na", "na", "ADP", [0, 2]], ["druh\u00fd", "druh\u00fd", "ADJ", [3, 8]], ["den", "den", "NOUN", [9, 12]], ["farm\u00e1\u0159", "farm\u00e1\u0159", "NOUN", [13, 19]], ["p\u0159ijel", "p\u0159ijet", "VERB", [20, 26]], ["a", "a", "CCONJ", [27, 28]], ["pov\u00edd\u00e1", "pov\u00eddat", "VERB", [29, 35]], ["mal\u00e9mu", "mal\u00fd", "ADJ", [36, 42]], ["Kennovi", "Kenn", "PROPN", [43, 50]], [".", ".", "PUNCT", [50, 51]]]], ["calgarske-listy_2003_unor_ocr.txt", "\"Je mi to l\u00edto synku, ale m\u00e1m pro Tebe \u0161patnou spr\u00e1vu, osl\u00edk po\u0161el.\"", [["\"", "\"", "PUNCT", [0, 1]], ["Je", "b\u00fdt", "AUX", [1, 3]], ["mi", "j\u00e1", "PRON", [4, 6]], ["to", "ten", "DET", [7, 9]], ["l\u00edto", "l\u00edto", "ADV", [10, 14]], ["synku", "synek", "NOUN", [15, 20]], [",", ",", "PUNCT", [20, 21]], ["ale", "ale", "CCONJ", [22, 25]], ["m\u00e1m", "m\u00edt", "VERB", [26, 29]], ["pro", "pro", "ADP", [30, 33]], ["Tebe", "tebe", "NOUN", [34, 38]], ["\u0161patnou", "\u0161patn\u00fd", "ADJ", [39, 46]], ["spr\u00e1vu", "spr\u00e1va", "NOUN", [47, 53]], [",", ",", "PUNCT", [53, 54]], ["osl\u00edk", "osl\u00edk", "NOUN", [55, 60]], ["po\u0161el", "poj\u00edt", "VERB", [61, 66]], [".", ".", "PUNCT", [66, 67]], ["\"", "\"", "PUNCT", [67, 68]]]], ["calgarske-listy_2003_unor_ocr.txt", "\"Tak mi vra\u0165te pen\u00edze.\" pov\u00edd\u00e1 mal\u00fd Kenny.", [["\"", "\"", "PUNCT", [0, 1]], ["Tak", "tak", "ADV", [1, 4]], ["mi", "j\u00e1", "PRON", [5, 7]], ["vra\u0165te", "vr\u00e1tit", "VERB", [8, 14]], ["pen\u00edze", "pen\u00edze", "NOUN", [15, 21]], [".", ".", "PUNCT", [21, 22]], ["\"", "\"", "PUNCT", [22, 23]], ["pov\u00edd\u00e1", "pov\u00eddat", "VERB", [24, 30]], ["mal\u00fd", "mal\u00fd", "ADJ", [31, 35]], ["Kenny", "Kenny", "PROPN", [36, 41]], [".", ".", "PUNCT", [41, 42]]]], ["calgarske-listy_2003_unor_ocr.txt", "Ale farm\u00e1\u0159 na to: J\u00e1 nemohu, u\u017e jsem je v\u0161echny utratil.\"", [["Ale", "ale", "CCONJ", [0, 3]], ["farm\u00e1\u0159", "farm\u00e1\u0159", "NOUN", [4, 10]], ["na", "na", "ADP", [11, 13]], ["to", "ten", "DET", [14, 16]], [":", ":", "PUNCT", [16, 17]], ["J\u00e1", "j\u00e1", "PRON", [18, 20]], ["nemohu", "moci", "VERB", [21, 27]], [",", ",", "PUNCT", [27, 28]], ["u\u017e", "u\u017e", "ADV", [29, 31]], ["jsem", "b\u00fdt", "AUX", [32, 36]], ["je", "on", "PRON", [37, 39]], ["v\u0161echny", "v\u0161echen", "DET", [40, 47]], ["utratil", "utratit", "VERB", [48, 55]], [".", ".", "PUNCT", [55, 56]], ["\"", "\"", "PUNCT", [56, 57]]]], ["calgarske-listy_2003_unor_ocr.txt", "Inu dobr\u00e1, tak toho osl\u00edka m\u016f\u017eete slo\u017eit.\"", [["Inu", "inu", "INTJ", [0, 3]], ["dobr\u00e1", "dobr\u00fd", "ADJ", [4, 9]], [",", ",", "PUNCT", [9, 10]], ["tak", "tak", "ADV", [11, 14]], ["toho", "ten", "DET", [15, 19]], ["osl\u00edka", "osl\u00edk", "NOUN", [20, 26]], ["m\u016f\u017eete", "moci", "VERB", [27, 33]], ["slo\u017eit", "slo\u017eit", "VERB", [34, 40]], [".", ".", "PUNCT", [40, 41]], ["\"", "\"", "PUNCT", [41, 42]]]], ["calgarske-listy_2003_unor_ocr.txt", "Farm\u00e1\u0159 se ale hned zeptal \"", [["Farm\u00e1\u0159", "farm\u00e1\u0159", "NOUN", [0, 6]], ["se", "se", "PRON", [7, 9]], ["ale", "ale", "CCONJ", [10, 13]], ["hned", "hned", "ADV", [14, 18]], ["zeptal", "zeptat", "VERB", [19, 25]], ["\"", "\"", "PUNCT", [26, 27]]]], ["calgarske-listy_2003_unor_ocr.txt", "Co s t\u00edm osl\u00edkem bude\u0161 d\u011blat?\"", [["Co", "co", "PRON", [0, 2]], ["s", "s", "ADP", [3, 4]], ["t\u00edm", "ten", "DET", [5, 8]], ["osl\u00edkem", "osl\u00edk", "NOUN", [9, 16]], ["bude\u0161", "b\u00fdt", "AUX", [17, 22]], ["d\u011blat", "d\u011blat", "VERB", [23, 28]], ["?", "?", "PUNCT", [28, 29]], ["\"", "\"", "PUNCT", [29, 30]]]], ["calgarske-listy_2003_unor_ocr.txt", "Kenny na to, \"Vydra\u017e\u00edm ho v loterii\".", [["Kenny", "Kenny", "PROPN", [0, 5]], ["na", "na", "ADP", [6, 8]], ["to", "ten", "DET", [9, 11]], [",", ",", "PUNCT", [11, 12]], ["\"", "\"", "PUNCT", [13, 14]], ["Vydra\u017e\u00edm", "vydra\u017eit", "VERB", [14, 22]], ["ho", "on", "PRON", [23, 25]], ["v", "v", "ADP", [26, 27]], ["loterii", "loterie", "NOUN", [28, 35]], ["\"", "\"", "PUNCT", [35, 36]], [".", ".", "PUNCT", [36, 37]]]], ["calgarske-listy_2003_unor_ocr.txt", "\"P\u0159eci nem\u016f\u017ee\u0161 vydra\u017eit mrtv\u00e9ho osla\" div\u00ed se farm\u00e1\u0159.", [["\"", "\"", "PUNCT", [0, 1]], ["P\u0159eci", "p\u0159eci", "PART", [1, 6]], ["nem\u016f\u017ee\u0161", "moci", "VERB", [7, 14]], ["vydra\u017eit", "vydra\u017eit", "VERB", [15, 23]], ["mrtv\u00e9ho", "mrtv\u00fd", "ADJ", [24, 31]], ["osla", "osel", "NOUN", [32, 36]], ["\"", "\"", "PUNCT", [36, 37]], ["div\u00ed", "divit", "VERB", [38, 42]], ["se", "se", "PRON", [43, 45]], ["farm\u00e1\u0159", "farm\u00e1\u0159", "NOUN", [46, 52]], [".", ".", "PUNCT", [52, 53]]]], ["calgarske-listy_2003_unor_ocr.txt", "Kenny, \" To je hotovka \u017ee mohu.", [["Kenny", "Kenny", "PROPN", [0, 5]], [",", ",", "PUNCT", [5, 6]], ["\"", "\"", "PUNCT", [7, 8]], ["To", "ten", "DET", [9, 11]], ["je", "b\u00fdt", "AUX", [12, 14]], ["hotovka", "hotovka", "NOUN", [15, 22]], ["\u017ee", "\u017ee", "SCONJ", [23, 25]], ["mohu", "moci", "VERB", [26, 30]], [".", ".", "PUNCT", [30, 31]]]], ["calgarske-listy_2003_unor_ocr.txt", "J\u00e1 ale nikomu nebudu \u0159\u00edkat \u017ee je mrtv\u00fd.", [["J\u00e1", "j\u00e1", "PRON", [0, 2]], ["ale", "ale", "CCONJ", [3, 6]], ["nikomu", "nikdo", "PRON", [7, 13]], ["nebudu", "b\u00fdt", "AUX", [14, 20]], ["\u0159\u00edkat", "\u0159\u00edkat", "VERB", [21, 26]], ["\u017ee", "\u017ee", "SCONJ", [27, 29]], ["je", "b\u00fdt", "AUX", [30, 32]], ["mrtv\u00fd", "mrtv\u00fd", "ADJ", [33, 38]], [".", ".", "PUNCT", [38, 39]]]], ["calgarske-listy_2003_unor_ocr.txt", "\" Asi za m\u011bs\u00edc pozd\u011bji potk\u00e1 farm\u00e1\u0159 Kennyho a pt\u00e1 se: \"Tak jak to dopadlo s t\u00edm mrtv\u00fdm oslem?", [["\"", "\"", "PUNCT", [0, 1]], ["Asi", "asi", "PART", [2, 5]], ["za", "za", "ADP", [6, 8]], ["m\u011bs\u00edc", "m\u011bs\u00edc", "NOUN", [9, 14]], ["pozd\u011bji", "pozd\u011b", "ADV", [15, 22]], ["potk\u00e1", "potkat", "VERB", [23, 28]], ["farm\u00e1\u0159", "farm\u00e1\u0159", "NOUN", [29, 35]], ["Kennyho", "Kenny", "PROPN", [36, 43]], ["a", "a", "CCONJ", [44, 45]], ["pt\u00e1", "pt\u00e1t", "VERB", [46, 49]], ["se", "se", "PRON", [50, 52]], [":", ":", "PUNCT", [52, 53]], ["\"", "\"", "PUNCT", [54, 55]], ["Tak", "tak", "ADV", [55, 58]], ["jak", "jak", "ADV", [59, 62]], ["to", "ten", "DET", [63, 65]], ["dopadlo", "dopadnout", "VERB", [66, 73]], ["s", "s", "ADP", [74, 75]], ["t\u00edm", "ten", "DET", [76, 79]], ["mrtv\u00fdm", "mrtv\u00fd", "ADJ", [80, 86]], ["oslem", "osel", "NOUN", [87, 92]], ["?", "?", "PUNCT", [92, 93]]]], ["calgarske-listy_2003_unor_ocr.txt", "Kenny na to: \"Tak j\u00e1 ho vydra\u017eil.", [["Kenny", "Kenny", "PROPN", [0, 5]], ["na", "na", "ADP", [6, 8]], ["to", "ten", "DET", [9, 11]], [":", ":", "PUNCT", [11, 12]], ["\"", "\"", "PUNCT", [13, 14]], ["Tak", "tak", "ADV", [14, 17]], ["j\u00e1", "j\u00e1", "PRON", [18, 20]], ["ho", "on", "PRON", [21, 23]], ["vydra\u017eil", "vydra\u017eit", "VERB", [24, 32]], [".", ".", "PUNCT", [32, 33]]]], ["calgarske-listy_2003_unor_ocr.txt", "Prodal jsem 500 l\u00edstk\u016f po dvou dolarech a tak jsem ud\u011blal profit 998 $.", [["Prodal", "prodat", "VERB", [0, 6]], ["jsem", "b\u00fdt", "AUX", [7, 11]], ["500", "500", "NUM", [12, 15]], ["l\u00edstk\u016f", "l\u00edstek", "NOUN", [16, 22]], ["po", "po", "ADP", [23, 25]], ["dvou", "dva", "NUM", [26, 30]], ["dolarech", "dolar", "NOUN", [31, 39]], ["a", "a", "CCONJ", [40, 41]], ["tak", "tak", "ADV", [42, 45]], ["jsem", "b\u00fdt", "AUX", [46, 50]], ["ud\u011blal", "ud\u011blat", "VERB", [51, 57]], ["profit", "profit", "NOUN", [58, 64]], ["998", "998", "NUM", [65, 68]], ["$", "$", "NOUN", [69, 70]], [".", ".", "PUNCT", [70, 71]]]], ["calgarske-listy_2003_unor_ocr.txt", "Farm\u00e1\u0159 10  krout\u00ed hlavou a pov\u00edd\u00e1: \"A to nikdo neprotestoval\".", [["Farm\u00e1\u0159", "farm\u00e1\u0159", "NOUN", [0, 6]], ["10", "10", "NUM", [7, 9]], ["krout\u00ed", "kroutit", "VERB", [11, 17]], ["hlavou", "hlava", "NOUN", [18, 24]], ["a", "a", "CCONJ", [25, 26]], ["pov\u00edd\u00e1", "pov\u00eddat", "VERB", [27, 33]], [":", ":", "PUNCT", [33, 34]], ["\"", "\"", "PUNCT", [35, 36]], ["A", "a", "CCONJ", [36, 37]], ["to", "to", "PART", [38, 40]], ["nikdo", "nikdo", "PRON", [41, 46]], ["neprotestoval", "protestovat", "VERB", [47, 60]], ["\"", "\"", "PUNCT", [60, 61]], [".", ".", "PUNCT", [61, 62]]]], ["calgarske-listy_2003_unor_ocr.txt", "Kenny: \"Ale jo, ten chlap\u00edk jeho\u017e l\u00edstek vyhr\u00e1l.", [["Kenny", "Kenny", "PROPN", [0, 5]], [":", ":", "PUNCT", [5, 6]], ["\"", "\"", "PUNCT", [7, 8]], ["Ale", "ale", "CCONJ", [8, 11]], ["jo", "jo", "INTJ", [12, 14]], [",", ",", "PUNCT", [14, 15]], ["ten", "ten", "DET", [16, 19]], ["chlap\u00edk", "chlap\u00edk", "NOUN", [20, 27]], ["jeho\u017e", "jeho\u017e", "DET", [28, 33]], ["l\u00edstek", "l\u00edstek", "NOUN", [34, 40]], ["vyhr\u00e1l", "vyhr\u00e1t", "VERB", [41, 47]], [".", ".", "PUNCT", [47, 48]]]], ["calgarske-listy_2003_unor_ocr.txt", "Tak jsem mu vr\u00e1til dva dolary.\"", [["Tak", "tak", "ADV", [0, 3]], ["jsem", "b\u00fdt", "AUX", [4, 8]], ["mu", "on", "PRON", [9, 11]], ["vr\u00e1til", "vr\u00e1tit", "VERB", [12, 18]], ["dva", "dva", "NUM", [19, 22]], ["dolary", "dolar", "NOUN", [23, 29]], [".", ".", "PUNCT", [29, 30]], ["\"", "\"", "PUNCT", [30, 31]]]], ["calgarske-listy_2003_unor_ocr.txt", "Otec se syn\u00e1\u010dkem za\u0161li spolu do m\u00edstn\u00edho prodejn\u00edho st\u0159ediska.", [["Otec", "otec", "NOUN", [0, 4]], ["se", "s", "ADP", [5, 7]], ["syn\u00e1\u010dkem", "syn\u00e1\u010dek", "NOUN", [8, 16]], ["za\u0161li", "zaj\u00edt", "VERB", [17, 22]], ["spolu", "spolu", "ADV", [23, 28]], ["do", "do", "ADP", [29, 31]], ["m\u00edstn\u00edho", "m\u00edstn\u00ed", "ADJ", [32, 40]], ["prodejn\u00edho", "prodejn\u00ed", "ADJ", [41, 51]], ["st\u0159ediska", "st\u0159edisko", "NOUN", [52, 61]], [".", ".", "PUNCT", [61, 62]]]], ["calgarske-listy_2003_unor_ocr.txt", "Mal\u00fd synek dr\u017e\u00ed v ruce \u010dtvr\u0165\u00e1k.", [["Mal\u00fd", "mal\u00fd", "ADJ", [0, 4]], ["synek", "synek", "NOUN", [5, 10]], ["dr\u017e\u00ed", "dr\u017eet", "VERB", [11, 15]], ["v", "v", "ADP", [16, 17]], ["ruce", "ruka", "NOUN", [18, 22]], ["\u010dtvr\u0165\u00e1k", "\u010dtvr\u0165\u00e1k", "NOUN", [23, 30]], [".", ".", "PUNCT", [30, 31]]]], ["calgarske-listy_2003_unor_ocr.txt", "Znenad\u00e1n\u00ed se za\u010dne mal\u00fd hoch dusit, u\u017e i modr\u00e1 v obli\u010deji.", [["Znenad\u00e1n\u00ed", "znenad\u00e1n\u00ed", "NOUN", [0, 9]], ["se", "se", "PRON", [10, 12]], ["za\u010dne", "za\u010d\u00edt", "VERB", [13, 18]], ["mal\u00fd", "mal\u00fd", "ADJ", [19, 23]], ["hoch", "hocha", "NOUN", [24, 28]], ["dusit", "dusit", "VERB", [29, 34]], [",", ",", "PUNCT", [34, 35]], ["u\u017e", "u\u017e", "ADV", [36, 38]], ["i", "i", "CCONJ", [39, 40]], ["modr\u00e1", "modr\u00fd", "ADJ", [41, 46]], ["v", "v", "ADP", [47, 48]], ["obli\u010deji", "obli\u010dej", "NOUN", [49, 57]], [".", ".", "PUNCT", [57, 58]]]], ["calgarske-listy_2003_unor_ocr.txt", "Otec synka si rychle uv\u011bdom\u00ed, \u017ee hoch asi spolkl ten \u010dtvr\u0165\u00e1k a tak za\u010dne panicky volat o pomoc.", [["Otec", "otec", "NOUN", [0, 4]], ["synka", "synka", "NOUN", [5, 10]], ["si", "se", "PRON", [11, 13]], ["rychle", "rychle", "ADV", [14, 20]], ["uv\u011bdom\u00ed", "uv\u011bdomit", "VERB", [21, 28]], [",", ",", "PUNCT", [28, 29]], ["\u017ee", "\u017ee", "SCONJ", [30, 32]], ["hoch", "hocha", "NOUN", [33, 37]], ["asi", "asi", "PART", [38, 41]], ["spolkl", "spolknout", "VERB", [42, 48]], ["ten", "ten", "DET", [49, 52]], ["\u010dtvr\u0165\u00e1k", "\u010dtvr\u0165\u00e1k", "NOUN", [53, 60]], ["a", "a", "CCONJ", [61, 62]], ["tak", "tak", "ADV", [63, 66]], ["za\u010dne", "za\u010d\u00edt", "VERB", [67, 72]], ["panicky", "panicky", "ADV", [73, 80]], ["volat", "volat", "VERB", [81, 86]], ["o", "o", "ADP", [87, 88]], ["pomoc", "pomoc", "NOUN", [89, 94]], [".", ".", "PUNCT", [94, 95]]]], ["calgarske-listy_2003_unor_ocr.txt", "Nedaleko v kav\u00e1rn\u011b sed\u00ed u stolku a pop\u00edj\u00ed k\u00e1vu a \u010dte noviny velmi dob\u0159e oble\u010den\u00e1, atraktivn\u00ed a velmi v\u00e1\u017en\u011b vyhl\u00ed\u017eej\u00edc\u00ed \u017eena v modr\u00e9m spole\u010densk\u00e9m obleku.", [["Nedaleko", "daleko", "ADV", [0, 8]], ["v", "v", "ADP", [9, 10]], ["kav\u00e1rn\u011b", "kav\u00e1rna", "NOUN", [11, 18]], ["sed\u00ed", "sed\u011bt", "VERB", [19, 23]], ["u", "u", "ADP", [24, 25]], ["stolku", "stolek", "NOUN", [26, 32]], ["a", "a", "CCONJ", [33, 34]], ["pop\u00edj\u00ed", "pop\u00edjet", "VERB", [35, 41]], ["k\u00e1vu", "k\u00e1va", "NOUN", [42, 46]], ["a", "a", "CCONJ", [47, 48]], ["\u010dte", "\u010d\u00edst", "VERB", [49, 52]], ["noviny", "noviny", "NOUN", [53, 59]], ["velmi", "velmi", "ADV", [60, 65]], ["dob\u0159e", "dob\u0159e", "ADV", [66, 71]], ["oble\u010den\u00e1", "oble\u010den\u00fd", "ADJ", [72, 80]], [",", ",", "PUNCT", [80, 81]], ["atraktivn\u00ed", "atraktivn\u00ed", "ADJ", [82, 92]], ["a", "a", "CCONJ", [93, 94]], ["velmi", "velmi", "ADV", [95, 100]], ["v\u00e1\u017en\u011b", "v\u00e1\u017en\u011b", "ADV", [101, 106]], ["vyhl\u00ed\u017eej\u00edc\u00ed", "vyhl\u00ed\u017eej\u00edc\u00ed", "ADJ", [107, 118]], ["\u017eena", "\u017eena", "NOUN", [119, 123]], ["v", "v", "ADP", [124, 125]], ["modr\u00e9m", "modr\u00fd", "ADJ", [126, 132]], ["spole\u010densk\u00e9m", "spole\u010densk\u00fd", "ADJ", [133, 145]], ["obleku", "oblek", "NOUN", [146, 152]], [".", ".", "PUNCT", [152, 153]]]], ["calgarske-listy_2003_unor_ocr.txt", "Zaslechla rozruch v bl\u00edzkosti, pohl\u00e9dla sm\u011brem k vytv\u00e1\u0159ej\u00edc\u00edmu se srocen\u00ed, postavila \u0161\u00e1lek od k\u00e1vy na tal\u00ed\u0159ek, pe\u010dliv\u011b slo\u017eila noviny a ulo\u017eila je do p\u0159\u00edslu\u0161n\u00e9 poli\u010dky.", [["Zaslechla", "zaslechnout", "VERB", [0, 9]], ["rozruch", "rozruch", "NOUN", [10, 17]], ["v", "v", "ADP", [18, 19]], ["bl\u00edzkosti", "bl\u00edzkost", "NOUN", [20, 29]], [",", ",", "PUNCT", [29, 30]], ["pohl\u00e9dla", "pohl\u00e9dnout", "VERB", [31, 39]], ["sm\u011brem", "sm\u011br", "NOUN", [40, 46]], ["k", "k", "ADP", [47, 48]], ["vytv\u00e1\u0159ej\u00edc\u00edmu", "vytv\u00e1\u0159ej\u00edc\u00ed", "ADJ", [49, 62]], ["se", "se", "PRON", [63, 65]], ["srocen\u00ed", "srocen\u00ed", "NOUN", [66, 73]], [",", ",", "PUNCT", [73, 74]], ["postavila", "postavit", "VERB", [75, 84]], ["\u0161\u00e1lek", "\u0161\u00e1lek", "NOUN", [85, 90]], ["od", "od", "ADP", [91, 93]], ["k\u00e1vy", "k\u00e1va", "NOUN", [94, 98]], ["na", "na", "ADP", [99, 101]], ["tal\u00ed\u0159ek", "tal\u00ed\u0159ek", "NOUN", [102, 109]], [",", ",", "PUNCT", [109, 110]], ["pe\u010dliv\u011b", "pe\u010dliv\u011b", "ADV", [111, 118]], ["slo\u017eila", "slo\u017eit", "VERB", [119, 126]], ["noviny", "noviny", "NOUN", [127, 133]], ["a", "a", "CCONJ", [134, 135]], ["ulo\u017eila", "ulo\u017eit", "VERB", [136, 143]], ["je", "on", "PRON", [144, 146]], ["do", "do", "ADP", [147, 149]], ["p\u0159\u00edslu\u0161n\u00e9", "p\u0159\u00edslu\u0161n\u00fd", "ADJ", [150, 159]], ["poli\u010dky", "poli\u010dka", "NOUN", [160, 167]], [".", ".", "PUNCT", [167, 168]]]], ["calgarske-listy_2003_unor_ocr.txt", "Potom vstala a zvolna kr\u00e1\u010dela k hlou\u010dku.", [["Potom", "potom", "ADV", [0, 5]], ["vstala", "vst\u00e1t", "VERB", [6, 12]], ["a", "a", "CCONJ", [13, 14]], ["zvolna", "zvolna", "ADV", [15, 21]], ["kr\u00e1\u010dela", "kr\u00e1\u010det", "VERB", [22, 29]], ["k", "k", "ADP", [30, 31]], ["hlou\u010dku", "hlou\u010dek", "NOUN", [32, 39]], [".", ".", "PUNCT", [39, 40]]]], ["calgarske-listy_2003_unor_ocr.txt", "Kenny pak dosp\u011bl v chytr\u00e9ho mlad\u00e9ho mu\u017ee a stal se nakonec p\u0159edsedou spr\u00e1vn\u00ed rady nechvaln\u011b zn\u00e1m\u00e9 americk\u00e9 firmy Enron.", [["Kenny", "Kenny", "PROPN", [0, 5]], ["pak", "pak", "ADV", [6, 9]], ["dosp\u011bl", "dosp\u011bt", "VERB", [10, 16]], ["v", "v", "ADP", [17, 18]], ["chytr\u00e9ho", "chytr\u00fd", "ADJ", [19, 27]], ["mlad\u00e9ho", "mlad\u00fd", "ADJ", [28, 35]], ["mu\u017ee", "mu\u017e", "NOUN", [36, 40]], ["a", "a", "CCONJ", [41, 42]], ["stal", "st\u00e1t", "VERB", [43, 47]], ["se", "se", "PRON", [48, 50]], ["nakonec", "nakonec", "ADV", [51, 58]], ["p\u0159edsedou", "p\u0159edseda", "NOUN", [59, 68]], ["spr\u00e1vn\u00ed", "spr\u00e1vn\u00ed", "ADJ", [69, 76]], ["rady", "rada", "NOUN", [77, 81]], ["nechvaln\u011b", "chvaln\u011b", "ADV", [82, 91]], ["zn\u00e1m\u00e9", "zn\u00e1m\u00fd", "ADJ", [92, 97]], ["americk\u00e9", "americk\u00fd", "ADJ", [98, 106]], ["firmy", "firma", "NOUN", [107, 112]], ["Enron", "Enron", "PROPN", [113, 118]], [".", ".", "PUNCT", [118, 119]]]], ["calgarske-listy_2003_unor_ocr.txt", "Vehementn\u011b se sklonila k mal\u00e9mu chlapci, opatrn\u011b uchopila jeho varlata a za\u010dala je sv\u00edrat, jemn\u011b zpo\u010d\u00e1tku a potom st\u00e1le v\u00edc a pevn\u011bji.", [["Vehementn\u011b", "vehementn\u011b", "ADV", [0, 10]], ["se", "se", "PRON", [11, 13]], ["sklonila", "sklonit", "VERB", [14, 22]], ["k", "k", "ADP", [23, 24]], ["mal\u00e9mu", "mal\u00fd", "ADJ", [25, 31]], ["chlapci", "chlapec", "NOUN", [32, 39]], [",", ",", "PUNCT", [39, 40]], ["opatrn\u011b", "opatrn\u011b", "ADV", [41, 48]], ["uchopila", "uchopit", "VERB", [49, 57]], ["jeho", "jeho", "DET", [58, 62]], ["varlata", "varlata", "NOUN", [63, 70]], ["a", "a", "CCONJ", [71, 72]], ["za\u010dala", "za\u010d\u00edt", "VERB", [73, 79]], ["je", "on", "PRON", [80, 82]], ["sv\u00edrat", "sv\u00edrat", "VERB", [83, 89]], [",", ",", "PUNCT", [89, 90]], ["jemn\u011b", "jemn\u011b", "ADV", [91, 96]], ["zpo\u010d\u00e1tku", "zpo\u010d\u00e1tku", "ADV", [97, 105]], ["a", "a", "CCONJ", [106, 107]], ["potom", "potom", "ADV", [108, 113]], ["st\u00e1le", "st\u00e1le", "ADV", [114, 119]], ["v\u00edc", "v\u00edce", "ADV", [120, 123]], ["a", "a", "CCONJ", [124, 125]], ["pevn\u011bji", "pevn\u011b", "ADV", [126, 133]], [".", ".", "PUNCT", [133, 134]]]], ["calgarske-listy_2003_unor_ocr.txt", "Po n\u011bkolika vte\u0159in\u00e1ch hoch za\u010dal k\u0159e\u010dovit\u011b a divoce zvracet a\u017e kone\u010dn\u011b vyka\u0161lal ten \u010dtvr\u0165\u00e1k, kter\u00fd ta \u017eena obratn\u011b uchopila do sv\u00e9 voln\u00e9 ruky.", [["Po", "po", "ADP", [0, 2]], ["n\u011bkolika", "n\u011bkolik", "DET", [3, 11]], ["vte\u0159in\u00e1ch", "vte\u0159ina", "NOUN", [12, 21]], ["hoch", "hocha", "NOUN", [22, 26]], ["za\u010dal", "za\u010d\u00edt", "VERB", [27, 32]], ["k\u0159e\u010dovit\u011b", "k\u0159e\u010dovit\u011b", "ADV", [33, 42]], ["a", "a", "CCONJ", [43, 44]], ["divoce", "divoce", "ADV", [45, 51]], ["zvracet", "zvracet", "VERB", [52, 59]], ["a\u017e", "a\u017e", "PART", [60, 62]], ["kone\u010dn\u011b", "kone\u010dn\u011b", "ADV", [63, 70]], ["vyka\u0161lal", "vyka\u0161lat", "VERB", [71, 79]], ["ten", "ten", "DET", [80, 83]], ["\u010dtvr\u0165\u00e1k", "\u010dtvr\u0165\u00e1k", "NOUN", [84, 91]], [",", ",", "PUNCT", [91, 92]], ["kter\u00fd", "kter\u00fd", "DET", [93, 98]], ["ta", "ten", "DET", [99, 101]], ["\u017eena", "\u017eena", "NOUN", [102, 106]], ["obratn\u011b", "obratn\u011b", "ADV", [107, 114]], ["uchopila", "uchopit", "VERB", [115, 123]], ["do", "do", "ADP", [124, 126]], ["sv\u00e9", "sv\u016fj", "DET", [127, 130]], ["voln\u00e9", "voln\u00fd", "ADJ", [131, 136]], ["ruky", "ruka", "NOUN", [137, 141]], [".", ".", "PUNCT", [141, 142]]]], ["calgarske-listy_2003_unor_ocr.txt", "Propustiv\u0161i chlapce, \u017eena podala otci \u010dtvr\u0165\u00e1k a ode\u0161la zp\u011bt k sv\u00e9mu m\u00edstu v kav\u00e1rn\u011b ani\u017e by slovo pronesla.", [["Propustiv\u0161i", "propustiv\u00fd", "ADJ", [0, 11]], ["chlapce", "chlapec", "NOUN", [12, 19]], [",", ",", "PUNCT", [19, 20]], ["\u017eena", "\u017eena", "NOUN", [21, 25]], ["podala", "podat", "VERB", [26, 32]], ["otci", "otec", "NOUN", [33, 37]], ["\u010dtvr\u0165\u00e1k", "\u010dtvr\u0165\u00e1k", "PROPN", [38, 45]], ["a", "a", "CCONJ", [46, 47]], ["ode\u0161la", "odej\u00edt", "VERB", [48, 54]], ["zp\u011bt", "zp\u011bt", "ADV", [55, 59]], ["k", "k", "ADP", [60, 61]], ["sv\u00e9mu", "sv\u016fj", "DET", [62, 67]], ["m\u00edstu", "m\u00edsto", "NOUN", [68, 73]], ["v", "v", "ADP", [74, 75]], ["kav\u00e1rn\u011b", "kav\u00e1rna", "NOUN", [76, 83]], ["ani\u017e", "ani\u017e", "SCONJ", [84, 88]], ["by", "b\u00fdt", "AUX", [89, 91]], ["slovo", "slovo", "NOUN", [92, 97]], ["pronesla", "pron\u00e9st", "VERB", [98, 106]], [".", ".", "PUNCT", [106, 107]]]], ["calgarske-listy_2003_unor_ocr.txt", "Otec si je\u0161t\u011b ov\u011b\u0159uje, \u017ee je s hochem v\u0161e v po\u0159\u00e1dku a pak sp\u011bch\u00e1 za onou \u017eenou, d\u011bkuje j\u00ed a pt\u00e1 se \" J\u00e1 jsem nikdy nevid\u011bl n\u011bkoho takhle zas\u00e1hnout, to bylo fantastick\u00e9, nejste l\u00e9ka\u0159ka?\"", [["Otec", "otec", "NOUN", [0, 4]], ["si", "se", "PRON", [5, 7]], ["je\u0161t\u011b", "je\u0161t\u011b", "ADV", [8, 13]], ["ov\u011b\u0159uje", "ov\u011b\u0159ovat", "VERB", [14, 21]], [",", ",", "PUNCT", [21, 22]], ["\u017ee", "\u017ee", "SCONJ", [23, 25]], ["je", "b\u00fdt", "AUX", [26, 28]], ["s", "s", "ADP", [29, 30]], ["hochem", "hoch", "NOUN", [31, 37]], ["v\u0161e", "v\u0161echen", "DET", [38, 41]], ["v", "v", "ADP", [42, 43]], ["po\u0159\u00e1dku", "po\u0159\u00e1dek", "NOUN", [44, 51]], ["a", "a", "CCONJ", [52, 53]], ["pak", "pak", "ADV", [54, 57]], ["sp\u011bch\u00e1", "sp\u011bchat", "VERB", [58, 64]], ["za", "za", "ADP", [65, 67]], ["onou", "onou", "ADJ", [68, 72]], ["\u017eenou", "\u017eena", "NOUN", [73, 78]], [",", ",", "PUNCT", [78, 79]], ["d\u011bkuje", "d\u011bkovat", "VERB", [80, 86]], ["j\u00ed", "on", "PRON", [87, 89]], ["a", "a", "CCONJ", [90, 91]], ["pt\u00e1", "pt\u00e1t", "VERB", [92, 95]], ["se", "se", "PRON", [96, 98]], ["\"", "\"", "PUNCT", [99, 100]], ["J\u00e1", "j\u00e1", "PRON", [101, 103]], ["jsem", "b\u00fdt", "AUX", [104, 108]], ["nikdy", "nikdy", "ADV", [109, 114]], ["nevid\u011bl", "vid\u011bt", "VERB", [115, 122]], ["n\u011bkoho", "n\u011bkdo", "PRON", [123, 129]], ["takhle", "takhle", "ADV", [130, 136]], ["zas\u00e1hnout", "zas\u00e1hnout", "VERB", [137, 146]], [",", ",", "PUNCT", [146, 147]], ["to", "ten", "DET", [148, 150]], ["bylo", "b\u00fdt", "AUX", [151, 155]], ["fantastick\u00e9", "fantastick\u00fd", "ADJ", [156, 167]], [",", ",", "PUNCT", [167, 168]], ["nejste", "b\u00fdt", "AUX", [169, 175]], ["l\u00e9ka\u0159ka", "l\u00e9ka\u0159ka", "NOUN", [176, 183]], ["?", "?", "PUNCT", [183, 184]], ["\"", "\"", "PUNCT", [184, 185]]]], ["calgarske-listy_2003_unor_ocr.txt", "\"Ne\" odv\u011bt\u00ed \u017eena, \"j\u00e1 d\u011bl\u00e1m rozvody\".", [["\"", "\"", "PUNCT", [0, 1]], ["Ne", "ne", "PART", [1, 3]], ["\"", "\"", "PUNCT", [3, 4]], ["odv\u011bt\u00ed", "odv\u011btit", "VERB", [5, 11]], ["\u017eena", "\u017eena", "NOUN", [12, 16]], [",", ",", "PUNCT", [16, 17]], ["\"", "\"", "PUNCT", [18, 19]], ["j\u00e1", "j\u00e1", "PRON", [19, 21]], ["d\u011bl\u00e1m", "d\u011blat", "VERB", [22, 27]], ["rozvody", "rozvod", "NOUN", [28, 35]], ["\"", "\"", "PUNCT", [35, 36]], [".", ".", "PUNCT", [36, 37]]]], ["calgarske-listy_2003_unor_ocr.txt", "V letadle let\u00ed \u010cech, Rus, Ameri\u010dan a Cik\u00e1n.", [["V", "v", "ADP", [0, 1]], ["letadle", "letadlo", "NOUN", [2, 9]], ["let\u00ed", "let\u011bt", "VERB", [10, 14]], ["\u010cech", "\u010cechy", "PROPN", [15, 19]], [",", ",", "PUNCT", [19, 20]], ["Rus", "Rus", "PROPN", [21, 24]], [",", ",", "PUNCT", [24, 25]], ["Ameri\u010dan", "Ameri\u010dan", "PROPN", [26, 34]], ["a", "a", "CCONJ", [35, 36]], ["Cik\u00e1n", "Cik\u00e1n", "PROPN", [37, 42]], [".", ".", "PUNCT", [42, 43]]]], ["calgarske-listy_2003_unor_ocr.txt", "Najednou za\u010dne letadlo padat.", [["Najednou", "najednou", "ADV", [0, 8]], ["za\u010dne", "za\u010d\u00edt", "VERB", [9, 14]], ["letadlo", "letadlo", "NOUN", [15, 22]], ["padat", "padat", "VERB", [23, 28]], [".", ".", "PUNCT", [28, 29]]]], ["calgarske-listy_2003_unor_ocr.txt", "Pilot se oto\u010d\u00ed do kabiny a k\u0159i\u010d\u00ed:\"Jeden z v\u00e1s mus\u00ed vysko\u010dit, jinak se z\u0159\u00edt\u00edme!\"", [["Pilot", "pilot", "NOUN", [0, 5]], ["se", "se", "PRON", [6, 8]], ["oto\u010d\u00ed", "oto\u010dit", "VERB", [9, 14]], ["do", "do", "ADP", [15, 17]], ["kabiny", "kabina", "NOUN", [18, 24]], ["a", "a", "CCONJ", [25, 26]], ["k\u0159i\u010d\u00ed", "k\u0159i\u010det", "VERB", [27, 32]], [":", ":", "PUNCT", [32, 33]], ["\"", "\"", "PUNCT", [33, 34]], ["Jeden", "jeden", "NUM", [34, 39]], ["z", "z", "ADP", [40, 41]], ["v\u00e1s", "vy", "PRON", [42, 45]], ["mus\u00ed", "muset", "VERB", [46, 50]], ["vysko\u010dit", "vysko\u010dit", "VERB", [51, 59]], [",", ",", "PUNCT", [59, 60]], ["jinak", "jinak", "ADV", [61, 66]], ["se", "se", "PRON", [67, 69]], ["z\u0159\u00edt\u00edme", "z\u0159\u00edtit", "VERB", [70, 77]], ["!", "!", "PUNCT", [77, 78]], ["\"", "\"", "PUNCT", [78, 79]]]], ["calgarske-listy_2003_unor_ocr.txt", "\u010cech \u0159\u00edk\u00e1: \"To je jasn\u00fd,vyhod\u00edme cik\u00e1na\"!", [["\u010cech", "\u010cechy", "PROPN", [0, 4]], ["\u0159\u00edk\u00e1", "\u0159\u00edkat", "VERB", [5, 9]], [":", ":", "PUNCT", [9, 10]], ["\"", "\"", "PUNCT", [11, 12]], ["To", "ten", "DET", [12, 14]], ["je", "b\u00fdt", "AUX", [15, 17]], ["jasn\u00fd", "jasn\u00fd", "ADJ", [18, 23]], [",", ",", "PUNCT", [23, 24]], ["vyhod\u00edme", "vyhodit", "VERB", [24, 32]], ["cik\u00e1na", "cik\u00e1n", "NOUN", [33, 39]], ["\"", "\"", "PUNCT", [39, 40]], ["!", "!", "PUNCT", [40, 41]]]], ["calgarske-listy_2003_unor_ocr.txt", "V tom p\u0159isko\u010d\u00ed Ameri\u010dan a \u0159\u00edk\u00e1: \"P\u00e1nov\u00e9, \u017e\u00e1dn\u00fd rasismus.", [["V", "v", "ADP", [0, 1]], ["tom", "ten", "DET", [2, 5]], ["p\u0159isko\u010d\u00ed", "p\u0159isko\u010dit", "VERB", [6, 14]], ["Ameri\u010dan", "Ameri\u010dan", "PROPN", [15, 23]], ["a", "a", "CCONJ", [24, 25]], ["\u0159\u00edk\u00e1", "\u0159\u00edkat", "VERB", [26, 30]], [":", ":", "PUNCT", [30, 31]], ["\"", "\"", "PUNCT", [32, 33]], ["P\u00e1nov\u00e9", "p\u00e1n", "NOUN", [33, 39]], [",", ",", "PUNCT", [39, 40]], ["\u017e\u00e1dn\u00fd", "\u017e\u00e1dn\u00fd", "DET", [41, 46]], ["rasismus", "rasismus", "NOUN", [47, 55]], [".", ".", "PUNCT", [55, 56]]]], ["calgarske-listy_2003_unor_ocr.txt", "Ud\u011bl\u00e1me to n\u00e1sledovn\u011b.", [["Ud\u011bl\u00e1me", "ud\u011blat", "VERB", [0, 7]], ["to", "ten", "DET", [8, 10]], ["n\u00e1sledovn\u011b", "n\u00e1sledovn\u011b", "ADV", [11, 21]], [".", ".", "PUNCT", [21, 22]]]], ["calgarske-listy_2003_unor_ocr.txt", "Ka\u017ed\u00e9mu polo\u017e\u00edm ot\u00e1zku a kdo ji nezodpov\u00ed, tak vysko\u010d\u00ed\"!", [["Ka\u017ed\u00e9mu", "ka\u017ed\u00fd", "DET", [0, 7]], ["polo\u017e\u00edm", "polo\u017eit", "VERB", [8, 15]], ["ot\u00e1zku", "ot\u00e1zka", "NOUN", [16, 22]], ["a", "a", "CCONJ", [23, 24]], ["kdo", "kdo", "PRON", [25, 28]], ["ji", "on", "PRON", [29, 31]], ["nezodpov\u00ed", "zodpovit", "VERB", [32, 41]], [",", ",", "PUNCT", [41, 42]], ["tak", "tak", "ADV", [43, 46]], ["vysko\u010d\u00ed", "vysko\u010dit", "VERB", [47, 54]], ["\"", "\"", "PUNCT", [54, 55]], ["!", "!", "PUNCT", [55, 56]]]], ["calgarske-listy_2003_unor_ocr.txt", "Pod\u00edv\u00e1 se na Rusa a \u0159\u00edk\u00e1: \"Jak\u00e1 byla nejv\u011bt\u0161\u00ed lodn\u00ed katastrofa na sv\u011bt\u011b\"?", [["Pod\u00edv\u00e1", "pod\u00edvat", "VERB", [0, 6]], ["se", "se", "PRON", [7, 9]], ["na", "na", "ADP", [10, 12]], ["Rusa", "Rus", "PROPN", [13, 17]], ["a", "a", "CCONJ", [18, 19]], ["\u0159\u00edk\u00e1", "\u0159\u00edkat", "VERB", [20, 24]], [":", ":", "PUNCT", [24, 25]], ["\"", "\"", "PUNCT", [26, 27]], ["Jak\u00e1", "jak\u00fd", "DET", [27, 31]], ["byla", "b\u00fdt", "AUX", [32, 36]], ["nejv\u011bt\u0161\u00ed", "velk\u00fd", "ADJ", [37, 45]], ["lodn\u00ed", "lodn\u00ed", "ADJ", [46, 51]], ["katastrofa", "katastrofa", "NOUN", [52, 62]], ["na", "na", "ADP", [63, 65]], ["sv\u011bt\u011b", "sv\u011bt", "NOUN", [66, 71]], ["\"", "\"", "PUNCT", [71, 72]], ["?", "?", "PUNCT", [72, 73]]]], ["calgarske-listy_2003_unor_ocr.txt", "\"Titanic\", odpov\u00ed spr\u00e1vn\u011b Rus.", [["\"", "\"", "PUNCT", [0, 1]], ["Titanic", "Titanice", "PROPN", [1, 8]], ["\"", "\"", "PUNCT", [8, 9]], [",", ",", "PUNCT", [9, 10]], ["odpov\u00ed", "odpov\u011bd\u011bt", "VERB", [11, 17]], ["spr\u00e1vn\u011b", "spr\u00e1vn\u011b", "ADV", [18, 25]], ["Rus", "Rus", "PROPN", [26, 29]], [".", ".", "PUNCT", [29, 30]]]], ["calgarske-listy_2003_unor_ocr.txt", "Na \u010cecha: \"Kolik tam zahynulo lid\u00ed?", [["Na", "na", "ADP", [0, 2]], ["\u010cecha", "\u010cech", "PROPN", [3, 8]], [":", ":", "PUNCT", [8, 9]], ["\"", "\"", "PUNCT", [10, 11]], ["Kolik", "kolik", "DET", [11, 16]], ["tam", "tam", "ADV", [17, 20]], ["zahynulo", "zahynout", "VERB", [21, 29]], ["lid\u00ed", "lid\u00e9", "NOUN", [30, 34]], ["?", "?", "PUNCT", [34, 35]]]], ["calgarske-listy_2003_unor_ocr.txt", "\"1161\", odpov\u00ed spr\u00e1vn\u011b \u010cech.", [["\"", "\"", "PUNCT", [0, 1]], ["1161", "1161", "NUM", [1, 5]], ["\"", "\"", "PUNCT", [5, 6]], [",", ",", "PUNCT", [6, 7]], ["odpov\u00ed", "odpov\u011bd\u011bt", "VERB", [8, 14]], ["spr\u00e1vn\u011b", "spr\u00e1vn\u011b", "ADV", [15, 22]], ["\u010cech", "\u010cechy", "PROPN", [23, 27]], [".", ".", "PUNCT", [27, 28]]]], ["calgarske-listy_2003_unor_ocr.txt", "Ameri\u010dan se oto\u010d\u00ed k Cik\u00e1novi a \u0159\u00edk\u00e1 \" Vyjmenuj je\"! . V\u011brn\u00e1 \u017eena.", [["Ameri\u010dan", "Ameri\u010dan", "PROPN", [0, 8]], ["se", "se", "PRON", [9, 11]], ["oto\u010d\u00ed", "oto\u010dit", "VERB", [12, 17]], ["k", "k", "ADP", [18, 19]], ["Cik\u00e1novi", "Cik\u00e1n", "PROPN", [20, 28]], ["a", "a", "CCONJ", [29, 30]], ["\u0159\u00edk\u00e1", "\u0159\u00edkat", "VERB", [31, 35]], ["\"", "\"", "PUNCT", [36, 37]], ["Vyjmenuj", "Vyjmenuj", "PROPN", [38, 46]], ["je", "b\u00fdt", "AUX", [47, 49]], ["\"", "\"", "PUNCT", [49, 50]], ["!", "!", "PUNCT", [50, 51]], [".", ".", "PUNCT", [52, 53]], ["V\u011brn\u00e1", "v\u011brn\u00fd", "ADJ", [54, 59]], ["\u017eena", "\u017eena", "NOUN", [60, 64]], [".", ".", "PUNCT", [64, 65]]]], ["calgarske-listy_2003_unor_ocr.txt", "Jej\u00ed mu\u017e byl po \u0159adu m\u011bs\u00edc\u016f v bezv\u011bdom\u00ed, z \u010deho\u017e se jen chvilkami prob\u00edral.", [["Jej\u00ed", "jeho", "DET", [0, 4]], ["mu\u017e", "mu\u017e", "NOUN", [5, 8]], ["byl", "b\u00fdt", "AUX", [9, 12]], ["po", "po", "ADP", [13, 15]], ["\u0159adu", "\u0159ada", "NOUN", [16, 20]], ["m\u011bs\u00edc\u016f", "m\u011bs\u00edc", "NOUN", [21, 27]], ["v", "v", "ADP", [28, 29]], ["bezv\u011bdom\u00ed", "bezv\u011bdom\u00ed", "NOUN", [30, 39]], [",", ",", "PUNCT", [39, 40]], ["z", "z", "ADP", [41, 42]], ["\u010deho\u017e", "co\u017e", "PRON", [43, 48]], ["se", "se", "PRON", [49, 51]], ["jen", "jen", "ADV", [52, 55]], ["chvilkami", "chvilka", "NOUN", [56, 65]], ["prob\u00edral", "prob\u00edrat", "VERB", [66, 74]], [".", ".", "PUNCT", [74, 75]]]], ["calgarske-listy_2003_unor_ocr.txt", "P\u0159esto jeho v\u011brn\u00e1 man\u017eelka cel\u00e9 dny prosed\u011bla u jeho l\u016f\u017eka.", [["P\u0159esto", "p\u0159esto", "CCONJ", [0, 6]], ["jeho", "jeho", "DET", [7, 11]], ["v\u011brn\u00e1", "v\u011brn\u00fd", "ADJ", [12, 17]], ["man\u017eelka", "man\u017eelka", "NOUN", [18, 26]], ["cel\u00e9", "cel\u00fd", "ADJ", [27, 31]], ["dny", "den", "NOUN", [32, 35]], ["prosed\u011bla", "prosed\u011bt", "VERB", [36, 45]], ["u", "u", "ADP", [46, 47]], ["jeho", "jeho", "DET", [48, 52]], ["l\u016f\u017eka", "l\u016f\u017eko", "NOUN", [53, 58]], [".", ".", "PUNCT", [58, 59]]]], ["calgarske-listy_2003_unor_ocr.txt", "Po jednom probuzen\u00ed ji op\u011bt spat\u0159il a \u0159ekl j\u00ed: \"Ve v\u0161ech t\u011b\u017ek\u00fdch chv\u00edl\u00edch jsi byla se mnou.", [["Po", "po", "ADP", [0, 2]], ["jednom", "jeden", "NUM", [3, 9]], ["probuzen\u00ed", "probuzen\u00ed", "NOUN", [10, 19]], ["ji", "on", "PRON", [20, 22]], ["op\u011bt", "op\u011bt", "ADV", [23, 27]], ["spat\u0159il", "spat\u0159it", "VERB", [28, 35]], ["a", "a", "CCONJ", [36, 37]], ["\u0159ekl", "\u0159\u00edci", "VERB", [38, 42]], ["j\u00ed", "on", "PRON", [43, 45]], [":", ":", "PUNCT", [45, 46]], ["\"", "\"", "PUNCT", [47, 48]], ["Ve", "v", "ADP", [48, 50]], ["v\u0161ech", "v\u0161echen", "DET", [51, 56]], ["t\u011b\u017ek\u00fdch", "t\u011b\u017ek\u00fd", "ADJ", [57, 64]], ["chv\u00edl\u00edch", "chv\u00edle", "NOUN", [65, 73]], ["jsi", "b\u00fdt", "AUX", [74, 77]], ["byla", "b\u00fdt", "AUX", [78, 82]], ["se", "s", "ADP", [83, 85]], ["mnou", "j\u00e1", "PRON", [86, 90]], [".", ".", "PUNCT", [90, 91]]]], ["calgarske-listy_2003_unor_ocr.txt", "Kdy\u017e mne vyhodili z pr\u00e1ce, byla jsi mou oporou.", [["Kdy\u017e", "kdy\u017e", "SCONJ", [0, 4]], ["mne", "j\u00e1", "PRON", [5, 8]], ["vyhodili", "vyhodit", "VERB", [9, 17]], ["z", "z", "ADP", [18, 19]], ["pr\u00e1ce", "pr\u00e1ce", "NOUN", [20, 25]], [",", ",", "PUNCT", [25, 26]], ["byla", "b\u00fdt", "AUX", [27, 31]], ["jsi", "b\u00fdt", "AUX", [32, 35]], ["mou", "m\u016fj", "DET", [36, 39]], ["oporou", "opora", "NOUN", [40, 46]], [".", ".", "PUNCT", [46, 47]]]], ["calgarske-listy_2003_unor_ocr.txt", "Kdy\u017e jsem za\u010dal podnikat a zkrachoval, byla jsi u toho.", [["Kdy\u017e", "kdy\u017e", "SCONJ", [0, 4]], ["jsem", "b\u00fdt", "AUX", [5, 9]], ["za\u010dal", "za\u010d\u00edt", "VERB", [10, 15]], ["podnikat", "podnikat", "VERB", [16, 24]], ["a", "a", "CCONJ", [25, 26]], ["zkrachoval", "zkrachovat", "VERB", [27, 37]], [",", ",", "PUNCT", [37, 38]], ["byla", "b\u00fdt", "AUX", [39, 43]], ["jsi", "b\u00fdt", "AUX", [44, 47]], ["u", "u", "ADP", [48, 49]], ["toho", "ten", "DET", [50, 54]], [".", ".", "PUNCT", [54, 55]]]], ["calgarske-listy_2003_unor_ocr.txt", "Kdy\u017e mne post\u0159elili, st\u00e1la jsi vedle mne.", [["Kdy\u017e", "kdy\u017e", "SCONJ", [0, 4]], ["mne", "j\u00e1", "PRON", [5, 8]], ["post\u0159elili", "post\u0159elit", "VERB", [9, 19]], [",", ",", "PUNCT", [19, 20]], ["st\u00e1la", "st\u00e1t", "VERB", [21, 26]], ["jsi", "b\u00fdt", "AUX", [27, 30]], ["vedle", "vedle", "ADP", [31, 36]], ["mne", "j\u00e1", "PRON", [37, 40]], [".", ".", "PUNCT", [40, 41]]]], ["calgarske-listy_2003_unor_ocr.txt", "Kdy\u017e jsme p\u0159i\u0161li o d\u016fm, podporovala jsi m\u011b.", [["Kdy\u017e", "kdy\u017e", "SCONJ", [0, 4]], ["jsme", "b\u00fdt", "AUX", [5, 9]], ["p\u0159i\u0161li", "p\u0159ij\u00edt", "VERB", [10, 16]], ["o", "o", "ADP", [17, 18]], ["d\u016fm", "d\u016fm", "NOUN", [19, 22]], [",", ",", "PUNCT", [22, 23]], ["podporovala", "podporovat", "VERB", [24, 35]], ["jsi", "b\u00fdt", "AUX", [36, 39]], ["m\u011b", "j\u00e1", "PRON", [40, 42]], [".", ".", "PUNCT", [42, 43]]]], ["calgarske-listy_2003_unor_ocr.txt", "Kdy\u017e jsem za\u010dal m\u00edt zdravotn\u00ed probl\u00e9my, i to jsi byla po m\u00e9m boku.", [["Kdy\u017e", "kdy\u017e", "SCONJ", [0, 4]], ["jsem", "b\u00fdt", "AUX", [5, 9]], ["za\u010dal", "za\u010d\u00edt", "VERB", [10, 15]], ["m\u00edt", "m\u00edt", "VERB", [16, 19]], ["zdravotn\u00ed", "zdravotn\u00ed", "ADJ", [20, 29]], ["probl\u00e9my", "probl\u00e9m", "NOUN", [30, 38]], [",", ",", "PUNCT", [38, 39]], ["i", "i", "CCONJ", [40, 41]], ["to", "ten", "DET", [42, 44]], ["jsi", "b\u00fdt", "AUX", [45, 48]], ["byla", "b\u00fdt", "AUX", [49, 53]], ["po", "po", "ADP", [54, 56]], ["m\u00e9m", "m\u016fj", "DET", [57, 60]], ["boku", "bok", "NOUN", [61, 65]], [".", ".", "PUNCT", [65, 66]]]], ["calgarske-listy_2003_unor_ocr.txt", "V\u00ed\u0161 co to znamen\u00e1?\"", [["V\u00ed\u0161", "v\u011bd\u011bt", "INTJ", [0, 3]], ["co", "co", "PRON", [4, 6]], ["to", "ten", "DET", [7, 9]], ["znamen\u00e1", "znamenat", "VERB", [10, 17]], ["?", "?", "PUNCT", [17, 18]], ["\"", "\"", "PUNCT", [18, 19]]]], ["calgarske-listy_2003_unor_ocr.txt", "\"Copak mil\u00e1\u010dku?\"", [["\"", "\"", "PUNCT", [0, 1]], ["Copak", "copak", "PART", [1, 6]], ["mil\u00e1\u010dku", "mil\u00e1\u010dek", "INTJ", [7, 14]], ["?", "?", "PUNCT", [14, 15]], ["\"", "\"", "PUNCT", [15, 16]]]], ["calgarske-listy_2003_unor_ocr.txt", "\"Nos\u00ed\u0161 mi sm\u016flu!\"", [["\"", "\"", "PUNCT", [0, 1]], ["Nos\u00ed\u0161", "nosit", "VERB", [1, 6]], ["mi", "j\u00e1", "PRON", [7, 9]], ["sm\u016flu", "sm\u016fla", "NOUN", [10, 15]], ["!", "!", "PUNCT", [15, 16]], ["\"", "\"", "PUNCT", [16, 17]]]], ["calgarske-listy_2003_unor_ocr.txt", "St\u011b\u017euje si pan\u00ed Von\u00e1skov\u00e1 sv\u00e9mu man\u017eelovi: \u201eSt\u00e1rne\u0161 hochu.", [["St\u011b\u017euje", "st\u011b\u017eovat", "VERB", [0, 7]], ["si", "se", "PRON", [8, 10]], ["pan\u00ed", "pan\u00ed", "NOUN", [11, 15]], ["Von\u00e1skov\u00e1", "Von\u00e1skov\u00e1", "PROPN", [16, 25]], ["sv\u00e9mu", "sv\u016fj", "DET", [26, 31]], ["man\u017eelovi", "man\u017eel", "NOUN", [32, 41]], [":", ":", "PUNCT", [41, 42]], ["\u201e", "\"", "PUNCT", [43, 44]], ["St\u00e1rne\u0161", "St\u00e1rne\u0161", "PROPN", [44, 51]], ["hochu", "hochu", "INTJ", [52, 57]], [".", ".", "PUNCT", [57, 58]]]], ["calgarske-listy_2003_unor_ocr.txt", "Kdy\u017e jsme byli mlad\u0161\u00ed, tv\u016fj v\u016fz m\u011bl poruchu v\u017edycky n\u011bkde v lese.", [["Kdy\u017e", "kdy\u017e", "SCONJ", [0, 4]], ["jsme", "b\u00fdt", "AUX", [5, 9]], ["byli", "b\u00fdt", "AUX", [10, 14]], ["mlad\u0161\u00ed", "mlad\u00fd", "ADJ", [15, 21]], [",", ",", "PUNCT", [21, 22]], ["tv\u016fj", "tv\u016fj", "DET", [23, 27]], ["v\u016fz", "v\u016fz", "NOUN", [28, 31]], ["m\u011bl", "m\u00edt", "VERB", [32, 35]], ["poruchu", "porucha", "NOUN", [36, 43]], ["v\u017edycky", "v\u017edycky", "ADV", [44, 51]], ["n\u011bkde", "n\u011bkde", "ADV", [52, 57]], ["v", "v", "ADP", [58, 59]], ["lese", "les", "NOUN", [60, 64]], [".", ".", "PUNCT", [64, 65]]]], ["calgarske-listy_2003_unor_ocr.txt", "A te\u010f se poka\u017ed\u00e9 pokaz\u00ed p\u0159ed n\u011bjakou hospodou.\u201c", [["A", "a", "CCONJ", [0, 1]], ["te\u010f", "te\u010f", "ADV", [2, 5]], ["se", "se", "PRON", [6, 8]], ["poka\u017ed\u00e9", "poka\u017ed\u00e9", "ADV", [9, 16]], ["pokaz\u00ed", "pokazit", "VERB", [17, 23]], ["p\u0159ed", "p\u0159ed", "ADP", [24, 28]], ["n\u011bjakou", "n\u011bjak\u00fd", "DET", [29, 36]], ["hospodou", "hospoda", "NOUN", [37, 45]], [".", ".", "PUNCT", [45, 46]], ["\u201c", "\"", "PUNCT", [46, 47]]]], ["calgarske-listy_2003_unor_ocr.txt", "\u201eNem\u016f\u017eete si posp\u00ed\u0161it?\u201c \u0159\u00edk\u00e1 \u017eebr\u00e1k mu\u017ei, hledaj\u00edc\u00edmu po kaps\u00e1ch drobn\u00e9 na almu\u017enu.", [["\u201e", "\"", "PUNCT", [0, 1]], ["Nem\u016f\u017eete", "moci", "VERB", [1, 9]], ["si", "se", "PRON", [10, 12]], ["posp\u00ed\u0161it", "posp\u00ed\u0161it", "VERB", [13, 21]], ["?", "?", "PUNCT", [21, 22]], ["\u201c", "\"", "PUNCT", [22, 23]], ["\u0159\u00edk\u00e1", "\u0159\u00edkat", "VERB", [24, 28]], ["\u017eebr\u00e1k", "\u017eebr\u00e1k", "NOUN", [29, 35]], ["mu\u017ei", "mu\u017e", "NOUN", [36, 40]], [",", ",", "PUNCT", [40, 41]], ["hledaj\u00edc\u00edmu", "hledaj\u00edc\u00ed", "ADJ", [42, 53]], ["po", "po", "ADP", [54, 56]], ["kaps\u00e1ch", "kapsa", "NOUN", [57, 64]], ["drobn\u00e9", "drobn\u00fd", "ADJ", [65, 71]], ["na", "na", "ADP", [72, 74]], ["almu\u017enu", "almu\u017ena", "NOUN", [75, 82]], [".", ".", "PUNCT", [82, 83]]]], ["calgarske-listy_2003_unor_ocr.txt", "\u201eParkuji s autem na zak\u00e1zan\u00e9m m\u00edst\u011b!\u201c", [["\u201e", "\"", "PUNCT", [0, 1]], ["Parkuji", "parkovat", "VERB", [1, 8]], ["s", "s", "ADP", [9, 10]], ["autem", "auto", "NOUN", [11, 16]], ["na", "na", "ADP", [17, 19]], ["zak\u00e1zan\u00e9m", "zak\u00e1zan\u00fd", "ADJ", [20, 29]], ["m\u00edst\u011b", "m\u00edsto", "NOUN", [30, 35]], ["!", "!", "PUNCT", [35, 36]], ["\u201c", "\"", "PUNCT", [36, 37]]]], ["calgarske-listy_2003_unor_ocr.txt", "P\u0159i tanci \u0159\u00edk\u00e1 v\u00fdznamn\u011b \u017eena sv\u00e9mu partnerovi: \"C\u00edt\u00edm se tak stra\u0161n\u011b opu\u0161t\u011bn\u00e1.", [["P\u0159i", "p\u0159i", "ADP", [0, 3]], ["tanci", "tanec", "NOUN", [4, 9]], ["\u0159\u00edk\u00e1", "\u0159\u00edkat", "VERB", [10, 14]], ["v\u00fdznamn\u011b", "v\u00fdznamn\u011b", "ADV", [15, 23]], ["\u017eena", "\u017eena", "NOUN", [24, 28]], ["sv\u00e9mu", "sv\u016fj", "DET", [29, 34]], ["partnerovi", "partner", "NOUN", [35, 45]], [":", ":", "PUNCT", [45, 46]], ["\"", "\"", "PUNCT", [47, 48]], ["C\u00edt\u00edm", "c\u00edtit", "VERB", [48, 53]], ["se", "se", "PRON", [54, 56]], ["tak", "tak", "ADV", [57, 60]], ["stra\u0161n\u011b", "stra\u0161n\u011b", "ADV", [61, 68]], ["opu\u0161t\u011bn\u00e1", "opu\u0161t\u011bn\u00fd", "ADJ", [69, 77]], [".", ".", "PUNCT", [77, 78]]]], ["calgarske-listy_2003_unor_ocr.txt", "Man\u017eel odjel na dva m\u011bs\u00edce do Lond\u00fdna.", [["Man\u017eel", "man\u017eel", "NOUN", [0, 6]], ["odjel", "odjet", "VERB", [7, 12]], ["na", "na", "ADP", [13, 15]], ["dva", "dva", "NUM", [16, 19]], ["m\u011bs\u00edce", "m\u011bs\u00edc", "NOUN", [20, 26]], ["do", "do", "ADP", [27, 29]], ["Lond\u00fdna", "Lond\u00fdn", "PROPN", [30, 37]], [".", ".", "PUNCT", [37, 38]]]], ["calgarske-listy_2003_unor_ocr.txt", "\"A mohla byste mi schovat zn\u00e1mky, jestli v\u00e1m bude ps\u00e1t?\"", [["\"", "\"", "PUNCT", [0, 1]], ["A", "a", "CCONJ", [1, 2]], ["mohla", "moci", "VERB", [3, 8]], ["byste", "b\u00fdt", "AUX", [9, 14]], ["mi", "j\u00e1", "PRON", [15, 17]], ["schovat", "schovat", "VERB", [18, 25]], ["zn\u00e1mky", "zn\u00e1mka", "NOUN", [26, 32]], [",", ",", "PUNCT", [32, 33]], ["jestli", "jestli", "SCONJ", [34, 40]], ["v\u00e1m", "vy", "PRON", [41, 44]], ["bude", "b\u00fdt", "AUX", [45, 49]], ["ps\u00e1t", "ps\u00e1t", "VERB", [50, 54]], ["?", "?", "PUNCT", [54, 55]], ["\"", "\"", "PUNCT", [55, 56]]]], ["calgarske-listy_2003_unor_ocr.txt", "Gynekolog zpov\u00edd\u00e1 t\u011bhotnou d\u00e1mu: \"M\u016f\u017eete, pros\u00edm uv\u00e9st jm\u00e9no otce?", [["Gynekolog", "gynekolog", "NOUN", [0, 9]], ["zpov\u00edd\u00e1", "zpov\u00eddat", "VERB", [10, 17]], ["t\u011bhotnou", "t\u011bhotn\u00fd", "ADJ", [18, 26]], ["d\u00e1mu", "d\u00e1ma", "NOUN", [27, 31]], [":", ":", "PUNCT", [31, 32]], ["\"", "\"", "PUNCT", [33, 34]], ["M\u016f\u017eete", "moci", "VERB", [34, 40]], [",", ",", "PUNCT", [40, 41]], ["pros\u00edm", "prosit", "VERB", [42, 48]], ["uv\u00e9st", "uv\u00e9st", "VERB", [49, 54]], ["jm\u00e9no", "jm\u00e9no", "NOUN", [55, 60]], ["otce", "otec", "NOUN", [61, 65]], ["?", "?", "PUNCT", [65, 66]]]], ["calgarske-listy_2003_unor_ocr.txt", "\"\u010cesk\u00e1 filharmonie.\"", [["\"", "\"", "PUNCT", [0, 1]], ["\u010cesk\u00e1", "\u010desk\u00fd", "ADJ", [1, 6]], ["filharmonie", "filharmonie", "NOUN", [7, 18]], [".", ".", "PUNCT", [18, 19]], ["\"", "\"", "PUNCT", [19, 20]]]], ["calgarske-listy_2003_unor_ocr.txt", "\"No to mi ne\u0159\u00edkejte, \u017ee otcem va\u0161eho d\u00edt\u011bte je hudebn\u00ed ans\u00e1mbl!\"", [["\"", "\"", "PUNCT", [0, 1]], ["No", "no", "INTJ", [1, 3]], ["to", "ten", "DET", [4, 6]], ["mi", "j\u00e1", "PRON", [7, 9]], ["ne\u0159\u00edkejte", "\u0159\u00edkat", "VERB", [10, 19]], [",", ",", "PUNCT", [19, 20]], ["\u017ee", "\u017ee", "SCONJ", [21, 23]], ["otcem", "otec", "NOUN", [24, 29]], ["va\u0161eho", "v\u00e1\u0161", "DET", [30, 36]], ["d\u00edt\u011bte", "d\u00edt\u011b", "NOUN", [37, 43]], ["je", "b\u00fdt", "AUX", [44, 46]], ["hudebn\u00ed", "hudebn\u00ed", "ADJ", [47, 54]], ["ans\u00e1mbl", "ans\u00e1mbl", "NOUN", [55, 62]], ["!", "!", "PUNCT", [62, 63]], ["\"", "\"", "PUNCT", [63, 64]]]], ["calgarske-listy_2003_unor_ocr.txt", "\"Kdy\u017e si u\u0159\u00edznete prst na cirkul\u00e1rce, tak v\u00edte, kterej zub v\u00e1m to ud\u011blal?\"", [["\"", "\"", "PUNCT", [0, 1]], ["Kdy\u017e", "kdy\u017e", "SCONJ", [1, 5]], ["si", "se", "PRON", [6, 8]], ["u\u0159\u00edznete", "u\u0159\u00edznout", "VERB", [9, 17]], ["prst", "prst", "NOUN", [18, 22]], ["na", "na", "ADP", [23, 25]], ["cirkul\u00e1rce", "cirkul\u00e1rce", "NOUN", [26, 36]], [",", ",", "PUNCT", [36, 37]], ["tak", "tak", "ADV", [38, 41]], ["v\u00edte", "v\u011bd\u011bt", "VERB", [42, 46]], [",", ",", "PUNCT", [46, 47]], ["kterej", "kter\u00fd", "DET", [48, 54]], ["zub", "zub", "NOUN", [55, 58]], ["v\u00e1m", "vy", "PRON", [59, 62]], ["to", "ten", "DET", [63, 65]], ["ud\u011blal", "ud\u011blat", "VERB", [66, 72]], ["?", "?", "PUNCT", [72, 73]], ["\"", "\"", "PUNCT", [73, 74]]]], ["calgarske-listy_2003_unor_ocr.txt", "Kter\u00e1 v\u00edra je lep\u0161\u00ed Rab\u00edn a katolick\u00fd kn\u011bz jedou spolu ve vlaku.", [["Kter\u00e1", "kter\u00fd", "DET", [0, 5]], ["v\u00edra", "v\u00edra", "NOUN", [6, 10]], ["je", "b\u00fdt", "AUX", [11, 13]], ["lep\u0161\u00ed", "lep\u0161\u00ed", "ADJ", [14, 19]], ["Rab\u00edn", "rab\u00edn", "NOUN", [20, 25]], ["a", "a", "CCONJ", [26, 27]], ["katolick\u00fd", "katolick\u00fd", "ADJ", [28, 37]], ["kn\u011bz", "kn\u011bz", "NOUN", [38, 42]], ["jedou", "jet", "VERB", [43, 48]], ["spolu", "spolu", "ADV", [49, 54]], ["ve", "v", "ADP", [55, 57]], ["vlaku", "vlak", "NOUN", [58, 63]], [".", ".", "PUNCT", [63, 64]]]], ["calgarske-listy_2003_unor_ocr.txt", "Po chv\u00edli se kn\u011bz osm\u011bl\u00ed a pov\u00edd\u00e1 rab\u00ednovi: \"Odpus\u0165te rebe, ale je to pravda, \u017ee lid\u00e9 va\u0161\u00ed v\u00edry maj\u00ed zapov\u011bzeno j\u00edst vep\u0159ov\u00e9?\"", [["Po", "po", "ADP", [0, 2]], ["chv\u00edli", "chv\u00edle", "NOUN", [3, 9]], ["se", "se", "PRON", [10, 12]], ["kn\u011bz", "kn\u011bz", "NOUN", [13, 17]], ["osm\u011bl\u00ed", "osm\u011blit", "VERB", [18, 24]], ["a", "a", "CCONJ", [25, 26]], ["pov\u00edd\u00e1", "pov\u00eddat", "VERB", [27, 33]], ["rab\u00ednovi", "rab\u00edn", "NOUN", [34, 42]], [":", ":", "PUNCT", [42, 43]], ["\"", "\"", "PUNCT", [44, 45]], ["Odpus\u0165te", "odpus\u0165it", "VERB", [45, 53]], ["rebe", "rebe", "NOUN", [54, 58]], [",", ",", "PUNCT", [58, 59]], ["ale", "ale", "CCONJ", [60, 63]], ["je", "b\u00fdt", "AUX", [64, 66]], ["to", "ten", "DET", [67, 69]], ["pravda", "pravda", "NOUN", [70, 76]], [",", ",", "PUNCT", [76, 77]], ["\u017ee", "\u017ee", "SCONJ", [78, 80]], ["lid\u00e9", "lid\u00e9", "NOUN", [81, 85]], ["va\u0161\u00ed", "v\u00e1\u0161", "DET", [86, 90]], ["v\u00edry", "v\u00edra", "NOUN", [91, 95]], ["maj\u00ed", "m\u00edt", "VERB", [96, 100]], ["zapov\u011bzeno", "zapov\u011bzen\u00fd", "ADJ", [101, 111]], ["j\u00edst", "j\u00edst", "VERB", [112, 116]], ["vep\u0159ov\u00e9", "vep\u0159ov\u00fd", "ADJ", [117, 124]], ["?", "?", "PUNCT", [124, 125]], ["\"", "\"", "PUNCT", [125, 126]]]], ["calgarske-listy_2003_unor_ocr.txt", "\"Ano ot\u010de, to je pravda.\"", [["\"", "\"", "PUNCT", [0, 1]], ["Ano", "ano", "PART", [1, 4]], ["ot\u010de", "ot\u010de", "NOUN", [5, 9]], [",", ",", "PUNCT", [9, 10]], ["to", "ten", "DET", [11, 13]], ["je", "b\u00fdt", "AUX", [14, 16]], ["pravda", "pravda", "NOUN", [17, 23]], [".", ".", "PUNCT", [23, 24]], ["\"", "\"", "PUNCT", [24, 25]]]], ["calgarske-listy_2003_unor_ocr.txt", "\"A \u0159ekn\u011bte mi - jako kn\u011bz kn\u011bzi - ochutnal jste jej n\u011bkdy?\"", [["\"", "\"", "PUNCT", [0, 1]], ["A", "a", "CCONJ", [1, 2]], ["\u0159ekn\u011bte", "\u0159\u00edci", "VERB", [3, 10]], ["mi", "j\u00e1", "PRON", [11, 13]], ["-", "-", "PUNCT", [14, 15]], ["jako", "jako", "SCONJ", [16, 20]], ["kn\u011bz", "kn\u011bz", "NOUN", [21, 25]], ["kn\u011bzi", "kn\u011bz", "NOUN", [26, 31]], ["-", "-", "PUNCT", [32, 33]], ["ochutnal", "ochutnat", "VERB", [34, 42]], ["jste", "b\u00fdt", "AUX", [43, 47]], ["jej", "on", "PRON", [48, 51]], ["n\u011bkdy", "n\u011bkdy", "ADV", [52, 57]], ["?", "?", "PUNCT", [57, 58]], ["\"", "\"", "PUNCT", [58, 59]]]], ["calgarske-listy_2003_unor_ocr.txt", "\"Inu, ano, kdysi jsem ochutnal kousek slaniny.\"", [["\"", "\"", "PUNCT", [0, 1]], ["Inu", "inu", "INTJ", [1, 4]], [",", ",", "PUNCT", [4, 5]], ["ano", "ano", "PART", [6, 9]], [",", ",", "PUNCT", [9, 10]], ["kdysi", "kdysi", "ADV", [11, 16]], ["jsem", "b\u00fdt", "AUX", [17, 21]], ["ochutnal", "ochutnat", "VERB", [22, 30]], ["kousek", "kousek", "NOUN", [31, 37]], ["slaniny", "slanina", "NOUN", [38, 45]], [".", ".", "PUNCT", [45, 46]], ["\"", "\"", "PUNCT", [46, 47]]]], ["calgarske-listy_2003_unor_ocr.txt", "\"A chutnala v\u00e1m?\"", [["\"", "\"", "PUNCT", [0, 1]], ["A", "a", "CCONJ", [1, 2]], ["chutnala", "chutnat", "VERB", [3, 11]], ["v\u00e1m", "vy", "PRON", [12, 15]], ["?", "?", "PUNCT", [15, 16]], ["\"", "\"", "PUNCT", [16, 17]]]], ["calgarske-listy_2003_unor_ocr.txt", "\"Mus\u00edm se p\u0159iznat, \u017ee chutnala.\"", [["\"", "\"", "PUNCT", [0, 1]], ["Mus\u00edm", "muset", "VERB", [1, 6]], ["se", "se", "PRON", [7, 9]], ["p\u0159iznat", "p\u0159iznat", "VERB", [10, 17]], [",", ",", "PUNCT", [17, 18]], ["\u017ee", "\u017ee", "SCONJ", [19, 21]], ["chutnala", "chutnat", "VERB", [22, 30]], [".", ".", "PUNCT", [30, 31]], ["\"", "\"", "PUNCT", [31, 32]]]], ["calgarske-listy_2003_unor_ocr.txt", "Po chv\u00edli se pro zm\u011bnu naklon\u00ed rab\u00edn ke kn\u011bzi: \"Prominou pane p\u00e1ter, ale je to pravda, \u017ee oni maj\u00ed zapov\u011bzeno t\u011blesn\u011b obcovat se \u017eenou?\"", [["Po", "po", "ADP", [0, 2]], ["chv\u00edli", "chv\u00edle", "NOUN", [3, 9]], ["se", "se", "PRON", [10, 12]], ["pro", "pro", "ADP", [13, 16]], ["zm\u011bnu", "zm\u011bna", "NOUN", [17, 22]], ["naklon\u00ed", "naklonit", "VERB", [23, 30]], ["rab\u00edn", "rab\u00edn", "NOUN", [31, 36]], ["ke", "k", "ADP", [37, 39]], ["kn\u011bzi", "kn\u011bz", "NOUN", [40, 45]], [":", ":", "PUNCT", [45, 46]], ["\"", "\"", "PUNCT", [47, 48]], ["Prominou", "prominout", "VERB", [48, 56]], ["pane", "pan", "INTJ", [57, 61]], ["p\u00e1ter", "p\u00e1ter", "NOUN", [62, 67]], [",", ",", "PUNCT", [67, 68]], ["ale", "ale", "CCONJ", [69, 72]], ["je", "b\u00fdt", "AUX", [73, 75]], ["to", "ten", "DET", [76, 78]], ["pravda", "pravda", "NOUN", [79, 85]], [",", ",", "PUNCT", [85, 86]], ["\u017ee", "\u017ee", "SCONJ", [87, 89]], ["oni", "on", "PRON", [90, 93]], ["maj\u00ed", "m\u00edt", "VERB", [94, 98]], ["zapov\u011bzeno", "zapov\u011bzen\u00fd", "ADJ", [99, 109]], ["t\u011blesn\u011b", "t\u011blesn\u011b", "ADV", [110, 117]], ["obcovat", "obcovat", "VERB", [118, 125]], ["se", "s", "ADP", [126, 128]], ["\u017eenou", "\u017eena", "NOUN", [129, 134]], ["?", "?", "PUNCT", [134, 135]], ["\"", "\"", "PUNCT", [135, 136]]]], ["calgarske-listy_2003_unor_ocr.txt", "\"Ach ano, je to tak, jak \u0159\u00edk\u00e1te.\"", [["\"", "\"", "PUNCT", [0, 1]], ["Ach", "ach", "INTJ", [1, 4]], ["ano", "ano", "PART", [5, 8]], [",", ",", "PUNCT", [8, 9]], ["je", "b\u00fdt", "AUX", [10, 12]], ["to", "ten", "DET", [13, 15]], ["tak", "tak", "ADV", [16, 19]], [",", ",", "PUNCT", [19, 20]], ["jak", "jak", "ADV", [21, 24]], ["\u0159\u00edk\u00e1te", "\u0159\u00edkat", "VERB", [25, 31]], [".", ".", "PUNCT", [31, 32]], ["\"", "\"", "PUNCT", [32, 33]]]], ["calgarske-listy_2003_unor_ocr.txt", "\"A \u0159eknou - jako kn\u011bz kn\u011bzi - dop\u0159\u00e1li si n\u011bkdy?\"", [["\"", "\"", "PUNCT", [0, 1]], ["A", "a", "CCONJ", [1, 2]], ["\u0159eknou", "\u0159\u00edci", "VERB", [3, 9]], ["-", "-", "PUNCT", [10, 11]], ["jako", "jako", "SCONJ", [12, 16]], ["kn\u011bz", "kn\u011bz", "NOUN", [17, 21]], ["kn\u011bzi", "kn\u011bz", "NOUN", [22, 27]], ["-", "-", "PUNCT", [28, 29]], ["dop\u0159\u00e1li", "dop\u0159\u00e1t", "VERB", [30, 37]], ["si", "se", "PRON", [38, 40]], ["n\u011bkdy", "n\u011bkdy", "ADV", [41, 46]], ["?", "?", "PUNCT", [46, 47]], ["\"", "\"", "PUNCT", [47, 48]]]], ["calgarske-listy_2003_unor_ocr.txt", "\"Popravd\u011b \u0159e\u010deno, nikoliv.\"", [["\"", "\"", "PUNCT", [0, 1]], ["Popravd\u011b", "popravd\u011b", "ADV", [1, 9]], ["\u0159e\u010deno", "\u0159e\u010den\u00fd", "ADJ", [10, 16]], [",", ",", "PUNCT", [16, 17]], ["nikoliv", "nikoliv", "PART", [18, 25]], [".", ".", "PUNCT", [25, 26]], ["\"", "\"", "PUNCT", [26, 27]]]], ["calgarske-listy_2003_unor_ocr.txt", "\"Hmm, \u0161koda,\" odtu\u0161\u00ed rab\u00edn, \"to je mnohem lep\u0161\u00ed ne\u017e vep\u0159ov\u00e9.\"", [["\"", "\"", "PUNCT", [0, 1]], ["Hmm", "hmm", "INTJ", [1, 4]], [",", ",", "PUNCT", [4, 5]], ["\u0161koda", "\u0161koda", "NOUN", [6, 11]], [",", ",", "PUNCT", [11, 12]], ["\"", "\"", "PUNCT", [12, 13]], ["odtu\u0161\u00ed", "odtu\u0161it", "VERB", [14, 20]], ["rab\u00edn", "rab\u00edn", "NOUN", [21, 26]], [",", ",", "PUNCT", [26, 27]], ["\"", "\"", "PUNCT", [28, 29]], ["to", "ten", "DET", [29, 31]], ["je", "b\u00fdt", "AUX", [32, 34]], ["mnohem", "mnohem", "ADV", [35, 41]], ["lep\u0161\u00ed", "lep\u0161\u00ed", "ADJ", [42, 47]], ["ne\u017e", "ne\u017e", "SCONJ", [48, 51]], ["vep\u0159ov\u00e9", "vep\u0159ov\u00fd", "ADJ", [52, 59]], [".", ".", "PUNCT", [59, 60]], ["\"", "\"", "PUNCT", [60, 61]]]], ["calgarske-listy_2003_unor_ocr.txt", "Definice ide\u00e1ln\u00edho man\u017eela : Ide\u00e1ln\u00ed man\u017eel: - nekou\u0159\u00ed, - nepije, - neflirtuje, - neexistuje.", [["Definice", "definice", "NOUN", [0, 8]], ["ide\u00e1ln\u00edho", "ide\u00e1ln\u00ed", "ADJ", [9, 18]], ["man\u017eela", "man\u017eel", "NOUN", [19, 26]], [":", ":", "PUNCT", [27, 28]], ["Ide\u00e1ln\u00ed", "ide\u00e1ln\u00ed", "ADJ", [29, 36]], ["man\u017eel", "man\u017eel", "NOUN", [37, 43]], [":", ":", "PUNCT", [43, 44]], ["-", "-", "PUNCT", [45, 46]], ["nekou\u0159\u00ed", "kou\u0159it", "VERB", [47, 54]], [",", ",", "PUNCT", [54, 55]], ["-", "-", "PUNCT", [56, 57]], ["nepije", "p\u00edt", "VERB", [58, 64]], [",", ",", "PUNCT", [64, 65]], ["-", "-", "PUNCT", [66, 67]], ["neflirtuje", "flirtovat", "VERB", [68, 78]], [",", ",", "PUNCT", [78, 79]], ["-", "-", "PUNCT", [80, 81]], ["neexistuje", "existovat", "VERB", [82, 92]], [".", ".", "PUNCT", [92, 93]]]], ["calgarske-listy_2003_unor_ocr.txt", "D\u016fchodce.", [["D\u016fchodce", "d\u016fchodce", "NOUN", [0, 8]], [".", ".", "PUNCT", [8, 9]]]], ["calgarske-listy_2003_unor_ocr.txt", "Ros\u0165a Hedv\u00ed\u010dek.", [["Ros\u0165a", "Ros\u0165", "PROPN", [0, 5]], ["Hedv\u00ed\u010dek", "Hedv\u00ed\u010dek", "PROPN", [6, 14]], [".", ".", "PUNCT", [14, 15]]]], ["calgarske-listy_2003_unor_ocr.txt", "P\u0159i sv\u00e9 n\u00e1v\u0161t\u011bv\u011b v \u010cesku v roce 1995 jsem vlezl do knihkupectv\u00ed a za\u010dal na pultech p\u00e1trat po foglarovk\u00e1ch a mayovk\u00e1ch, proto\u017ee to bylo asi tak v\u0161echno, co mne z \u010desk\u00e9 kni\u017en\u00ed produkce zaj\u00edmalo.", [["P\u0159i", "p\u0159i", "ADP", [0, 3]], ["sv\u00e9", "sv\u016fj", "DET", [4, 7]], ["n\u00e1v\u0161t\u011bv\u011b", "n\u00e1v\u0161t\u011bva", "NOUN", [8, 16]], ["v", "v", "ADP", [17, 18]], ["\u010cesku", "\u010cesko", "PROPN", [19, 24]], ["v", "v", "ADP", [25, 26]], ["roce", "rok", "NOUN", [27, 31]], ["1995", "1995", "NUM", [32, 36]], ["jsem", "b\u00fdt", "AUX", [37, 41]], ["vlezl", "vl\u00e9zt", "VERB", [42, 47]], ["do", "do", "ADP", [48, 50]], ["knihkupectv\u00ed", "knihkupectv\u00ed", "NOUN", [51, 63]], ["a", "a", "CCONJ", [64, 65]], ["za\u010dal", "za\u010d\u00edt", "VERB", [66, 71]], ["na", "na", "ADP", [72, 74]], ["pultech", "pult", "NOUN", [75, 82]], ["p\u00e1trat", "p\u00e1trat", "VERB", [83, 89]], ["po", "po", "ADP", [90, 92]], ["foglarovk\u00e1ch", "foglarovka", "NOUN", [93, 105]], ["a", "a", "CCONJ", [106, 107]], ["mayovk\u00e1ch", "mayovka", "NOUN", [108, 117]], [",", ",", "PUNCT", [117, 118]], ["proto\u017ee", "proto\u017ee", "SCONJ", [119, 126]], ["to", "ten", "DET", [127, 129]], ["bylo", "b\u00fdt", "AUX", [130, 134]], ["asi", "asi", "PART", [135, 138]], ["tak", "tak", "ADV", [139, 142]], ["v\u0161echno", "v\u0161echen", "DET", [143, 150]], [",", ",", "PUNCT", [150, 151]], ["co", "co", "PRON", [152, 154]], ["mne", "j\u00e1", "PRON", [155, 158]], ["z", "z", "ADP", [159, 160]], ["\u010desk\u00e9", "\u010desk\u00fd", "ADJ", [161, 166]], ["kni\u017en\u00ed", "kni\u017en\u00ed", "ADJ", [167, 173]], ["produkce", "produkce", "NOUN", [174, 182]], ["zaj\u00edmalo", "zaj\u00edmat", "VERB", [183, 191]], [".", ".", "PUNCT", [191, 192]]]], ["calgarske-listy_2003_unor_ocr.txt", "Vedle mne st\u00e1l star\u0161\u00ed p\u00e1n, jasn\u011b d\u016fchodce, a \u010detl si v n\u011bjak\u00e9 kn\u00ed\u017ece, tedy \u010dinnost zcela norm\u00e1ln\u00ed v ka\u017ed\u00e9 civilizovan\u00e9 prodejn\u011b knih jako t\u0159eba Barnes&", [["Vedle", "vedle", "ADP", [0, 5]], ["mne", "j\u00e1", "PRON", [6, 9]], ["st\u00e1l", "st\u00e1t", "VERB", [10, 14]], ["star\u0161\u00ed", "star\u00fd", "ADJ", [15, 21]], ["p\u00e1n", "p\u00e1n", "NOUN", [22, 25]], [",", ",", "PUNCT", [25, 26]], ["jasn\u011b", "jasn\u011b", "ADV", [27, 32]], ["d\u016fchodce", "d\u016fchodce", "NOUN", [33, 41]], [",", ",", "PUNCT", [41, 42]], ["a", "a", "CCONJ", [43, 44]], ["\u010detl", "\u010d\u00edst", "VERB", [45, 49]], ["si", "se", "PRON", [50, 52]], ["v", "v", "ADP", [53, 54]], ["n\u011bjak\u00e9", "n\u011bjak\u00fd", "DET", [55, 61]], ["kn\u00ed\u017ece", "kn\u00ed\u017eka", "NOUN", [62, 68]], [",", ",", "PUNCT", [68, 69]], ["tedy", "tedy", "CCONJ", [70, 74]], ["\u010dinnost", "\u010dinnost", "NOUN", [75, 82]], ["zcela", "zcela", "ADV", [83, 88]], ["norm\u00e1ln\u00ed", "norm\u00e1ln\u00ed", "ADJ", [89, 97]], ["v", "v", "ADP", [98, 99]], ["ka\u017ed\u00e9", "ka\u017ed\u00fd", "DET", [100, 105]], ["civilizovan\u00e9", "civilizovan\u00fd", "ADJ", [106, 118]], ["prodejn\u011b", "prodejna", "NOUN", [119, 127]], ["knih", "kniha", "NOUN", [128, 132]], ["jako", "jako", "SCONJ", [133, 137]], ["t\u0159eba", "t\u0159eba", "PART", [138, 143]], ["Barnes", "Barnes", "PROPN", [144, 150]], ["&", "&", "PUNCT", [150, 151]]]], ["calgarske-listy_2003_unor_ocr.txt", "Noble nebo Books A Million.", [["Noble", "Noble", "X", [0, 5]], ["nebo", "nebo", "CCONJ", [6, 10]], ["Books", "Books", "X", [11, 16]], ["A", "A", "X", [17, 18]], ["Million", "Million", "X", [19, 26]], [".", ".", "PUNCT", [26, 27]]]], ["calgarske-listy_2003_unor_ocr.txt", "Nikoliv tomu tak v \u010cesku.", [["Nikoliv", "nikoliv", "PART", [0, 7]], ["tomu", "ten", "DET", [8, 12]], ["tak", "tak", "ADV", [13, 16]], ["v", "v", "ADP", [17, 18]], ["\u010cesku", "\u010cesko", "PROPN", [19, 24]], [".", ".", "PUNCT", [24, 25]]]], ["calgarske-listy_2003_unor_ocr.txt", "Zezadu p\u0159i\u0161la prodava\u010dka, kter\u00e1 p\u0159edt\u00edm aspo\u0148 deset minut telefonovala, mne minula, proto\u017ee jsem zrovna jednu kn\u00ed\u017eku polo\u017eil a po druh\u00e9 s\u00e1hl, ale oslovila toho d\u011bdulu vedle mne.", [["Zezadu", "zezadu", "NOUN", [0, 6]], ["p\u0159i\u0161la", "p\u0159ij\u00edt", "VERB", [7, 13]], ["prodava\u010dka", "prodava\u010dka", "NOUN", [14, 24]], [",", ",", "PUNCT", [24, 25]], ["kter\u00e1", "kter\u00fd", "DET", [26, 31]], ["p\u0159edt\u00edm", "p\u0159edt\u00edm", "ADV", [32, 39]], ["aspo\u0148", "aspo\u0148", "ADV", [40, 45]], ["deset", "deset", "NUM", [46, 51]], ["minut", "minuta", "NOUN", [52, 57]], ["telefonovala", "telefonovat", "VERB", [58, 70]], [",", ",", "PUNCT", [70, 71]], ["mne", "j\u00e1", "PRON", [72, 75]], ["minula", "minout", "VERB", [76, 82]], [",", ",", "PUNCT", [82, 83]], ["proto\u017ee", "proto\u017ee", "SCONJ", [84, 91]], ["jsem", "b\u00fdt", "AUX", [92, 96]], ["zrovna", "zrovna", "ADV", [97, 103]], ["jednu", "jeden", "NUM", [104, 109]], ["kn\u00ed\u017eku", "kn\u00ed\u017eka", "NOUN", [110, 116]], ["polo\u017eil", "polo\u017eit", "VERB", [117, 124]], ["a", "a", "CCONJ", [125, 126]], ["po", "po", "ADP", [127, 129]], ["druh\u00e9", "druh\u00fd", "ADJ", [130, 135]], ["s\u00e1hl", "s\u00e1hnout", "VERB", [136, 140]], [",", ",", "PUNCT", [140, 141]], ["ale", "ale", "CCONJ", [142, 145]], ["oslovila", "oslovit", "VERB", [146, 154]], ["toho", "ten", "DET", [155, 159]], ["d\u011bdulu", "d\u011bdul", "NOUN", [160, 166]], ["vedle", "vedle", "ADP", [167, 172]], ["mne", "j\u00e1", "PRON", [173, 176]], [".", ".", "PUNCT", [176, 177]]]], ["calgarske-listy_2003_unor_ocr.txt", "\"Tak koup\u00edte si tu kn\u00ed\u017eku nebo si ji chcete p\u0159e\u010d\u00edst hned tady?\"", [["\"", "\"", "PUNCT", [0, 1]], ["Tak", "tak", "ADV", [1, 4]], ["koup\u00edte", "koupit", "VERB", [5, 12]], ["si", "se", "PRON", [13, 15]], ["tu", "ten", "DET", [16, 18]], ["kn\u00ed\u017eku", "kn\u00ed\u017eka", "NOUN", [19, 25]], ["nebo", "nebo", "CCONJ", [26, 30]], ["si", "se", "PRON", [31, 33]], ["ji", "on", "PRON", [34, 36]], ["chcete", "cht\u00edt", "VERB", [37, 43]], ["p\u0159e\u010d\u00edst", "p\u0159e\u010d\u00edst", "VERB", [44, 51]], ["hned", "hned", "ADV", [52, 56]], ["tady", "tady", "ADV", [57, 61]], ["?", "?", "PUNCT", [61, 62]], ["\"", "\"", "PUNCT", [62, 63]]]], ["calgarske-listy_2003_unor_ocr.txt", "Star\u00fd' p\u00e1n okam\u017eit\u011b polo\u017eil kn\u00ed\u017eku a s\u00e1hl po dve\u0159\u00edch a ode\u0161el - j\u00e1 bych to popsal jako \"okam\u017eit\u00e9 prchnut\u00ed\".", [["Star\u00fd", "star\u00fd", "ADJ", [0, 5]], ["'", "'", "PUNCT", [5, 6]], ["p\u00e1n", "p\u00e1n", "NOUN", [7, 10]], ["okam\u017eit\u011b", "okam\u017eit\u011b", "ADV", [11, 19]], ["polo\u017eil", "polo\u017eit", "VERB", [20, 27]], ["kn\u00ed\u017eku", "kn\u00ed\u017eka", "NOUN", [28, 34]], ["a", "a", "CCONJ", [35, 36]], ["s\u00e1hl", "s\u00e1hnout", "VERB", [37, 41]], ["po", "po", "ADP", [42, 44]], ["dve\u0159\u00edch", "dve\u0159e", "NOUN", [45, 52]], ["a", "a", "CCONJ", [53, 54]], ["ode\u0161el", "odej\u00edt", "VERB", [55, 61]], ["-", "-", "PUNCT", [62, 63]], ["j\u00e1", "j\u00e1", "PRON", [64, 66]], ["bych", "b\u00fdt", "AUX", [67, 71]], ["to", "ten", "DET", [72, 74]], ["popsal", "popsat", "VERB", [75, 81]], ["jako", "jako", "SCONJ", [82, 86]], ["\"", "\"", "PUNCT", [87, 88]], ["okam\u017eit\u00e9", "okam\u017eit\u00fd", "ADJ", [88, 96]], ["prchnut\u00ed", "prchnut\u00ed", "NOUN", [97, 105]], ["\"", "\"", "PUNCT", [105, 106]], [".", ".", "PUNCT", [106, 107]]]], ["calgarske-listy_2003_unor_ocr.txt", "Prodava\u010dka se za n\u00edm pod\u00edvala a pronesla: \"D\u016fchodce zasranej!\".", [["Prodava\u010dka", "prodava\u010dka", "NOUN", [0, 10]], ["se", "se", "PRON", [11, 13]], ["za", "za", "ADP", [14, 16]], ["n\u00edm", "on", "PRON", [17, 20]], ["pod\u00edvala", "pod\u00edvat", "VERB", [21, 29]], ["a", "a", "CCONJ", [30, 31]], ["pronesla", "pron\u00e9st", "VERB", [32, 40]], [":", ":", "PUNCT", [40, 41]], ["\"", "\"", "PUNCT", [42, 43]], ["D\u016fchodce", "d\u016fchodce", "NOUN", [43, 51]], ["zasranej", "zasranat", "VERB", [52, 60]], ["!", "!", "PUNCT", [60, 61]], ["\"", "\"", "PUNCT", [61, 62]], [".", ".", "PUNCT", [62, 63]]]], ["calgarske-listy_2003_unor_ocr.txt", "\"A copak v\u00e1m ten d\u016fchodce ud\u011blal?\" zaj\u00edmal jsem se okam\u017eit\u011b.", [["\"", "\"", "PUNCT", [0, 1]], ["A", "a", "CCONJ", [1, 2]], ["copak", "copak", "PART", [3, 8]], ["v\u00e1m", "vy", "PRON", [9, 12]], ["ten", "ten", "DET", [13, 16]], ["d\u016fchodce", "d\u016fchodce", "NOUN", [17, 25]], ["ud\u011blal", "ud\u011blat", "VERB", [26, 32]], ["?", "?", "PUNCT", [32, 33]], ["\"", "\"", "PUNCT", [33, 34]], ["zaj\u00edmal", "zaj\u00edmat", "VERB", [35, 42]], ["jsem", "b\u00fdt", "AUX", [43, 47]], ["se", "se", "PRON", [48, 50]], ["okam\u017eit\u011b", "okam\u017eit\u011b", "ADV", [51, 59]], [".", ".", "PUNCT", [59, 60]]]], ["calgarske-listy_2003_unor_ocr.txt", "\"Starejte se laskav\u011b o sv\u00fd!\" bylo mi odseknuto.", [["\"", "\"", "PUNCT", [0, 1]], ["Starejte", "starat", "VERB", [1, 9]], ["se", "se", "PRON", [10, 12]], ["laskav\u011b", "laskav\u011b", "ADV", [13, 20]], ["o", "o", "ADP", [21, 22]], ["sv\u00fd", "sv\u00fd", "NOUN", [23, 26]], ["!", "!", "PUNCT", [26, 27]], ["\"", "\"", "PUNCT", [27, 28]], ["bylo", "b\u00fdt", "AUX", [29, 33]], ["mi", "j\u00e1", "PRON", [34, 36]], ["odseknuto", "odseknut\u00fd", "ADJ", [37, 46]], [".", ".", "PUNCT", [46, 47]]]], ["calgarske-listy_2003_unor_ocr.txt", "Tak jsem polo\u017eil u\u017e vybran\u00e9 kn\u00ed\u017eky, foglarovka, nefoglarovka a \u0161el si je koupit jinam.", [["Tak", "tak", "ADV", [0, 3]], ["jsem", "b\u00fdt", "AUX", [4, 8]], ["polo\u017eil", "polo\u017eit", "VERB", [9, 16]], ["u\u017e", "u\u017e", "ADV", [17, 19]], ["vybran\u00e9", "vybran\u00fd", "ADJ", [20, 27]], ["kn\u00ed\u017eky", "kn\u00ed\u017eka", "NOUN", [28, 34]], [",", ",", "PUNCT", [34, 35]], ["foglarovka", "foglarovka", "NOUN", [36, 46]], [",", ",", "PUNCT", [46, 47]], ["nefoglarovka", "nefoglarovka", "NOUN", [48, 60]], ["a", "a", "CCONJ", [61, 62]], ["\u0161el", "j\u00edt", "VERB", [63, 66]], ["si", "se", "PRON", [67, 69]], ["je", "on", "PRON", [70, 72]], ["koupit", "koupit", "VERB", [73, 79]], ["jinam", "jinam", "ADV", [80, 85]], [".", ".", "PUNCT", [85, 86]]]], ["calgarske-listy_2003_unor_ocr.txt", "A \u017easl jsem nad t\u00edm, jak je to mo\u017en\u00e9.", [["A", "a", "CCONJ", [0, 1]], ["\u017easl", "\u017easnout", "VERB", [2, 6]], ["jsem", "b\u00fdt", "AUX", [7, 11]], ["nad", "nad", "ADP", [12, 15]], ["t\u00edm", "ten", "DET", [16, 19]], [",", ",", "PUNCT", [19, 20]], ["jak", "jak", "ADV", [21, 24]], ["je", "b\u00fdt", "AUX", [25, 27]], ["to", "ten", "DET", [28, 30]], ["mo\u017en\u00e9", "mo\u017en\u00fd", "ADJ", [31, 36]], [".", ".", "PUNCT", [36, 37]]]], ["calgarske-listy_2003_unor_ocr.txt", "Pro\u010d v tom \u010cesku je takov\u00e1 nen\u00e1vist k d\u016fchodc\u016fm?", [["Pro\u010d", "pro\u010d", "ADV", [0, 4]], ["v", "v", "ADP", [5, 6]], ["tom", "ten", "DET", [7, 10]], ["\u010cesku", "\u010cesko", "PROPN", [11, 16]], ["je", "b\u00fdt", "AUX", [17, 19]], ["takov\u00e1", "takov\u00fd", "DET", [20, 26]], ["nen\u00e1vist", "nen\u00e1vist", "NOUN", [27, 35]], ["k", "k", "ADP", [36, 37]], ["d\u016fchodc\u016fm", "d\u016fchodce", "NOUN", [38, 47]], ["?", "?", "PUNCT", [47, 48]]]], ["calgarske-listy_2003_unor_ocr.txt", "D\u016fchodce je v civilizovan\u00e9m sv\u011bt\u011b (co\u017e znamen\u00e1, \u017ee nemluv\u00edm o \u010cesku) osoba respektovan\u00e1 a dost\u00e1v\u00e1 se mu nejlep\u0161\u00edho zach\u00e1zen\u00ed a ohledu.", [["D\u016fchodce", "d\u016fchodce", "NOUN", [0, 8]], ["je", "b\u00fdt", "AUX", [9, 11]], ["v", "v", "ADP", [12, 13]], ["civilizovan\u00e9m", "civilizovan\u00fd", "ADJ", [14, 27]], ["sv\u011bt\u011b", "sv\u011bt", "NOUN", [28, 33]], ["(", "(", "PUNCT", [34, 35]], ["co\u017e", "co\u017e", "PRON", [35, 38]], ["znamen\u00e1", "znamenat", "VERB", [39, 46]], [",", ",", "PUNCT", [46, 47]], ["\u017ee", "\u017ee", "SCONJ", [48, 50]], ["nemluv\u00edm", "mluvit", "VERB", [51, 59]], ["o", "o", "ADP", [60, 61]], ["\u010cesku", "\u010cesko", "PROPN", [62, 67]], [")", ")", "PUNCT", [67, 68]], ["osoba", "osoba", "NOUN", [69, 74]], ["respektovan\u00e1", "respektovan\u00fd", "ADJ", [75, 87]], ["a", "a", "CCONJ", [88, 89]], ["dost\u00e1v\u00e1", "dost\u00e1vat", "VERB", [90, 97]], ["se", "se", "PRON", [98, 100]], ["mu", "on", "PRON", [101, 103]], ["nejlep\u0161\u00edho", "lep\u0161\u00ed", "ADJ", [104, 114]], ["zach\u00e1zen\u00ed", "zach\u00e1zen\u00ed", "NOUN", [115, 124]], ["a", "a", "CCONJ", [125, 126]], ["ohledu", "ohled", "NOUN", [127, 133]], [".", ".", "PUNCT", [133, 134]]]], ["calgarske-listy_2003_unor_ocr.txt", "Vzpom\u011bl jsem si na toho v\u00fd\u0161e zm\u00edn\u011bn\u00e9ho \u010desk\u00e9ho d\u016fchodce p\u0159ed p\u00e1r dny v na\u0161em knihkupectv\u00ed Barnes&", [["Vzpom\u011bl", "vzpom\u011bt", "VERB", [0, 7]], ["jsem", "b\u00fdt", "AUX", [8, 12]], ["si", "se", "PRON", [13, 15]], ["na", "na", "ADP", [16, 18]], ["toho", "ten", "DET", [19, 23]], ["v\u00fd\u0161e", "vysoko", "ADV", [24, 28]], ["zm\u00edn\u011bn\u00e9ho", "zm\u00edn\u011bn\u00fd", "ADJ", [29, 38]], ["\u010desk\u00e9ho", "\u010desk\u00fd", "ADJ", [39, 46]], ["d\u016fchodce", "d\u016fchodce", "NOUN", [47, 55]], ["p\u0159ed", "p\u0159ed", "ADP", [56, 60]], ["p\u00e1r", "p\u00e1r", "DET", [61, 64]], ["dny", "den", "NOUN", [65, 68]], ["v", "v", "ADP", [69, 70]], ["na\u0161em", "n\u00e1\u0161", "DET", [71, 76]], ["knihkupectv\u00ed", "knihkupectv\u00ed", "NOUN", [77, 89]], ["Barnes", "Barnes", "PROPN", [90, 96]], ["&", "&", "PUNCT", [96, 97]]]], ["calgarske-listy_2003_unor_ocr.txt", "Noble, co\u017e je knihkupeck\u00e1 samoobsluha, \u017e\u00e1dn\u00e1 pultovka.", [["Noble", "Noble", "PROPN", [0, 5]], [",", ",", "PUNCT", [5, 6]], ["co\u017e", "co\u017e", "PRON", [7, 10]], ["je", "b\u00fdt", "AUX", [11, 13]], ["knihkupeck\u00e1", "knihkupeck\u00fd", "ADJ", [14, 25]], ["samoobsluha", "samoobsluha", "NOUN", [26, 37]], [",", ",", "PUNCT", [37, 38]], ["\u017e\u00e1dn\u00e1", "\u017e\u00e1dn\u00fd", "DET", [39, 44]], ["pultovka", "pultovka", "NOUN", [45, 53]], [".", ".", "PUNCT", [53, 54]]]], ["calgarske-listy_2003_unor_ocr.txt", "Jeden d\u016fchodce si tam sedl a prodava\u010dka tam b\u011bhala a vytahovala mu kn\u00ed\u017eky z reg\u00e1lu, i kdy\u017e si je teoreticky mohl vyt\u00e1hnout s\u00e1m (dovedete si p\u0159edstavit ty \"ochotn\u00e9\" prodava\u010dky v \u010cesku?).", [["Jeden", "jeden", "NUM", [0, 5]], ["d\u016fchodce", "d\u016fchodce", "NOUN", [6, 14]], ["si", "se", "PRON", [15, 17]], ["tam", "tam", "ADV", [18, 21]], ["sedl", "sednout", "VERB", [22, 26]], ["a", "a", "CCONJ", [27, 28]], ["prodava\u010dka", "prodava\u010dka", "NOUN", [29, 39]], ["tam", "tam", "ADV", [40, 43]], ["b\u011bhala", "b\u011bhat", "VERB", [44, 50]], ["a", "a", "CCONJ", [51, 52]], ["vytahovala", "vytahovat", "VERB", [53, 63]], ["mu", "on", "PRON", [64, 66]], ["kn\u00ed\u017eky", "kn\u00ed\u017eka", "NOUN", [67, 73]], ["z", "z", "ADP", [74, 75]], ["reg\u00e1lu", "reg\u00e1l", "NOUN", [76, 82]], [",", ",", "PUNCT", [82, 83]], ["i", "i", "CCONJ", [84, 85]], ["kdy\u017e", "kdy\u017e", "SCONJ", [86, 90]], ["si", "se", "PRON", [91, 93]], ["je", "on", "PRON", [94, 96]], ["teoreticky", "teoreticky", "ADV", [97, 107]], ["mohl", "moci", "VERB", [108, 112]], ["vyt\u00e1hnout", "vyt\u00e1hnout", "VERB", [113, 122]], ["s\u00e1m", "sam\u00fd", "DET", [123, 126]], ["(", "(", "PUNCT", [127, 128]], ["dovedete", "dov\u00e9st", "VERB", [128, 136]], ["si", "se", "PRON", [137, 139]], ["p\u0159edstavit", "p\u0159edstavit", "VERB", [140, 150]], ["ty", "ten", "DET", [151, 153]], ["\"", "\"", "PUNCT", [154, 155]], ["ochotn\u00e9", "ochotn\u00fd", "ADJ", [155, 162]], ["\"", "\"", "PUNCT", [162, 163]], ["prodava\u010dky", "prodava\u010dka", "NOUN", [164, 174]], ["v", "v", "ADP", [175, 176]], ["\u010cesku", "\u010cesko", "PROPN", [177, 182]], ["?", "?", "PUNCT", [182, 183]], [")", ")", "PUNCT", [183, 184]], [".", ".", "PUNCT", [184, 185]]]], ["calgarske-listy_2003_unor_ocr.txt", "D\u016fchodce vypadal jako Raymond Cromley a cht\u011bl kn\u00ed\u017eky o Berl\u00edn\u011b.", [["D\u016fchodce", "d\u016fchodce", "NOUN", [0, 8]], ["vypadal", "vypadat", "VERB", [9, 16]], ["jako", "jako", "SCONJ", [17, 21]], ["Raymond", "Raymond", "PROPN", [22, 29]], ["Cromley", "Cromley", "PROPN", [30, 37]], ["a", "a", "CCONJ", [38, 39]], ["cht\u011bl", "cht\u00edt", "VERB", [40, 45]], ["kn\u00ed\u017eky", "kn\u00ed\u017eka", "NOUN", [46, 52]], ["o", "o", "ADP", [53, 54]], ["Berl\u00edn\u011b", "Berl\u00edn", "PROPN", [55, 62]], [".", ".", "PUNCT", [62, 63]]]], ["calgarske-listy_2003_unor_ocr.txt", "A tak jsem nakonec i j\u00e1 str\u00e1vil p\u011bknou chv\u00edli pov\u00edd\u00e1n\u00edm s prodava\u010dkou, kter\u00e1 nikoho nenapadala a neodsek\u00e1vala, a s d\u016fchodcem se z\u00e1jmem o Berl\u00edn.", [["A", "a", "CCONJ", [0, 1]], ["tak", "tak", "ADV", [2, 5]], ["jsem", "b\u00fdt", "AUX", [6, 10]], ["nakonec", "nakonec", "ADV", [11, 18]], ["i", "i", "CCONJ", [19, 20]], ["j\u00e1", "j\u00e1", "PRON", [21, 23]], ["str\u00e1vil", "str\u00e1vit", "VERB", [24, 31]], ["p\u011bknou", "p\u011bkn\u00fd", "ADJ", [32, 38]], ["chv\u00edli", "chv\u00edle", "NOUN", [39, 45]], ["pov\u00edd\u00e1n\u00edm", "pov\u00edd\u00e1n\u00ed", "NOUN", [46, 55]], ["s", "s", "ADP", [56, 57]], ["prodava\u010dkou", "prodava\u010dka", "NOUN", [58, 69]], [",", ",", "PUNCT", [69, 70]], ["kter\u00e1", "kter\u00fd", "DET", [71, 76]], ["nikoho", "nikdo", "PRON", [77, 83]], ["nenapadala", "napadat", "VERB", [84, 94]], ["a", "a", "CCONJ", [95, 96]], ["neodsek\u00e1vala", "odsek\u00e1vat", "VERB", [97, 109]], [",", ",", "PUNCT", [109, 110]], ["a", "a", "CCONJ", [111, 112]], ["s", "s", "ADP", [113, 114]], ["d\u016fchodcem", "d\u016fchodce", "NOUN", [115, 124]], ["se", "s", "ADP", [125, 127]], ["z\u00e1jmem", "z\u00e1jem", "NOUN", [128, 134]], ["o", "o", "ADP", [135, 136]], ["Berl\u00edn", "Berl\u00edn", "PROPN", [137, 143]], [".", ".", "PUNCT", [143, 144]]]], ["calgarske-listy_2003_unor_ocr.txt", "Raymond Cromley nikdy nebyl v Berl\u00edn\u011b, je report\u00e9rem v Pentagonu.", [["Raymond", "Raymond", "PROPN", [0, 7]], ["Cromley", "Cromley", "PROPN", [8, 15]], ["nikdy", "nikdy", "ADV", [16, 21]], ["nebyl", "b\u00fdt", "AUX", [22, 27]], ["v", "v", "ADP", [28, 29]], ["Berl\u00edn\u011b", "Berl\u00edn", "PROPN", [30, 37]], [",", ",", "PUNCT", [37, 38]], ["je", "b\u00fdt", "AUX", [39, 41]], ["report\u00e9rem", "report\u00e9r", "NOUN", [42, 52]], ["v", "v", "ADP", [53, 54]], ["Pentagonu", "Pentagon", "PROPN", [55, 64]], [".", ".", "PUNCT", [64, 65]]]], ["calgarske-listy_2003_unor_ocr.txt", "T\u00edm \u00fapln\u011b nej star\u0161\u00edm.", [["T\u00edm", "ten", "DET", [0, 3]], ["\u00fapln\u011b", "\u00fapln\u011b", "ADV", [4, 9]], ["nej", "nej", "INTJ", [10, 13]], ["star\u0161\u00edm", "star\u00fd", "ADJ", [14, 21]], [".", ".", "PUNCT", [21, 22]]]], ["calgarske-listy_2003_unor_ocr.txt", "Akreditaci report\u00e9ra m\u00e1 v Pentagonu p\u0159es 500 lid\u00ed.", [["Akreditaci", "akreditace", "NOUN", [0, 10]], ["report\u00e9ra", "report\u00e9r", "NOUN", [11, 20]], ["m\u00e1", "m\u00edt", "VERB", [21, 23]], ["v", "v", "ADP", [24, 25]], ["Pentagonu", "Pentagon", "PROPN", [26, 35]], ["p\u0159es", "p\u0159es", "ADP", [36, 40]], ["500", "500", "NUM", [41, 44]], ["lid\u00ed", "lid\u00e9", "NOUN", [45, 49]], [".", ".", "PUNCT", [49, 50]]]], ["calgarske-listy_2003_unor_ocr.txt", "Jedn\u00edm z nich je Raymond Cromley, v\u00fdhradn\u00ed zpravodaj pro Cromley News Service.", [["Jedn\u00edm", "jeden", "NUM", [0, 6]], ["z", "z", "ADP", [7, 8]], ["nich", "on", "PRON", [9, 13]], ["je", "b\u00fdt", "AUX", [14, 16]], ["Raymond", "Raymond", "PROPN", [17, 24]], ["Cromley", "Cromley", "PROPN", [25, 32]], [",", ",", "PUNCT", [32, 33]], ["v\u00fdhradn\u00ed", "v\u00fdhradn\u00ed", "ADJ", [34, 42]], ["zpravodaj", "zpravodaj", "NOUN", [43, 52]], ["pro", "pro", "ADP", [53, 56]], ["Cromley", "Cromley", "X", [57, 64]], ["News", "News", "X", [65, 69]], ["Service", "Service", "X", [70, 77]], [".", ".", "PUNCT", [77, 78]]]], ["calgarske-listy_2003_unor_ocr.txt", "Je mu 91 let, v jeho kancel\u00e1\u0159i je star\u00fd psac\u00ed stroj Royal bez p\u00e1sky, 1971 World Almanac a 17 zubn\u00edch kart\u00e1\u010dk\u016f v plastick\u00e9m kel\u00edmku.", [["Je", "b\u00fdt", "AUX", [0, 2]], ["mu", "on", "PRON", [3, 5]], ["91", "91", "NUM", [6, 8]], ["let", "l\u00e9ta", "NOUN", [9, 12]], [",", ",", "PUNCT", [12, 13]], ["v", "v", "ADP", [14, 15]], ["jeho", "jeho", "DET", [16, 20]], ["kancel\u00e1\u0159i", "kancel\u00e1\u0159", "NOUN", [21, 30]], ["je", "b\u00fdt", "AUX", [31, 33]], ["star\u00fd", "star\u00fd", "ADJ", [34, 39]], ["psac\u00ed", "psac\u00ed", "ADJ", [40, 45]], ["stroj", "stroj", "NOUN", [46, 51]], ["Royal", "Royal", "PROPN", [52, 57]], ["bez", "bez", "ADP", [58, 61]], ["p\u00e1sky", "p\u00e1ska", "NOUN", [62, 67]], [",", ",", "PUNCT", [67, 68]], ["1971", "1971", "NUM", [69, 73]], ["World", "World", "X", [74, 79]], ["Almanac", "Almanac", "X", [80, 87]], ["a", "a", "CCONJ", [88, 89]], ["17", "17", "NUM", [90, 92]], ["zubn\u00edch", "zubn\u00ed", "ADJ", [93, 100]], ["kart\u00e1\u010dk\u016f", "kart\u00e1\u010dek", "NOUN", [101, 109]], ["v", "v", "ADP", [110, 111]], ["plastick\u00e9m", "plastick\u00fd", "ADJ", [112, 122]], ["kel\u00edmku", "kel\u00edmek", "NOUN", [123, 130]], [".", ".", "PUNCT", [130, 131]]]], ["calgarske-listy_2003_unor_ocr.txt", "Na pravideln\u00fdch tiskov\u00fdch konferenc\u00edch sed\u00ed v prvn\u00ed \u0159ad\u011b a d\u011bl\u00e1 si pozn\u00e1mky na \u010dtvrtky pap\u00edru, kter\u00e9 mu pasuj\u00ed do kapsy na ko\u0161ili.", [["Na", "na", "ADP", [0, 2]], ["pravideln\u00fdch", "pravideln\u00fd", "ADJ", [3, 15]], ["tiskov\u00fdch", "tiskov\u00fd", "ADJ", [16, 25]], ["konferenc\u00edch", "konference", "NOUN", [26, 38]], ["sed\u00ed", "sed\u011bt", "VERB", [39, 43]], ["v", "v", "ADP", [44, 45]], ["prvn\u00ed", "prvn\u00ed", "ADJ", [46, 51]], ["\u0159ad\u011b", "\u0159ada", "NOUN", [52, 56]], ["a", "a", "CCONJ", [57, 58]], ["d\u011bl\u00e1", "d\u011blat", "VERB", [59, 63]], ["si", "se", "PRON", [64, 66]], ["pozn\u00e1mky", "pozn\u00e1mka", "NOUN", [67, 75]], ["na", "na", "ADP", [76, 78]], ["\u010dtvrtky", "\u010dtvrtek", "NOUN", [79, 86]], ["pap\u00edru", "pap\u00edr", "NOUN", [87, 93]], [",", ",", "PUNCT", [93, 94]], ["kter\u00e9", "kter\u00fd", "DET", [95, 100]], ["mu", "on", "PRON", [101, 103]], ["pasuj\u00ed", "pasovat", "VERB", [104, 110]], ["do", "do", "ADP", [111, 113]], ["kapsy", "kapsa", "NOUN", [114, 119]], ["na", "na", "ADP", [120, 122]], ["ko\u0161ili", "ko\u0161ile", "NOUN", [123, 129]], [".", ".", "PUNCT", [129, 130]]]], ["calgarske-listy_2003_unor_ocr.txt", "Jeho fotka vis\u00ed na zdi spolu s ostatn\u00edmi report\u00e9ry z Pentagonu.", [["Jeho", "jeho", "DET", [0, 4]], ["fotka", "fotka", "NOUN", [5, 10]], ["vis\u00ed", "viset", "VERB", [11, 15]], ["na", "na", "ADP", [16, 18]], ["zdi", "ze\u010f", "NOUN", [19, 22]], ["spolu", "spolu", "ADV", [23, 28]], ["s", "s", "ADP", [29, 30]], ["ostatn\u00edmi", "ostatn\u00ed", "ADJ", [31, 40]], ["report\u00e9ry", "report\u00e9r", "NOUN", [41, 50]], ["z", "z", "ADP", [51, 52]], ["Pentagonu", "Pentagon", "PROPN", [53, 62]], [".", ".", "PUNCT", [62, 63]]]], ["calgarske-listy_2003_unor_ocr.txt", "Pokud je zn\u00e1mo, tak Raymond Cromley nenapsal \u017e\u00e1dnou report\u00e1\u017e u\u017e \u0159adu let, ale nikomu to nevad\u00ed.", [["Pokud", "pokud", "SCONJ", [0, 5]], ["je", "b\u00fdt", "AUX", [6, 8]], ["zn\u00e1mo", "zn\u00e1m\u00fd", "ADJ", [9, 14]], [",", ",", "PUNCT", [14, 15]], ["tak", "tak", "ADV", [16, 19]], ["Raymond", "Raymond", "PROPN", [20, 27]], ["Cromley", "Cromley", "PROPN", [28, 35]], ["nenapsal", "napsat", "VERB", [36, 44]], ["\u017e\u00e1dnou", "\u017e\u00e1dn\u00fd", "DET", [45, 51]], ["report\u00e1\u017e", "report\u00e1\u017e", "NOUN", [52, 60]], ["u\u017e", "u\u017e", "ADV", [61, 63]], ["\u0159adu", "\u0159ada", "NOUN", [64, 68]], ["let", "l\u00e9ta", "NOUN", [69, 72]], [",", ",", "PUNCT", [72, 73]], ["ale", "ale", "CCONJ", [74, 77]], ["nikomu", "nikdo", "PRON", [78, 84]], ["to", "ten", "DET", [85, 87]], ["nevad\u00ed", "vadit", "VERB", [88, 94]], [".", ".", "PUNCT", [94, 95]]]], ["calgarske-listy_2003_unor_ocr.txt", "Tenhle d\u016fchodce chod\u00ed po Pentagonu ve vytahan\u00e9m svetru a br\u00fdl\u00edch jak\u00e9 nos\u00edval Felix Holzmann.", [["Tenhle", "tenhle", "DET", [0, 6]], ["d\u016fchodce", "d\u016fchodce", "NOUN", [7, 15]], ["chod\u00ed", "chodit", "VERB", [16, 21]], ["po", "po", "ADP", [22, 24]], ["Pentagonu", "Pentagon", "PROPN", [25, 34]], ["ve", "v", "ADP", [35, 37]], ["vytahan\u00e9m", "vytahan\u00fd", "ADJ", [38, 47]], ["svetru", "svetr", "NOUN", [48, 54]], ["a", "a", "CCONJ", [55, 56]], ["br\u00fdl\u00edch", "br\u00fdle", "NOUN", [57, 64]], ["jak\u00e9", "jak\u00fd", "DET", [65, 69]], ["nos\u00edval", "nos\u00edvat", "VERB", [70, 77]], ["Felix", "Felix", "PROPN", [78, 83]], ["Holzmann", "Holzmann", "PROPN", [84, 92]], [".", ".", "PUNCT", [92, 93]]]], ["calgarske-listy_2003_unor_ocr.txt", "Ka\u017ed\u00e9 r\u00e1no p\u0159ijede do kancel\u00e1\u0159e sv\u00fdm dvacet let star\u00fdm Mercedesem a jde si zaplavat do Pentagon Officers Athletic Club.", [["Ka\u017ed\u00e9", "ka\u017ed\u00fd", "DET", [0, 5]], ["r\u00e1no", "r\u00e1no", "ADV", [6, 10]], ["p\u0159ijede", "p\u0159ijet", "VERB", [11, 18]], ["do", "do", "ADP", [19, 21]], ["kancel\u00e1\u0159e", "kancel\u00e1\u0159", "NOUN", [22, 31]], ["sv\u00fdm", "sv\u016fj", "DET", [32, 36]], ["dvacet", "dvacet", "NUM", [37, 43]], ["let", "l\u00e9ta", "NOUN", [44, 47]], ["star\u00fdm", "star\u00fd", "ADJ", [48, 54]], ["Mercedesem", "Mercedes", "PROPN", [55, 65]], ["a", "a", "CCONJ", [66, 67]], ["jde", "j\u00edt", "VERB", [68, 71]], ["si", "se", "PRON", [72, 74]], ["zaplavat", "zaplavat", "VERB", [75, 83]], ["do", "do", "ADP", [84, 86]], ["Pentagon", "pentagon", "X", [87, 95]], ["Officers", "Officers", "X", [96, 104]], ["Athletic", "Athletic", "X", [105, 113]], ["Club", "Club", "X", [114, 118]], [".", ".", "PUNCT", [118, 119]]]], ["calgarske-listy_2003_unor_ocr.txt", "Pak zkontroluje kursy na stock marketu a jde si vz\u00edt nov\u00e9 press releases.", [["Pak", "pak", "ADV", [0, 3]], ["zkontroluje", "zkontrolovat", "VERB", [4, 15]], ["kursy", "kurs", "NOUN", [16, 21]], ["na", "na", "ADP", [22, 24]], ["stock", "stock", "ADJ", [25, 30]], ["marketu", "market", "NOUN", [31, 38]], ["a", "a", "CCONJ", [39, 40]], ["jde", "j\u00edt", "VERB", [41, 44]], ["si", "se", "PRON", [45, 47]], ["vz\u00edt", "vz\u00edt", "VERB", [48, 52]], ["nov\u00e9", "nov\u00fd", "ADJ", [53, 57]], ["press", "press", "X", [58, 63]], ["releases", "releases", "X", [64, 72]], [".", ".", "PUNCT", [72, 73]]]], ["calgarske-listy_2003_unor_ocr.txt", "P\u0159i tiskov\u00fdch konferenc\u00edch report\u00e9\u0159i v\u0159\u00edskaj\u00ed jeden p\u0159es druh\u00e9ho, aby jim bu\u010f Kenneth Bacon nebo Donald Rumsfeld odpov\u011bd\u011bl, ale star\u00fd p\u00e1n Cromley se nikdy nept\u00e1.", [["P\u0159i", "p\u0159i", "ADP", [0, 3]], ["tiskov\u00fdch", "tiskov\u00fd", "ADJ", [4, 13]], ["konferenc\u00edch", "konference", "NOUN", [14, 26]], ["report\u00e9\u0159i", "report\u00e9r", "NOUN", [27, 36]], ["v\u0159\u00edskaj\u00ed", "v\u0159\u00edskat", "VERB", [37, 45]], ["jeden", "jeden", "NUM", [46, 51]], ["p\u0159es", "p\u0159es", "ADP", [52, 56]], ["druh\u00e9ho", "druh\u00fd", "ADJ", [57, 64]], [",", ",", "PUNCT", [64, 65]], ["aby", "aby", "SCONJ", [-384, -384]], ["by", "b\u00fdt", "AUX", [-384, -384]], ["jim", "on", "PRON", [70, 73]], ["bu\u010f", "bu\u010f", "CCONJ", [74, 77]], ["Kenneth", "Kenneth", "PROPN", [78, 85]], ["Bacon", "Bacon", "PROPN", [86, 91]], ["nebo", "nebo", "CCONJ", [92, 96]], ["Donald", "Donald", "PROPN", [97, 103]], ["Rumsfeld", "Rumsfeld", "PROPN", [104, 112]], ["odpov\u011bd\u011bl", "odpov\u011bd\u011bt", "VERB", [113, 122]], [",", ",", "PUNCT", [122, 123]], ["ale", "ale", "CCONJ", [124, 127]], ["star\u00fd", "star\u00fd", "ADJ", [128, 133]], ["p\u00e1n", "p\u00e1n", "NOUN", [134, 137]], ["Cromley", "Cromley", "PROPN", [138, 145]], ["se", "se", "PRON", [146, 148]], ["nikdy", "nikdy", "ADV", [149, 154]], ["nept\u00e1", "pt\u00e1t", "VERB", [155, 160]], [".", ".", "PUNCT", [160, 161]]]], ["calgarske-listy_2003_unor_ocr.txt", "Pouze te\u010f za\u010d\u00e1tkem \u00fanora promluvil.", [["Pouze", "pouze", "ADV", [0, 5]], ["te\u010f", "te\u010f", "ADV", [6, 9]], ["za\u010d\u00e1tkem", "za\u010d\u00e1tek", "NOUN", [10, 18]], ["\u00fanora", "\u00fanor", "NOUN", [19, 24]], ["promluvil", "promluvit", "VERB", [25, 34]], [".", ".", "PUNCT", [34, 35]]]], ["calgarske-listy_2003_unor_ocr.txt", "Rummy zrovna vysv\u011btloval, \u017ee p\u0159i bombardovan\u00ed vojensk\u00fdch c\u00edl\u016f v\u017edy m\u016f\u017eou b\u00fdt civiln\u00ed ob\u011bti, kdy\u017e tu se ozvalo z prvn\u00ed \u0159ady: \"I was bombed\" (J\u00e1 jsem byl bombardov\u00e1n).\"", [["Rummy", "rumma", "NOUN", [0, 5]], ["zrovna", "zrovna", "ADV", [6, 12]], ["vysv\u011btloval", "vysv\u011btlovat", "VERB", [13, 24]], [",", ",", "PUNCT", [24, 25]], ["\u017ee", "\u017ee", "SCONJ", [26, 28]], ["p\u0159i", "p\u0159i", "ADP", [29, 32]], ["bombardovan\u00ed", "bombardovan\u00fd", "ADJ", [33, 45]], ["vojensk\u00fdch", "vojensk\u00fd", "ADJ", [46, 56]], ["c\u00edl\u016f", "c\u00edl", "NOUN", [57, 61]], ["v\u017edy", "v\u017edy", "ADV", [62, 66]], ["m\u016f\u017eou", "moci", "VERB", [67, 72]], ["b\u00fdt", "b\u00fdt", "AUX", [73, 76]], ["civiln\u00ed", "civiln\u00ed", "ADJ", [77, 84]], ["ob\u011bti", "ob\u011b\u0165", "NOUN", [85, 90]], [",", ",", "PUNCT", [90, 91]], ["kdy\u017e", "kdy\u017e", "SCONJ", [92, 96]], ["tu", "tu", "ADV", [97, 99]], ["se", "se", "PRON", [100, 102]], ["ozvalo", "ozvat", "VERB", [103, 109]], ["z", "z", "ADP", [110, 111]], ["prvn\u00ed", "prvn\u00ed", "ADJ", [112, 117]], ["\u0159ady", "\u0159ada", "NOUN", [118, 122]], [":", ":", "PUNCT", [122, 123]], ["\"", "\"", "PUNCT", [124, 125]], ["I", "i", "CCONJ", [125, 126]], ["was", "was", "X", [127, 130]], ["bombed", "bombed", "X", [131, 137]], ["\"", "\"", "PUNCT", [137, 138]], ["(", "(", "PUNCT", [139, 140]], ["J\u00e1", "j\u00e1", "PRON", [140, 142]], ["jsem", "b\u00fdt", "AUX", [143, 147]], ["byl", "b\u00fdt", "AUX", [148, 151]], ["bombardov\u00e1n", "bombardovan\u00fd", "ADJ", [152, 163]], [")", ")", "PUNCT", [163, 164]], [".", ".", "PUNCT", [164, 165]], ["\"", "\"", "PUNCT", [165, 166]]]], ["calgarske-listy_2003_unor_ocr.txt", "Wha\u0165d you say?\"", [["Wha\u0165d", "Wha\u0165d", "X", [0, 5]], ["you", "you", "X", [6, 9]], ["say", "say", "X", [10, 13]], ["?", "?", "PUNCT", [13, 14]], ["\"", "\"", "PUNCT", [14, 15]]]], ["calgarske-listy_2003_unor_ocr.txt", "(Co\u017ee?) ztuhl v Rumsfeld.", [["(", "(", "PUNCT", [0, 1]], ["Co\u017ee", "co\u017ee", "INTJ", [1, 5]], ["?", "?", "PUNCT", [5, 6]], [")", ")", "PUNCT", [6, 7]], ["ztuhl", "ztuhnout", "VERB", [8, 13]], ["v", "v", "ADP", [14, 15]], ["Rumsfeld", "Rumsfeld", "PROPN", [16, 24]], [".", ".", "PUNCT", [24, 25]]]], ["calgarske-listy_2003_unor_ocr.txt", "\"I said I was bombed\" (\u0158ekl jsem, \u017ee jsem byl bombardov\u00e1n), potvrdil klidn\u011b pan Cromley.", [["\"", "\"", "PUNCT", [0, 1]], ["I", "i", "CCONJ", [1, 2]], ["said", "said", "X", [3, 7]], ["I", "I", "X", [8, 9]], ["was", "was", "X", [10, 13]], ["bombed", "bombed", "X", [14, 20]], ["\"", "\"", "PUNCT", [20, 21]], ["(", "(", "PUNCT", [22, 23]], ["\u0158ekl", "\u0159\u00edci", "VERB", [23, 27]], ["jsem", "b\u00fdt", "AUX", [28, 32]], [",", ",", "PUNCT", [32, 33]], ["\u017ee", "\u017ee", "SCONJ", [34, 36]], ["jsem", "b\u00fdt", "AUX", [37, 41]], ["byl", "b\u00fdt", "AUX", [42, 45]], ["bombardov\u00e1n", "bombardovan\u00fd", "ADJ", [46, 57]], [")", ")", "PUNCT", [57, 58]], [",", ",", "PUNCT", [58, 59]], ["potvrdil", "potvrdit", "VERB", [60, 68]], ["klidn\u011b", "klidn\u011b", "ADV", [69, 75]], ["pan", "pan", "NOUN", [76, 79]], ["Cromley", "Cromley", "PROPN", [80, 87]], [".", ".", "PUNCT", [87, 88]]]], ["calgarske-listy_2003_unor_ocr.txt", "\"You were?\" (V\u00e1\u017en\u011b?), d\u011bsil se Rumsfeld.", [["\"", "\"", "PUNCT", [0, 1]], ["You", "You", "X", [1, 4]], ["were", "were", "X", [5, 9]], ["?", "?", "PUNCT", [9, 10]], ["\"", "\"", "PUNCT", [10, 11]], ["(", "(", "PUNCT", [12, 13]], ["V\u00e1\u017en\u011b", "v\u00e1\u017en\u011b", "ADV", [13, 18]], ["?", "?", "PUNCT", [18, 19]], [")", ")", "PUNCT", [19, 20]], [",", ",", "PUNCT", [20, 21]], ["d\u011bsil", "d\u011bsit", "VERB", [22, 27]], ["se", "se", "PRON", [28, 30]], ["Rumsfeld", "Rumsfeld", "PROPN", [31, 39]], [".", ".", "PUNCT", [39, 40]]]], ["calgarske-listy_2003_unor_ocr.txt", "\"In World War II. Yes, sir.\" (Ano, ve druh\u00e9 sv\u011btov\u00e9 v\u00e1lce).", [["\"", "\"", "PUNCT", [0, 1]], ["In", "In", "X", [1, 3]], ["World", "World", "X", [4, 9]], ["War", "War", "X", [10, 13]], ["II", "II", "NUM", [14, 16]], [".", ".", "PUNCT", [16, 17]], ["Yes", "Yes", "PROPN", [18, 21]], [",", ",", "PUNCT", [21, 22]], ["sir", "sir", "NOUN", [23, 26]], [".", ".", "PUNCT", [26, 27]], ["\"", "\"", "PUNCT", [27, 28]], ["(", "(", "PUNCT", [29, 30]], ["Ano", "ano", "PART", [30, 33]], [",", ",", "PUNCT", [33, 34]], ["ve", "v", "ADP", [35, 37]], ["druh\u00e9", "druh\u00fd", "ADJ", [38, 43]], ["sv\u011btov\u00e9", "sv\u011btov\u00fd", "ADJ", [44, 51]], ["v\u00e1lce", "v\u00e1lka", "NOUN", [52, 57]], [")", ")", "PUNCT", [57, 58]], [".", ".", "PUNCT", [58, 59]]]], ["calgarske-listy_2003_unor_ocr.txt", "Mezi ostatn\u00edmi report\u00e9ry koluj\u00ed f\u00e1my o p\u00e1n\u011b Cromleyho minulosti - \u017ee je \u0161\u00edlen\u00fd milion\u00e1\u0159, \u017ee byl v OSS, \u017ee m\u011bl z\u00e1kaz psan\u00ed v pades\u00e1t\u00fdch letech.", [["Mezi", "mezi", "ADP", [0, 4]], ["ostatn\u00edmi", "ostatn\u00ed", "ADJ", [5, 14]], ["report\u00e9ry", "report\u00e9r", "NOUN", [15, 24]], ["koluj\u00ed", "kolovat", "VERB", [25, 31]], ["f\u00e1my", "f\u00e1ma", "NOUN", [32, 36]], ["o", "o", "ADP", [37, 38]], ["p\u00e1n\u011b", "p\u00e1n", "NOUN", [39, 43]], ["Cromleyho", "Cromley", "PROPN", [44, 53]], ["minulosti", "minulost", "NOUN", [54, 63]], ["-", "-", "PUNCT", [64, 65]], ["\u017ee", "\u017ee", "SCONJ", [66, 68]], ["je", "b\u00fdt", "AUX", [69, 71]], ["\u0161\u00edlen\u00fd", "\u0161\u00edlen\u00fd", "ADJ", [72, 78]], ["milion\u00e1\u0159", "milion\u00e1\u0159", "NOUN", [79, 87]], [",", ",", "PUNCT", [87, 88]], ["\u017ee", "\u017ee", "SCONJ", [89, 91]], ["byl", "b\u00fdt", "AUX", [92, 95]], ["v", "v", "ADP", [96, 97]], ["OSS", "OSS", "NOUN", [98, 101]], [",", ",", "PUNCT", [101, 102]], ["\u017ee", "\u017ee", "SCONJ", [103, 105]], ["m\u011bl", "m\u00edt", "VERB", [106, 109]], ["z\u00e1kaz", "z\u00e1kaz", "NOUN", [110, 115]], ["psan\u00ed", "psan\u00ed", "NOUN", [116, 121]], ["v", "v", "ADP", [122, 123]], ["pades\u00e1t\u00fdch", "pades\u00e1t\u00fd", "ADJ", [124, 134]], ["letech", "l\u00e9ta", "NOUN", [135, 141]], [".", ".", "PUNCT", [141, 142]]]], ["calgarske-listy_2003_unor_ocr.txt", "Cromley s\u00e1m \u0159\u00edk\u00e1, \u017ee jsou to blbosti, \u017ee byl v\u017edycky Republik\u00e1n.", [["Cromley", "Cromley", "PROPN", [0, 7]], ["s\u00e1m", "sam\u00fd", "DET", [8, 11]], ["\u0159\u00edk\u00e1", "\u0159\u00edkat", "VERB", [12, 16]], [",", ",", "PUNCT", [16, 17]], ["\u017ee", "\u017ee", "SCONJ", [18, 20]], ["jsou", "b\u00fdt", "AUX", [21, 25]], ["to", "ten", "DET", [26, 28]], ["blbosti", "blbost", "NOUN", [29, 36]], [",", ",", "PUNCT", [36, 37]], ["\u017ee", "\u017ee", "SCONJ", [38, 40]], ["byl", "b\u00fdt", "AUX", [41, 44]], ["v\u017edycky", "v\u017edycky", "ADV", [45, 52]], ["Republik\u00e1n", "republik\u00e1n", "PROPN", [53, 63]], [".", ".", "PUNCT", [63, 64]]]], ["calgarske-listy_2003_unor_ocr.txt", "A skute\u010dnost je mnohem zaj\u00edmav\u011bj\u0161\u00ed ne\u017e v\u0161echny f\u00e1my.", [["A", "a", "CCONJ", [0, 1]], ["skute\u010dnost", "skute\u010dnost", "NOUN", [2, 12]], ["je", "b\u00fdt", "AUX", [13, 15]], ["mnohem", "mnohem", "ADV", [16, 22]], ["zaj\u00edmav\u011bj\u0161\u00ed", "zaj\u00edmav\u00fd", "ADJ", [23, 34]], ["ne\u017e", "ne\u017e", "SCONJ", [35, 38]], ["v\u0161echny", "v\u0161echen", "DET", [39, 46]], ["f\u00e1my", "f\u00e1ma", "NOUN", [47, 51]], [".", ".", "PUNCT", [51, 52]]]], ["calgarske-listy_2003_unor_ocr.txt", "V t\u0159ic\u00e1t\u00fdch letech za\u010dal Raymond Cromley, syn kalifornsk\u00e9ho farm\u00e1\u0159e, studovat fyziku na Cal tech v Pasaden\u011b, kde se sp\u0159\u00e1telil s Albertem Einsteinem, kter\u00fd tam hr\u00e1val na housle a violu.", [["V", "v", "ADP", [0, 1]], ["t\u0159ic\u00e1t\u00fdch", "t\u0159ic\u00e1t\u00fd", "ADJ", [2, 11]], ["letech", "l\u00e9ta", "NOUN", [12, 18]], ["za\u010dal", "za\u010d\u00edt", "VERB", [19, 24]], ["Raymond", "Raymond", "PROPN", [25, 32]], ["Cromley", "Cromley", "PROPN", [33, 40]], [",", ",", "PUNCT", [40, 41]], ["syn", "syn", "NOUN", [42, 45]], ["kalifornsk\u00e9ho", "kalifornsk\u00fd", "ADJ", [46, 59]], ["farm\u00e1\u0159e", "farm\u00e1\u0159", "NOUN", [60, 67]], [",", ",", "PUNCT", [67, 68]], ["studovat", "studovat", "VERB", [69, 77]], ["fyziku", "fyzika", "NOUN", [78, 84]], ["na", "na", "ADP", [85, 87]], ["Cal", "Cal", "X", [88, 91]], ["tech", "tech", "X", [92, 96]], ["v", "v", "ADP", [97, 98]], ["Pasaden\u011b", "Pasadena", "PROPN", [99, 107]], [",", ",", "PUNCT", [107, 108]], ["kde", "kde", "ADV", [109, 112]], ["se", "se", "PRON", [113, 115]], ["sp\u0159\u00e1telil", "sp\u0159\u00e1telit", "VERB", [116, 125]], ["s", "s", "ADP", [126, 127]], ["Albertem", "Albert", "PROPN", [128, 136]], ["Einsteinem", "Einstein", "PROPN", [137, 147]], [",", ",", "PUNCT", [147, 148]], ["kter\u00fd", "kter\u00fd", "DET", [149, 154]], ["tam", "tam", "ADV", [155, 158]], ["hr\u00e1val", "hr\u00e1vat", "VERB", [159, 165]], ["na", "na", "ADP", [166, 168]], ["housle", "housle", "NOUN", [169, 175]], ["a", "a", "CCONJ", [176, 177]], ["violu", "viola", "NOUN", [178, 183]], [".", ".", "PUNCT", [183, 184]]]], ["calgarske-listy_2003_unor_ocr.txt", "\"Jeden z nejhor\u0161\u00edch houslist\u016f, kter\u00e9 jsem kdy sly\u0161el\", prav\u00ed dnes Cromley.", [["\"", "\"", "PUNCT", [0, 1]], ["Jeden", "jeden", "NUM", [1, 6]], ["z", "z", "ADP", [7, 8]], ["nejhor\u0161\u00edch", "hor\u0161\u00ed", "ADJ", [9, 19]], ["houslist\u016f", "houslista", "NOUN", [20, 29]], [",", ",", "PUNCT", [29, 30]], ["kter\u00e9", "kter\u00fd", "DET", [31, 36]], ["jsem", "b\u00fdt", "AUX", [37, 41]], ["kdy", "kdy", "ADV", [42, 45]], ["sly\u0161el", "sly\u0161et", "VERB", [46, 52]], ["\"", "\"", "PUNCT", [52, 53]], [",", ",", "PUNCT", [53, 54]], ["prav\u00ed", "pravit", "VERB", [55, 60]], ["dnes", "dnes", "ADV", [61, 65]], ["Cromley", "Cromley", "PROPN", [66, 73]], [".", ".", "PUNCT", [73, 74]]]], ["calgarske-listy_2003_unor_ocr.txt", "Mlad\u00fd Cromley dokon\u010dil studium fyziky v roce 1933 a p\u0159est\u011bhoval se do Japonska, proto\u017ee se mu to zd\u00e1lo dobrodru\u017en\u00e9.", [["Mlad\u00fd", "mlad\u00fd", "ADJ", [0, 5]], ["Cromley", "Cromley", "PROPN", [6, 13]], ["dokon\u010dil", "dokon\u010dit", "VERB", [14, 22]], ["studium", "studium", "NOUN", [23, 30]], ["fyziky", "fyzika", "NOUN", [31, 37]], ["v", "v", "ADP", [38, 39]], ["roce", "rok", "NOUN", [40, 44]], ["1933", "1933", "NUM", [45, 49]], ["a", "a", "CCONJ", [50, 51]], ["p\u0159est\u011bhoval", "p\u0159est\u011bhovat", "VERB", [52, 63]], ["se", "se", "PRON", [64, 66]], ["do", "do", "ADP", [67, 69]], ["Japonska", "Japonsko", "PROPN", [70, 78]], [",", ",", "PUNCT", [78, 79]], ["proto\u017ee", "proto\u017ee", "SCONJ", [80, 87]], ["se", "se", "PRON", [88, 90]], ["mu", "on", "PRON", [91, 93]], ["to", "ten", "DET", [94, 96]], ["zd\u00e1lo", "zd\u00e1t", "VERB", [97, 102]], ["dobrodru\u017en\u00e9", "dobrodru\u017en\u00fd", "ADJ", [103, 114]], [".", ".", "PUNCT", [114, 115]]]], ["calgarske-listy_2003_unor_ocr.txt", "Ve vlaku se sezn\u00e1mil se studentkou medic\u00edny jm\u00e9nem Masuyo, brzo se s n\u00ed o\u017eenil, m\u011bli syna jm\u00e9nem Donald a Cromley za\u010dal ps\u00e1t pro Wall Street Journal v Tokyu.", [["Ve", "v", "ADP", [0, 2]], ["vlaku", "vlak", "NOUN", [3, 8]], ["se", "se", "PRON", [9, 11]], ["sezn\u00e1mil", "sezn\u00e1mit", "VERB", [12, 20]], ["se", "s", "ADP", [21, 23]], ["studentkou", "studentka", "NOUN", [24, 34]], ["medic\u00edny", "medic\u00edna", "NOUN", [35, 43]], ["jm\u00e9nem", "jm\u00e9no", "NOUN", [44, 50]], ["Masuyo", "Masuyo", "PROPN", [51, 57]], [",", ",", "PUNCT", [57, 58]], ["brzo", "brzy", "ADV", [59, 63]], ["se", "se", "PRON", [64, 66]], ["s", "s", "ADP", [67, 68]], ["n\u00ed", "on", "PRON", [69, 71]], ["o\u017eenil", "o\u017eenit", "VERB", [72, 78]], [",", ",", "PUNCT", [78, 79]], ["m\u011bli", "m\u00edt", "VERB", [80, 84]], ["syna", "syn", "NOUN", [85, 89]], ["jm\u00e9nem", "jm\u00e9no", "NOUN", [90, 96]], ["Donald", "Donald", "PROPN", [97, 103]], ["a", "a", "CCONJ", [104, 105]], ["Cromley", "Cromley", "PROPN", [106, 113]], ["za\u010dal", "za\u010d\u00edt", "VERB", [114, 119]], ["ps\u00e1t", "ps\u00e1t", "VERB", [120, 124]], ["pro", "pro", "ADP", [125, 128]], ["Wall", "Wall", "X", [129, 133]], ["Street", "Street", "X", [134, 140]], ["Journal", "Journal", "X", [141, 148]], ["v", "v", "ADP", [149, 150]], ["Tokyu", "Tokyu", "PROPN", [151, 156]], [".", ".", "PUNCT", [156, 157]]]], ["calgarske-listy_2003_unor_ocr.txt", "P\u00e1r dn\u016f p\u0159ed japonsk\u00fdm \u00fatokem na Pearl Harbor byl Cromley spolu s ostatn\u00edmi americk\u00fdmi report\u00e9ry v Japonsku zat\u010den, dr\u017een na samotce a mu\u010den.", [["P\u00e1r", "p\u00e1r", "DET", [0, 3]], ["dn\u016f", "den", "NOUN", [4, 7]], ["p\u0159ed", "p\u0159ed", "ADP", [8, 12]], ["japonsk\u00fdm", "japonsk\u00fd", "ADJ", [13, 22]], ["\u00fatokem", "\u00fatok", "NOUN", [23, 29]], ["na", "na", "ADP", [30, 32]], ["Pearl", "Pearl", "X", [33, 38]], ["Harbor", "Harbor", "X", [39, 45]], ["byl", "b\u00fdt", "AUX", [46, 49]], ["Cromley", "Cromley", "PROPN", [50, 57]], ["spolu", "spolu", "ADV", [58, 63]], ["s", "s", "ADP", [64, 65]], ["ostatn\u00edmi", "ostatn\u00ed", "ADJ", [66, 75]], ["americk\u00fdmi", "americk\u00fd", "ADJ", [76, 86]], ["report\u00e9ry", "report\u00e9r", "NOUN", [87, 96]], ["v", "v", "ADP", [97, 98]], ["Japonsku", "Japonsko", "PROPN", [99, 107]], ["zat\u010den", "zat\u010den\u00fd", "ADJ", [108, 114]], [",", ",", "PUNCT", [114, 115]], ["dr\u017een", "dr\u017een\u00fd", "ADJ", [116, 121]], ["na", "na", "ADP", [122, 124]], ["samotce", "samotec", "NOUN", [125, 132]], ["a", "a", "CCONJ", [133, 134]], ["mu\u010den", "mu\u010den\u00fd", "ADJ", [135, 140]], [".", ".", "PUNCT", [140, 141]]]], ["calgarske-listy_2003_unor_ocr.txt", "Kdy\u017e Jimmy Doolittle bombardoval Tokyo v dubnu 1942, bomby padaly i na v\u011bzen\u00ed, kde byl Raymond Cromley zav\u0159en\u00fd.", [["Kdy\u017e", "kdy\u017e", "SCONJ", [0, 4]], ["Jimmy", "Jimmy", "PROPN", [5, 10]], ["Doolittle", "Doolittle", "PROPN", [11, 20]], ["bombardoval", "bombardovat", "VERB", [21, 32]], ["Tokyo", "Tokyo", "PROPN", [33, 38]], ["v", "v", "ADP", [39, 40]], ["dubnu", "duben", "NOUN", [41, 46]], ["1942", "1942", "NUM", [47, 51]], [",", ",", "PUNCT", [51, 52]], ["bomby", "bomba", "NOUN", [53, 58]], ["padaly", "padat", "VERB", [59, 65]], ["i", "i", "CCONJ", [66, 67]], ["na", "na", "ADP", [68, 70]], ["v\u011bzen\u00ed", "v\u011bzen\u00ed", "NOUN", [71, 77]], [",", ",", "PUNCT", [77, 78]], ["kde", "kde", "ADV", [79, 82]], ["byl", "b\u00fdt", "AUX", [83, 86]], ["Raymond", "Raymond", "PROPN", [87, 94]], ["Cromley", "Cromley", "PROPN", [95, 102]], ["zav\u0159en\u00fd", "zav\u0159en\u00fd", "ADJ", [103, 110]], [".", ".", "PUNCT", [110, 111]]]], ["calgarske-listy_2003_unor_ocr.txt", "A to bylo to bombardov\u00e1n\u00ed, o kter\u00e9m mluvil.", [["A", "a", "CCONJ", [0, 1]], ["to", "ten", "DET", [2, 4]], ["bylo", "b\u00fdt", "AUX", [5, 9]], ["to", "ten", "DET", [10, 12]], ["bombardov\u00e1n\u00ed", "bombardov\u00e1n\u00ed", "NOUN", [13, 25]], [",", ",", "PUNCT", [25, 26]], ["o", "o", "ADP", [27, 28]], ["kter\u00e9m", "kter\u00fd", "DET", [29, 35]], ["mluvil", "mluvit", "VERB", [36, 42]], [".", ".", "PUNCT", [42, 43]]]], ["calgarske-listy_2003_unor_ocr.txt", "O dva m\u011bs\u00edce pozd\u011bji byl Cromley vym\u011bn\u011bn za japonsk\u00e9 diplomaty, kte\u0159\u00ed byli dr\u017eeni ve Washingtonu.", [["O", "o", "ADP", [0, 1]], ["dva", "dva", "NUM", [2, 5]], ["m\u011bs\u00edce", "m\u011bs\u00edc", "NOUN", [6, 12]], ["pozd\u011bji", "pozd\u011b", "ADV", [13, 20]], ["byl", "b\u00fdt", "AUX", [21, 24]], ["Cromley", "Cromley", "PROPN", [25, 32]], ["vym\u011bn\u011bn", "vym\u011bn\u011bn\u00fd", "ADJ", [33, 40]], ["za", "za", "ADP", [41, 43]], ["japonsk\u00e9", "japonsk\u00fd", "ADJ", [44, 52]], ["diplomaty", "diplomat", "NOUN", [53, 62]], [",", ",", "PUNCT", [62, 63]], ["kte\u0159\u00ed", "kter\u00fd", "DET", [64, 69]], ["byli", "b\u00fdt", "AUX", [70, 74]], ["dr\u017eeni", "dr\u017een\u00fd", "ADJ", [75, 81]], ["ve", "v", "ADP", [82, 84]], ["Washingtonu", "Washington", "PROPN", [85, 96]], [".", ".", "PUNCT", [96, 97]]]], ["calgarske-listy_2003_unor_ocr.txt", "Vr\u00e1til se do USA na \u0161v\u00e9dsk\u00e9 lodi Gripsholm s dvoulet\u00fdm synem Donaldem.", [["Vr\u00e1til", "vr\u00e1tit", "VERB", [0, 6]], ["se", "se", "PRON", [7, 9]], ["do", "do", "ADP", [10, 12]], ["USA", "USA", "PROPN", [13, 16]], ["na", "na", "ADP", [17, 19]], ["\u0161v\u00e9dsk\u00e9", "\u0161v\u00e9dsk\u00fd", "ADJ", [20, 27]], ["lodi", "lo\u010f", "NOUN", [28, 32]], ["Gripsholm", "Gripsholm", "PROPN", [33, 42]], ["s", "s", "ADP", [43, 44]], ["dvoulet\u00fdm", "dvoulet\u00fd", "ADJ", [45, 54]], ["synem", "syn", "NOUN", [55, 60]], ["Donaldem", "Donald", "PROPN", [61, 69]], [".", ".", "PUNCT", [69, 70]]]], ["calgarske-listy_2003_unor_ocr.txt", "Man\u017eelka musela z\u016fstat v Japonsku, proto\u017ee Japonsko m\u011blo m\u00e1lo l\u00e9ka\u0159\u016f a prost\u011b ji nepustili.", [["Man\u017eelka", "man\u017eelka", "NOUN", [0, 8]], ["musela", "muset", "VERB", [9, 15]], ["z\u016fstat", "z\u016fstat", "VERB", [16, 22]], ["v", "v", "ADP", [23, 24]], ["Japonsku", "Japonsko", "PROPN", [25, 33]], [",", ",", "PUNCT", [33, 34]], ["proto\u017ee", "proto\u017ee", "SCONJ", [35, 42]], ["Japonsko", "Japonsko", "PROPN", [43, 51]], ["m\u011blo", "m\u00edt", "VERB", [52, 56]], ["m\u00e1lo", "m\u00e1lo", "DET", [57, 61]], ["l\u00e9ka\u0159\u016f", "l\u00e9ka\u0159", "NOUN", [62, 68]], ["a", "a", "CCONJ", [69, 70]], ["prost\u011b", "prost\u011b", "ADV", [71, 77]], ["ji", "on", "PRON", [78, 80]], ["nepustili", "pustit", "VERB", [81, 90]], [".", ".", "PUNCT", [90, 91]]]], ["calgarske-listy_2003_unor_ocr.txt", "Doma v Americe se Raymondovi rodi\u010de za\u010dali starat o mal\u00e9ho Donalda a pan Cromley vstoupil do arm\u00e1dy a proto\u017ee um\u011bl japonsky a \u010d\u00ednsky byl v arm\u00e1d\u011b p\u0159id\u011blen k vojensk\u00e9mu zpravodajstv\u00ed a v \u010dervenci 1944 byl s ostatn\u00edmi vysl\u00e1n na super tajnou akci \"Dixie Mission\" do \u010c\u00edny za Mao Tse-tungem.", [["Doma", "doma", "ADV", [0, 4]], ["v", "v", "ADP", [5, 6]], ["Americe", "Amerika", "PROPN", [7, 14]], ["se", "se", "PRON", [15, 17]], ["Raymondovi", "Raymond", "PROPN", [18, 28]], ["rodi\u010de", "rodi\u010d", "NOUN", [29, 35]], ["za\u010dali", "za\u010d\u00edt", "VERB", [36, 42]], ["starat", "starat", "VERB", [43, 49]], ["o", "o", "ADP", [50, 51]], ["mal\u00e9ho", "mal\u00fd", "ADJ", [52, 58]], ["Donalda", "Donald", "PROPN", [59, 66]], ["a", "a", "CCONJ", [67, 68]], ["pan", "pan", "NOUN", [69, 72]], ["Cromley", "Cromley", "PROPN", [73, 80]], ["vstoupil", "vstoupit", "VERB", [81, 89]], ["do", "do", "ADP", [90, 92]], ["arm\u00e1dy", "arm\u00e1da", "NOUN", [93, 99]], ["a", "a", "CCONJ", [100, 101]], ["proto\u017ee", "proto\u017ee", "SCONJ", [102, 109]], ["um\u011bl", "um\u011bt", "VERB", [110, 114]], ["japonsky", "japonsky", "ADV", [115, 123]], ["a", "a", "CCONJ", [124, 125]], ["\u010d\u00ednsky", "\u010d\u00ednsky", "ADV", [126, 132]], ["byl", "b\u00fdt", "AUX", [133, 136]], ["v", "v", "ADP", [137, 138]], ["arm\u00e1d\u011b", "arm\u00e1da", "NOUN", [139, 145]], ["p\u0159id\u011blen", "p\u0159id\u011blen\u00fd", "ADJ", [146, 154]], ["k", "k", "ADP", [155, 156]], ["vojensk\u00e9mu", "vojensk\u00fd", "ADJ", [157, 167]], ["zpravodajstv\u00ed", "zpravodajstv\u00ed", "NOUN", [168, 181]], ["a", "a", "CCONJ", [182, 183]], ["v", "v", "ADP", [184, 185]], ["\u010dervenci", "\u010dervenec", "NOUN", [186, 194]], ["1944", "1944", "NUM", [195, 199]], ["byl", "b\u00fdt", "AUX", [200, 203]], ["s", "s", "ADP", [204, 205]], ["ostatn\u00edmi", "ostatn\u00ed", "ADJ", [206, 215]], ["vysl\u00e1n", "vyslan\u00fd", "ADJ", [216, 222]], ["na", "na", "ADP", [223, 225]], ["super", "super", "NOUN", [226, 231]], ["tajnou", "tajn\u00fd", "ADJ", [232, 238]], ["akci", "akce", "NOUN", [239, 243]], ["\"", "\"", "PUNCT", [244, 245]], ["Dixie", "Dixie", "X", [245, 250]], ["Mission", "Mission", "X", [251, 258]], ["\"", "\"", "PUNCT", [258, 259]], ["do", "do", "ADP", [260, 262]], ["\u010c\u00edny", "\u010c\u00edna", "PROPN", [263, 267]], ["za", "za", "ADP", [268, 270]], ["Mao", "Mao", "X", [271, 274]], ["Tse", "tse", "NOUN", [275, 278]], ["-", "-", "PUNCT", [278, 279]], ["tungem", "tung", "NOUN", [279, 285]], [".", ".", "PUNCT", [285, 286]]]], ["calgarske-listy_2003_unor_ocr.txt", "V t\u00e9 dob\u011b nebyl", [["V", "v", "ADP", [0, 1]], ["t\u00e9", "ten", "DET", [2, 4]], ["dob\u011b", "doba", "NOUN", [5, 9]], ["nebyl", "b\u00fdt", "AUX", [10, 15]]]], ["calgarske-listy_2003_unor_ocr.txt", "Mao nic v\u00edc ne\u017e charismatick\u00fd mlad\u00fd v\u016fdce \u010d\u00ednsk\u00e9 Komunistick\u00e9 strany, bojuj\u00edc\u00ed s nacionalistickou vl\u00e1dou gener\u00e1la Chiang Kai-sheka, a byl s celou jeho 12  arm\u00e1dou schovan\u00fd v jeskyn\u00edch bl\u00edzko m\u011bsta Yenan.", [["Mao", "Mao", "PROPN", [0, 3]], ["nic", "nic", "PRON", [4, 7]], ["v\u00edc", "v\u00edce", "ADV", [8, 11]], ["ne\u017e", "ne\u017e", "SCONJ", [12, 15]], ["charismatick\u00fd", "charismatick\u00fd", "ADJ", [16, 29]], ["mlad\u00fd", "mlad\u00fd", "ADJ", [30, 35]], ["v\u016fdce", "v\u016fdce", "NOUN", [36, 41]], ["\u010d\u00ednsk\u00e9", "\u010d\u00ednsk\u00fd", "ADJ", [42, 48]], ["Komunistick\u00e9", "komunistick\u00fd", "ADJ", [49, 61]], ["strany", "strana", "NOUN", [62, 68]], [",", ",", "PUNCT", [68, 69]], ["bojuj\u00edc\u00ed", "bojuj\u00edc\u00ed", "ADJ", [70, 78]], ["s", "s", "ADP", [79, 80]], ["nacionalistickou", "nacionalistick\u00fd", "ADJ", [81, 97]], ["vl\u00e1dou", "vl\u00e1da", "NOUN", [98, 104]], ["gener\u00e1la", "gener\u00e1l", "NOUN", [105, 113]], ["Chiang", "Chiang", "PROPN", [114, 120]], ["Kai", "Kai", "PROPN", [121, 124]], ["-", "-", "PUNCT", [124, 125]], ["sheka", "sheka", "PROPN", [125, 130]], [",", ",", "PUNCT", [130, 131]], ["a", "a", "CCONJ", [132, 133]], ["byl", "b\u00fdt", "AUX", [134, 137]], ["s", "s", "ADP", [138, 139]], ["celou", "cel\u00fd", "ADJ", [140, 145]], ["jeho", "jeho", "DET", [146, 150]], ["12", "12", "NUM", [151, 153]], ["arm\u00e1dou", "arm\u00e1da", "NOUN", [155, 162]], ["schovan\u00fd", "schovan\u00fd", "ADJ", [163, 171]], ["v", "v", "ADP", [172, 173]], ["jeskyn\u00edch", "jeskyn\u011b", "NOUN", [174, 183]], ["bl\u00edzko", "bl\u00edzko", "ADV", [184, 190]], ["m\u011bsta", "m\u011bsto", "NOUN", [191, 196]], ["Yenan", "Yenan", "PROPN", [197, 202]], [".", ".", "PUNCT", [202, 203]]]], ["calgarske-listy_2003_unor_ocr.txt", "To bylo je\u0161t\u011b p\u00e1r let p\u0159edt\u00edm, ne\u017e uchv\u00e1til kontrolu nad celou \u010c\u00ednou.", [["To", "ten", "DET", [0, 2]], ["bylo", "b\u00fdt", "AUX", [3, 7]], ["je\u0161t\u011b", "je\u0161t\u011b", "ADV", [8, 13]], ["p\u00e1r", "p\u00e1r", "DET", [14, 17]], ["let", "l\u00e9ta", "NOUN", [18, 21]], ["p\u0159edt\u00edm", "p\u0159edt\u00edm", "ADV", [22, 29]], [",", ",", "PUNCT", [29, 30]], ["ne\u017e", "ne\u017e", "SCONJ", [31, 34]], ["uchv\u00e1til", "uchv\u00e1tit", "VERB", [35, 43]], ["kontrolu", "kontrola", "NOUN", [44, 52]], ["nad", "nad", "ADP", [53, 56]], ["celou", "cel\u00fd", "ADJ", [57, 62]], ["\u010c\u00ednou", "\u010c\u00edna", "PROPN", [63, 68]], [".", ".", "PUNCT", [68, 69]]]], ["calgarske-listy_2003_unor_ocr.txt", "President Roosevelt, demokrat do morku kosti, si bl\u00e1hov\u00e9 myslel, \u017ee p\u0159esv\u011bd\u010d\u00ed nacionalisty a komunisty, aby vytvo\u0159ili koali\u010dn\u00ed vl\u00e1du a tak \u017ee on, FDR, zabr\u00e1n\u00ed ob\u010dansk\u00e9 v\u00e1lce v \u010c\u00edn\u011b.", [["President", "President", "PROPN", [0, 9]], ["Roosevelt", "Roosevelt", "PROPN", [10, 19]], [",", ",", "PUNCT", [19, 20]], ["demokrat", "demokrat", "NOUN", [21, 29]], ["do", "do", "ADP", [30, 32]], ["morku", "morek", "NOUN", [33, 38]], ["kosti", "kost", "NOUN", [39, 44]], [",", ",", "PUNCT", [44, 45]], ["si", "se", "PRON", [46, 48]], ["bl\u00e1hov\u00e9", "bl\u00e1hov\u00fd", "ADJ", [49, 56]], ["myslel", "myslit", "VERB", [57, 63]], [",", ",", "PUNCT", [63, 64]], ["\u017ee", "\u017ee", "SCONJ", [65, 67]], ["p\u0159esv\u011bd\u010d\u00ed", "p\u0159esv\u011bd\u010dit", "VERB", [68, 77]], ["nacionalisty", "nacionalista", "NOUN", [78, 90]], ["a", "a", "CCONJ", [91, 92]], ["komunisty", "komunista", "NOUN", [93, 102]], [",", ",", "PUNCT", [102, 103]], ["aby", "aby", "SCONJ", [-2910, -2910]], ["by", "b\u00fdt", "AUX", [-2910, -2910]], ["vytvo\u0159ili", "vytvo\u0159it", "VERB", [108, 117]], ["koali\u010dn\u00ed", "koali\u010dn\u00ed", "ADJ", [118, 126]], ["vl\u00e1du", "vl\u00e1da", "NOUN", [127, 132]], ["a", "a", "CCONJ", [133, 134]], ["tak", "tak", "ADV", [135, 138]], ["\u017ee", "\u017ee", "SCONJ", [139, 141]], ["on", "on", "PRON", [142, 144]], [",", ",", "PUNCT", [144, 145]], ["FDR", "FDR", "NOUN", [146, 149]], [",", ",", "PUNCT", [149, 150]], ["zabr\u00e1n\u00ed", "zabr\u00e1nit", "VERB", [151, 158]], ["ob\u010dansk\u00e9", "ob\u010dansk\u00fd", "ADJ", [159, 167]], ["v\u00e1lce", "v\u00e1lka", "NOUN", [168, 173]], ["v", "v", "ADP", [174, 175]], ["\u010c\u00edn\u011b", "\u010c\u00edna", "PROPN", [176, 180]], [".", ".", "PUNCT", [180, 181]]]], ["calgarske-listy_2003_unor_ocr.txt", "A tak kdy\u017e Mao bydlel v jeskyni, tak se stalo, \u017ee Raymond Cromley bydlel v jeskyni taky.", [["A", "a", "CCONJ", [0, 1]], ["tak", "tak", "ADV", [2, 5]], ["kdy\u017e", "kdy\u017e", "SCONJ", [6, 10]], ["Mao", "Mao", "PROPN", [11, 14]], ["bydlel", "bydlet", "VERB", [15, 21]], ["v", "v", "ADP", [22, 23]], ["jeskyni", "jeskyn\u011b", "NOUN", [24, 31]], [",", ",", "PUNCT", [31, 32]], ["tak", "tak", "ADV", [33, 36]], ["se", "se", "PRON", [37, 39]], ["stalo", "st\u00e1t", "VERB", [40, 45]], [",", ",", "PUNCT", [45, 46]], ["\u017ee", "\u017ee", "SCONJ", [47, 49]], ["Raymond", "Raymond", "PROPN", [50, 57]], ["Cromley", "Cromley", "PROPN", [58, 65]], ["bydlel", "bydlet", "VERB", [66, 72]], ["v", "v", "ADP", [73, 74]], ["jeskyni", "jeskyn\u011b", "NOUN", [75, 82]], ["taky", "taky", "ADV", [83, 87]], [".", ".", "PUNCT", [87, 88]]]], ["calgarske-listy_2003_unor_ocr.txt", "N\u011bco p\u0159es \u0161est m\u011bs\u00edc\u016f.", [["N\u011bco", "n\u011bco", "PRON", [0, 4]], ["p\u0159es", "p\u0159es", "ADP", [5, 9]], ["\u0161est", "\u0161est", "NUM", [10, 14]], ["m\u011bs\u00edc\u016f", "m\u011bs\u00edc", "NOUN", [15, 21]], [".", ".", "PUNCT", [21, 22]]]], ["calgarske-listy_2003_unor_ocr.txt", "Maova jeskyn\u011b byla hned vedle.", [["Maova", "Maova", "PROPN", [0, 5]], ["jeskyn\u011b", "jeskyn\u011b", "NOUN", [6, 13]], ["byla", "b\u00fdt", "AUX", [14, 18]], ["hned", "hned", "ADV", [19, 23]], ["vedle", "vedle", "ADP", [24, 29]], [".", ".", "PUNCT", [29, 30]]]], ["calgarske-listy_2003_unor_ocr.txt", "Postupem \u010dasu byl schopen se s Maem i \u010d\u00e1ste\u010dn\u011b sp\u0159\u00e1telit a dokonce tan\u010dil i s jeho \u017eenou Jiang Qing na oslav\u011b \u010d\u00ednsk\u00e9ho Nov\u00e9ho roku.", [["Postupem", "postup", "NOUN", [0, 8]], ["\u010dasu", "\u010das", "NOUN", [9, 13]], ["byl", "b\u00fdt", "AUX", [14, 17]], ["schopen", "schopn\u00fd", "ADJ", [18, 25]], ["se", "se", "PRON", [26, 28]], ["s", "s", "ADP", [29, 30]], ["Maem", "Ma", "PROPN", [31, 35]], ["i", "i", "CCONJ", [36, 37]], ["\u010d\u00e1ste\u010dn\u011b", "\u010d\u00e1ste\u010dn\u011b", "ADV", [38, 46]], ["sp\u0159\u00e1telit", "sp\u0159\u00e1telit", "VERB", [47, 56]], ["a", "a", "CCONJ", [57, 58]], ["dokonce", "dokonce", "ADV", [59, 66]], ["tan\u010dil", "tan\u010dit", "VERB", [67, 73]], ["i", "i", "CCONJ", [74, 75]], ["s", "s", "ADP", [76, 77]], ["jeho", "jeho", "DET", [78, 82]], ["\u017eenou", "\u017eena", "NOUN", [83, 88]], ["Jiang", "Jiang", "PROPN", [89, 94]], ["Qing", "Qing", "PROPN", [95, 99]], ["na", "na", "ADP", [100, 102]], ["oslav\u011b", "oslava", "NOUN", [103, 109]], ["\u010d\u00ednsk\u00e9ho", "\u010d\u00ednsk\u00fd", "ADJ", [110, 118]], ["Nov\u00e9ho", "nov\u00fd", "ADJ", [119, 125]], ["roku", "rok", "NOUN", [126, 130]], [".", ".", "PUNCT", [130, 131]]]], ["calgarske-listy_2003_unor_ocr.txt", "Kdy\u017e se v\u00e1lka ch\u00fdlila ke konci, Mao po\u017e\u00e1dal Raymonda Cromleyho, aby poslal vzkaz presidentu Rooseveltovi o tom, \u017ee Mao je ochoten p\u0159ijet do Washingtonu k jedn\u00e1n\u00ed, pokud bude p\u0159ijat jako hlavn\u00ed \u010d\u00ednsk\u00fd p\u0159edstavitel.", [["Kdy\u017e", "kdy\u017e", "SCONJ", [0, 4]], ["se", "se", "PRON", [5, 7]], ["v\u00e1lka", "v\u00e1lka", "NOUN", [8, 13]], ["ch\u00fdlila", "ch\u00fdlit", "VERB", [14, 21]], ["ke", "k", "ADP", [22, 24]], ["konci", "konec", "NOUN", [25, 30]], [",", ",", "PUNCT", [30, 31]], ["Mao", "Mao", "PROPN", [32, 35]], ["po\u017e\u00e1dal", "po\u017e\u00e1dat", "VERB", [36, 43]], ["Raymonda", "Raymond", "PROPN", [44, 52]], ["Cromleyho", "Cromley", "PROPN", [53, 62]], [",", ",", "PUNCT", [62, 63]], ["aby", "aby", "SCONJ", [-3367, -3367]], ["by", "b\u00fdt", "AUX", [-3367, -3367]], ["poslal", "poslat", "VERB", [68, 74]], ["vzkaz", "vzkaz", "NOUN", [75, 80]], ["presidentu", "president", "NOUN", [81, 91]], ["Rooseveltovi", "Roosevelt", "PROPN", [92, 104]], ["o", "o", "ADP", [105, 106]], ["tom", "ten", "DET", [107, 110]], [",", ",", "PUNCT", [110, 111]], ["\u017ee", "\u017ee", "SCONJ", [112, 114]], ["Mao", "Mao", "PROPN", [115, 118]], ["je", "b\u00fdt", "AUX", [119, 121]], ["ochoten", "ochotn\u00fd", "ADJ", [122, 129]], ["p\u0159ijet", "p\u0159ijet", "VERB", [130, 136]], ["do", "do", "ADP", [137, 139]], ["Washingtonu", "Washington", "PROPN", [140, 151]], ["k", "k", "ADP", [152, 153]], ["jedn\u00e1n\u00ed", "jedn\u00e1n\u00ed", "NOUN", [154, 161]], [",", ",", "PUNCT", [161, 162]], ["pokud", "pokud", "SCONJ", [163, 168]], ["bude", "b\u00fdt", "AUX", [169, 173]], ["p\u0159ijat", "p\u0159ijat\u00fd", "ADJ", [174, 180]], ["jako", "jako", "SCONJ", [181, 185]], ["hlavn\u00ed", "hlavn\u00ed", "ADJ", [186, 192]], ["\u010d\u00ednsk\u00fd", "\u010d\u00ednsk\u00fd", "ADJ", [193, 199]], ["p\u0159edstavitel", "p\u0159edstavitel", "NOUN", [200, 212]], [".", ".", "PUNCT", [212, 213]]]], ["calgarske-listy_2003_unor_ocr.txt", "Tento kabelov\u00fd vzkaz byl ale zachycen v Chunkingu tehdej\u0161\u00edm americk\u00fdm velvyslancem v \u010c\u00edn\u011b Patrickem Hurleym, kter\u00fd byl proti takov\u00e9mu st\u0159etnut\u00ed.", [["Tento", "tento", "DET", [0, 5]], ["kabelov\u00fd", "kabelov\u00fd", "ADJ", [6, 14]], ["vzkaz", "vzkaz", "NOUN", [15, 20]], ["byl", "b\u00fdt", "AUX", [21, 24]], ["ale", "ale", "CCONJ", [25, 28]], ["zachycen", "zachycen\u00fd", "ADJ", [29, 37]], ["v", "v", "ADP", [38, 39]], ["Chunkingu", "Chunking", "PROPN", [40, 49]], ["tehdej\u0161\u00edm", "tehdej\u0161\u00ed", "ADJ", [50, 59]], ["americk\u00fdm", "americk\u00fd", "ADJ", [60, 69]], ["velvyslancem", "velvyslanec", "NOUN", [70, 82]], ["v", "v", "ADP", [83, 84]], ["\u010c\u00edn\u011b", "\u010c\u00edna", "PROPN", [85, 89]], ["Patrickem", "Patrick", "PROPN", [90, 99]], ["Hurleym", "Hurleym", "PROPN", [100, 107]], [",", ",", "PUNCT", [107, 108]], ["kter\u00fd", "kter\u00fd", "DET", [109, 114]], ["byl", "b\u00fdt", "AUX", [115, 118]], ["proti", "proti", "ADP", [119, 124]], ["takov\u00e9mu", "takov\u00fd", "DET", [125, 133]], ["st\u0159etnut\u00ed", "st\u0159etnut\u00ed", "NOUN", [134, 143]], [".", ".", "PUNCT", [143, 144]]]], ["calgarske-listy_2003_unor_ocr.txt", "Vzkaz Rooseveltovi jednodu\u0161e zadr\u017eel a nedal doru\u010dit.", [["Vzkaz", "vzkaz", "NOUN", [0, 5]], ["Rooseveltovi", "Roosevelt", "PROPN", [6, 18]], ["jednodu\u0161e", "jednodu\u0161e", "ADV", [19, 28]], ["zadr\u017eel", "zadr\u017eet", "VERB", [29, 36]], ["a", "a", "CCONJ", [37, 38]], ["nedal", "d\u00e1t", "VERB", [39, 44]], ["doru\u010dit", "doru\u010dit", "VERB", [45, 52]], [".", ".", "PUNCT", [52, 53]]]], ["calgarske-listy_2003_unor_ocr.txt", "\"Nedoru\u010den\u00fd telegram byl jednou z nejv\u011bt\u0161\u00edch ironi\u00ed t\u00e9 doby,\" napsala histori\u010dka Barbara Tuchman v roce 1972 v eseji Foreign Affairs nazvan\u00e9 \"If Mao had Come to Washington\".", [["\"", "\"", "PUNCT", [0, 1]], ["Nedoru\u010den\u00fd", "doru\u010den\u00fd", "ADJ", [1, 11]], ["telegram", "telegram", "NOUN", [12, 20]], ["byl", "b\u00fdt", "AUX", [21, 24]], ["jednou", "jeden", "NUM", [25, 31]], ["z", "z", "ADP", [32, 33]], ["nejv\u011bt\u0161\u00edch", "velk\u00fd", "ADJ", [34, 44]], ["ironi\u00ed", "ironie", "NOUN", [45, 51]], ["t\u00e9", "ten", "DET", [52, 54]], ["doby", "doba", "NOUN", [55, 59]], [",", ",", "PUNCT", [59, 60]], ["\"", "\"", "PUNCT", [60, 61]], ["napsala", "napsat", "VERB", [62, 69]], ["histori\u010dka", "histori\u010dka", "NOUN", [70, 80]], ["Barbara", "Barbara", "PROPN", [81, 88]], ["Tuchman", "Tuchman", "PROPN", [89, 96]], ["v", "v", "ADP", [97, 98]], ["roce", "rok", "NOUN", [99, 103]], ["1972", "1972", "NUM", [104, 108]], ["v", "v", "ADP", [109, 110]], ["eseji", "esej", "NOUN", [111, 116]], ["Foreign", "Foreign", "X", [117, 124]], ["Affairs", "Affairs", "X", [125, 132]], ["nazvan\u00e9", "nazvan\u00fd", "ADJ", [133, 140]], ["\"", "\"", "PUNCT", [141, 142]], ["If", "If", "NOUN", [142, 144]], ["Mao", "Mao", "X", [145, 148]], ["had", "had", "X", [149, 152]], ["Come", "Come", "X", [153, 157]], ["to", "to", "X", [158, 160]], ["Washington", "Washington", "PROPN", [161, 171]], ["\"", "\"", "PUNCT", [171, 172]], [".", ".", "PUNCT", [172, 173]]]], ["calgarske-listy_2003_unor_ocr.txt", "(Kdyby Mao p\u0159ijel do Washingtonu).", [["(", "(", "PUNCT", [0, 1]], ["Kdy\u017e", "kdy\u017e", "SCONJ", [-3954, -3954]], ["by", "b\u00fdt", "AUX", [-3954, -3954]], ["Mao", "Mao", "PROPN", [7, 10]], ["p\u0159ijel", "p\u0159ijet", "VERB", [11, 17]], ["do", "do", "ADP", [18, 20]], ["Washingtonu", "Washington", "PROPN", [21, 32]], [")", ")", "PUNCT", [32, 33]], [".", ".", "PUNCT", [33, 34]]]], ["calgarske-listy_2003_unor_ocr.txt", "Barbara Tuchman se d\u00e1le domn\u00edv\u00e1, \u017ee pokud by Mao tehdy p\u0159ijel do D.C., mo\u017en\u00e1 by U.S. nepodporovaly tak siln\u011b nacionalistickou vl\u00e1du a Mao by se nestal tak proti-americk\u00fdm (obzvl\u00e1\u0161t\u011b kdy\u017e proti sov\u011btsk\u00fdm komunist\u016fm m\u011bl taky v\u00fdhrady) a mo\u017en\u00e1 by ani nedo\u0161lo ke korejsk\u00e9 v\u00e1lce.", [["Barbara", "Barbara", "PROPN", [0, 7]], ["Tuchman", "Tuchman", "PROPN", [8, 15]], ["se", "se", "PRON", [16, 18]], ["d\u00e1le", "d\u00e1le", "ADV", [19, 23]], ["domn\u00edv\u00e1", "domn\u00edvat", "VERB", [24, 31]], [",", ",", "PUNCT", [31, 32]], ["\u017ee", "\u017ee", "SCONJ", [33, 35]], ["pokud", "pokud", "SCONJ", [36, 41]], ["by", "b\u00fdt", "AUX", [42, 44]], ["Mao", "Mao", "PROPN", [45, 48]], ["tehdy", "tehdy", "ADV", [49, 54]], ["p\u0159ijel", "p\u0159ijet", "VERB", [55, 61]], ["do", "do", "ADP", [62, 64]], ["D", "D", "NOUN", [65, 66]], [".", ".", "PUNCT", [66, 67]], ["C", "C", "NOUN", [67, 68]], [".", ".", "PUNCT", [68, 69]], [",", ",", "PUNCT", [69, 70]], ["mo\u017en\u00e1", "mo\u017en\u00e1", "ADV", [71, 76]], ["by", "b\u00fdt", "AUX", [77, 79]], ["U", "U", "NOUN", [80, 81]], [".", ".", "PUNCT", [81, 82]], ["S", "S", "NOUN", [82, 83]], [".", ".", "PUNCT", [83, 84]], ["nepodporovaly", "podporovat", "VERB", [85, 98]], ["tak", "tak", "ADV", [99, 102]], ["siln\u011b", "siln\u011b", "ADV", [103, 108]], ["nacionalistickou", "nacionalistick\u00fd", "ADJ", [109, 125]], ["vl\u00e1du", "vl\u00e1da", "NOUN", [126, 131]], ["a", "a", "CCONJ", [132, 133]], ["Mao", "Mao", "PROPN", [134, 137]], ["by", "b\u00fdt", "AUX", [138, 140]], ["se", "se", "PRON", [141, 143]], ["nestal", "st\u00e1t", "VERB", [144, 150]], ["tak", "tak", "ADV", [151, 154]], ["proti", "proti", "ADP", [155, 160]], ["-", "-", "PUNCT", [160, 161]], ["americk\u00fdm", "americk\u00fd", "ADJ", [161, 170]], ["(", "(", "PUNCT", [171, 172]], ["obzvl\u00e1\u0161t\u011b", "obzvl\u00e1\u0161t\u011b", "ADV", [172, 181]], ["kdy\u017e", "kdy\u017e", "SCONJ", [182, 186]], ["proti", "proti", "ADP", [187, 192]], ["sov\u011btsk\u00fdm", "sov\u011btsk\u00fd", "ADJ", [193, 202]], ["komunist\u016fm", "komunista", "NOUN", [203, 213]], ["m\u011bl", "m\u00edt", "VERB", [214, 217]], ["taky", "taky", "ADV", [218, 222]], ["v\u00fdhrady", "v\u00fdhrada", "NOUN", [223, 230]], [")", ")", "PUNCT", [230, 231]], ["a", "a", "CCONJ", [232, 233]], ["mo\u017en\u00e1", "mo\u017en\u00e1", "ADV", [234, 239]], ["by", "b\u00fdt", "AUX", [240, 242]], ["ani", "ani", "CCONJ", [243, 246]], ["nedo\u0161lo", "doj\u00edt", "VERB", [247, 254]], ["ke", "k", "ADP", [255, 257]], ["korejsk\u00e9", "korejsk\u00fd", "ADJ", [258, 266]], ["v\u00e1lce", "v\u00e1lka", "NOUN", [267, 272]], [".", ".", "PUNCT", [272, 273]]]], ["calgarske-listy_2003_unor_ocr.txt", "A mo\u017en\u00e1 ani k vietnamsk\u00e9 v\u00e1lce ne.", [["A", "a", "CCONJ", [0, 1]], ["mo\u017en\u00e1", "mo\u017en\u00e1", "ADV", [2, 7]], ["ani", "ani", "CCONJ", [8, 11]], ["k", "k", "ADP", [12, 13]], ["vietnamsk\u00e9", "vietnamsk\u00fd", "ADJ", [14, 24]], ["v\u00e1lce", "v\u00e1lka", "NOUN", [25, 30]], ["ne", "ne", "PART", [31, 33]], [".", ".", "PUNCT", [33, 34]]]], ["calgarske-listy_2003_unor_ocr.txt", "Tak je to aspo\u0148 v jej\u00edm \u010dl\u00e1nku.", [["Tak", "tak", "ADV", [0, 3]], ["je", "b\u00fdt", "AUX", [4, 6]], ["to", "ten", "DET", [7, 9]], ["aspo\u0148", "aspo\u0148", "ADV", [10, 15]], ["v", "v", "ADP", [16, 17]], ["jej\u00edm", "jeho", "DET", [18, 23]], ["\u010dl\u00e1nku", "\u010dl\u00e1nek", "NOUN", [24, 30]], [".", ".", "PUNCT", [30, 31]]]], ["calgarske-listy_2003_unor_ocr.txt", "Kdy\u017e v\u00e1lka skon\u010dila, tak se Raymond Cromley vypravil do Japonska p\u00e1trat po jeho \u017een\u011b.", [["Kdy\u017e", "kdy\u017e", "SCONJ", [0, 4]], ["v\u00e1lka", "v\u00e1lka", "NOUN", [5, 10]], ["skon\u010dila", "skon\u010dit", "VERB", [11, 19]], [",", ",", "PUNCT", [19, 20]], ["tak", "tak", "ADV", [21, 24]], ["se", "se", "PRON", [25, 27]], ["Raymond", "Raymond", "PROPN", [28, 35]], ["Cromley", "Cromley", "PROPN", [36, 43]], ["vypravil", "vypravit", "VERB", [44, 52]], ["do", "do", "ADP", [53, 55]], ["Japonska", "Japonsko", "PROPN", [56, 64]], ["p\u00e1trat", "p\u00e1trat", "VERB", [65, 71]], ["po", "po", "ADP", [72, 74]], ["jeho", "jeho", "DET", [75, 79]], ["\u017een\u011b", "\u017eena", "NOUN", [80, 84]], [".", ".", "PUNCT", [84, 85]]]], ["calgarske-listy_2003_unor_ocr.txt", "Na\u0161el ji v Tokyu, um\u00edraj\u00edc\u00ed na tuberkul\u00f3zu.", [["Na\u0161el", "naj\u00edt", "VERB", [0, 5]], ["ji", "on", "PRON", [6, 8]], ["v", "v", "ADP", [9, 10]], ["Tokyu", "Tokyu", "PROPN", [11, 16]], [",", ",", "PUNCT", [16, 17]], ["um\u00edraj\u00edc\u00ed", "um\u00edraj\u00edc\u00ed", "ADJ", [18, 27]], ["na", "na", "ADP", [28, 30]], ["tuberkul\u00f3zu", "tuberkul\u00f3za", "NOUN", [31, 42]], [".", ".", "PUNCT", [42, 43]]]], ["calgarske-listy_2003_unor_ocr.txt", "Zem\u0159ela po n\u011bkolika m\u011bs\u00edc\u00edch a Cromley se vr\u00e1til do U.S.A, s\u00e1m.", [["Zem\u0159ela", "zem\u0159\u00edt", "VERB", [0, 7]], ["po", "po", "ADP", [8, 10]], ["n\u011bkolika", "n\u011bkolik", "DET", [11, 19]], ["m\u011bs\u00edc\u00edch", "m\u011bs\u00edc", "NOUN", [20, 28]], ["a", "a", "CCONJ", [29, 30]], ["Cromley", "Cromley", "PROPN", [31, 38]], ["se", "se", "PRON", [39, 41]], ["vr\u00e1til", "vr\u00e1tit", "VERB", [42, 48]], ["do", "do", "ADP", [49, 51]], ["U", "U", "NOUN", [52, 53]], [".", ".", "PUNCT", [53, 54]], ["S", "S", "NOUN", [54, 55]], [".", ".", "PUNCT", [55, 56]], ["A", "A", "NOUN", [56, 57]], [",", ",", "PUNCT", [57, 58]], ["s\u00e1m", "sam\u00fd", "DET", [59, 62]], [".", ".", "PUNCT", [62, 63]]]], ["calgarske-listy_2003_unor_ocr.txt", "Za\u010dal zase pracovat pro Wall Street Journal a psal \u010dl\u00e1nky na t\u00e9mata n\u00e1rodn\u00ed bezpe\u010dnosti.", [["Za\u010dal", "za\u010d\u00edt", "VERB", [0, 5]], ["zase", "zase", "ADV", [6, 10]], ["pracovat", "pracovat", "VERB", [11, 19]], ["pro", "pro", "ADP", [20, 23]], ["Wall", "Wall", "X", [24, 28]], ["Street", "Street", "X", [29, 35]], ["Journal", "Journal", "X", [36, 43]], ["a", "a", "CCONJ", [44, 45]], ["psal", "ps\u00e1t", "VERB", [46, 50]], ["\u010dl\u00e1nky", "\u010dl\u00e1nek", "NOUN", [51, 57]], ["na", "na", "ADP", [58, 60]], ["t\u00e9mata", "t\u00e9ma", "NOUN", [61, 67]], ["n\u00e1rodn\u00ed", "n\u00e1rodn\u00ed", "ADJ", [68, 75]], ["bezpe\u010dnosti", "bezpe\u010dnost", "NOUN", [76, 87]], [".", ".", "PUNCT", [87, 88]]]], ["calgarske-listy_2003_unor_ocr.txt", "Koncem pades\u00e1t\u00fdch se znovu o\u017eenil a m\u011bl \u010dty\u0159i dal\u0161\u00ed d\u011bti.", [["Koncem", "konec", "NOUN", [0, 6]], ["pades\u00e1t\u00fdch", "pades\u00e1t\u00fd", "ADJ", [7, 17]], ["se", "se", "PRON", [18, 20]], ["znovu", "znovu", "ADV", [21, 26]], ["o\u017eenil", "o\u017eenit", "VERB", [27, 33]], ["a", "a", "CCONJ", [34, 35]], ["m\u011bl", "m\u00edt", "VERB", [36, 39]], ["\u010dty\u0159i", "\u010dty\u0159i", "NUM", [40, 45]], ["dal\u0161\u00ed", "dal\u0161\u00ed", "ADJ", [46, 51]], ["d\u011bti", "d\u00edt\u011b", "NOUN", [52, 56]], [".", ".", "PUNCT", [56, 57]]]], ["calgarske-listy_2003_unor_ocr.txt", "V roce 1967 jeho nov\u00e1 man\u017eelka n\u00e1hle zem\u0159ela na toxick\u00fd \u0161ok, kdy\u017e jejich d\u011bti m\u011bly 2, 4, 7 a 9 let.", [["V", "v", "ADP", [0, 1]], ["roce", "rok", "NOUN", [2, 6]], ["1967", "1967", "NUM", [7, 11]], ["jeho", "jeho", "DET", [12, 16]], ["nov\u00e1", "nov\u00fd", "ADJ", [17, 21]], ["man\u017eelka", "man\u017eelka", "NOUN", [22, 30]], ["n\u00e1hle", "n\u00e1hle", "ADV", [31, 36]], ["zem\u0159ela", "zem\u0159\u00edt", "VERB", [37, 44]], ["na", "na", "ADP", [45, 47]], ["toxick\u00fd", "toxick\u00fd", "ADJ", [48, 55]], ["\u0161ok", "\u0161ok", "NOUN", [56, 59]], [",", ",", "PUNCT", [59, 60]], ["kdy\u017e", "kdy\u017e", "SCONJ", [61, 65]], ["jejich", "jeho", "DET", [66, 72]], ["d\u011bti", "d\u00edt\u011b", "NOUN", [73, 77]], ["m\u011bly", "m\u00edt", "VERB", [78, 82]], ["2", "2", "NUM", [83, 84]], [",", ",", "PUNCT", [84, 85]], ["4", "4", "NUM", [86, 87]], [",", ",", "PUNCT", [87, 88]], ["7", "7", "NUM", [89, 90]], ["a", "a", "CCONJ", [91, 92]], ["9", "9", "NUM", [93, 94]], ["let", "l\u00e9ta", "NOUN", [95, 98]], [".", ".", "PUNCT", [98, 99]]]], ["calgarske-listy_2003_unor_ocr.txt", "Pan Cromley pracoval d\u00e1l a \u010dasto si bral d\u011bti sebou do Pentagonu, kde bylo pro n\u011b hodn\u011b p\u0159\u00edle\u017eitosti b\u011bhat po chodb\u00e1ch a nebo jezdit v pono\u017ek\u00e1ch po nale\u0161t\u011bn\u00fdch linoleov\u00fdch podlah\u00e1ch a nebo i na r\u016fzn\u00e9 ud\u00e1losti, a\u0165 u\u017e z nutnosti a nebo prost\u011b \u017ee cht\u011bl, aby d\u011bti v\u011bd\u011bly, co se ve sv\u011bt\u011b d\u011bje.", [["Pan", "pan", "NOUN", [0, 3]], ["Cromley", "Cromley", "PROPN", [4, 11]], ["pracoval", "pracovat", "VERB", [12, 20]], ["d\u00e1l", "d\u00e1l", "ADV", [21, 24]], ["a", "a", "CCONJ", [25, 26]], ["\u010dasto", "\u010dasto", "ADV", [27, 32]], ["si", "se", "PRON", [33, 35]], ["bral", "br\u00e1t", "VERB", [36, 40]], ["d\u011bti", "d\u00edt\u011b", "NOUN", [41, 45]], ["sebou", "se", "PRON", [46, 51]], ["do", "do", "ADP", [52, 54]], ["Pentagonu", "Pentagon", "PROPN", [55, 64]], [",", ",", "PUNCT", [64, 65]], ["kde", "kde", "ADV", [66, 69]], ["bylo", "b\u00fdt", "AUX", [70, 74]], ["pro", "pro", "ADP", [75, 78]], ["n\u011b", "on", "PRON", [79, 81]], ["hodn\u011b", "hodn\u011b", "ADV", [82, 87]], ["p\u0159\u00edle\u017eitosti", "p\u0159\u00edle\u017eitost", "NOUN", [88, 100]], ["b\u011bhat", "b\u011bhat", "VERB", [101, 106]], ["po", "po", "ADP", [107, 109]], ["chodb\u00e1ch", "chodba", "NOUN", [110, 118]], ["a", "a", "CCONJ", [119, 120]], ["nebo", "nebo", "CCONJ", [121, 125]], ["jezdit", "jezdit", "VERB", [126, 132]], ["v", "v", "ADP", [133, 134]], ["pono\u017ek\u00e1ch", "pono\u017eka", "NOUN", [135, 144]], ["po", "po", "ADP", [145, 147]], ["nale\u0161t\u011bn\u00fdch", "nale\u0161t\u011bn\u00fd", "ADJ", [148, 159]], ["linoleov\u00fdch", "linoleov\u00fd", "ADJ", [160, 171]], ["podlah\u00e1ch", "podlaha", "NOUN", [172, 181]], ["a", "a", "CCONJ", [182, 183]], ["nebo", "nebo", "CCONJ", [184, 188]], ["i", "i", "CCONJ", [189, 190]], ["na", "na", "ADP", [191, 193]], ["r\u016fzn\u00e9", "r\u016fzn\u00fd", "ADJ", [194, 199]], ["ud\u00e1losti", "ud\u00e1lost", "NOUN", [200, 208]], [",", ",", "PUNCT", [208, 209]], ["a\u0165", "a\u0165", "SCONJ", [210, 212]], ["u\u017e", "u\u017e", "ADV", [213, 215]], ["z", "z", "ADP", [216, 217]], ["nutnosti", "nutnost", "NOUN", [218, 226]], ["a", "a", "CCONJ", [227, 228]], ["nebo", "nebo", "CCONJ", [229, 233]], ["prost\u011b", "prost\u011b", "ADV", [234, 240]], ["\u017ee", "\u017ee", "SCONJ", [241, 243]], ["cht\u011bl", "cht\u00edt", "VERB", [244, 249]], [",", ",", "PUNCT", [249, 250]], ["aby", "aby", "SCONJ", [-4771, -4771]], ["by", "b\u00fdt", "AUX", [-4771, -4771]], ["d\u011bti", "d\u00edt\u011b", "NOUN", [255, 259]], ["v\u011bd\u011bly", "v\u011bd\u011bt", "VERB", [260, 266]], [",", ",", "PUNCT", [266, 267]], ["co", "co", "PRON", [268, 270]], ["se", "se", "PRON", [271, 273]], ["ve", "v", "ADP", [274, 276]], ["sv\u011bt\u011b", "sv\u011bt", "NOUN", [277, 282]], ["d\u011bje", "d\u00edt", "VERB", [283, 287]], [".", ".", "PUNCT", [287, 288]]]], ["calgarske-listy_2003_unor_ocr.txt", "V roce 1975 Raymond Cromley vytvo\u0159il svou vlastn\u00ed firmu, Cromley News Service, s j\u00edm sam\u00fdm jako jedin\u00fdm zam\u011bstnancem.", [["V", "v", "ADP", [0, 1]], ["roce", "rok", "NOUN", [2, 6]], ["1975", "1975", "NUM", [7, 11]], ["Raymond", "Raymond", "PROPN", [12, 19]], ["Cromley", "Cromley", "PROPN", [20, 27]], ["vytvo\u0159il", "vytvo\u0159it", "VERB", [28, 36]], ["svou", "sv\u016fj", "DET", [37, 41]], ["vlastn\u00ed", "vlastn\u00ed", "ADJ", [42, 49]], ["firmu", "firma", "NOUN", [50, 55]], [",", ",", "PUNCT", [55, 56]], ["Cromley", "Cromley", "X", [57, 64]], ["News", "News", "X", [65, 69]], ["Service", "Service", "X", [70, 77]], [",", ",", "PUNCT", [77, 78]], ["s", "s", "ADP", [79, 80]], ["j\u00edm", "on", "PRON", [81, 84]], ["sam\u00fdm", "sam\u00fd", "NOUN", [85, 90]], ["jako", "jako", "SCONJ", [91, 95]], ["jedin\u00fdm", "jedin\u00fd", "ADJ", [96, 103]], ["zam\u011bstnancem", "zam\u011bstnanec", "NOUN", [104, 116]], [".", ".", "PUNCT", [116, 117]]]], ["calgarske-listy_2003_unor_ocr.txt", "Psal sv\u00e9 pravideln\u00e9 \u010dl\u00e1nky a sloupce, kter\u00e9 byly otiskov\u00e1ny ve zhruba Z m\u00e9ho \u017eivota.", [["Psal", "ps\u00e1t", "VERB", [0, 4]], ["sv\u00e9", "sv\u016fj", "DET", [5, 8]], ["pravideln\u00e9", "pravideln\u00fd", "ADJ", [9, 19]], ["\u010dl\u00e1nky", "\u010dl\u00e1nek", "NOUN", [20, 26]], ["a", "a", "CCONJ", [27, 28]], ["sloupce", "sloupec", "NOUN", [29, 36]], [",", ",", "PUNCT", [36, 37]], ["kter\u00e9", "kter\u00fd", "DET", [38, 43]], ["byly", "b\u00fdt", "AUX", [44, 48]], ["otiskov\u00e1ny", "otiskovan\u00fd", "ADJ", [49, 59]], ["ve", "v", "ADP", [60, 62]], ["zhruba", "zhruba", "ADV", [63, 69]], ["Z", "z", "ADP", [70, 71]], ["m\u00e9ho", "m\u016fj", "DET", [72, 76]], ["\u017eivota", "\u017eivot", "NOUN", [77, 83]], [".", ".", "PUNCT", [83, 84]]]], ["calgarske-listy_2003_unor_ocr.txt", "(Pokra\u010dov\u00e1n\u00ed z listopadov\u00e9ho \u010d\u00edsla)", [["(", "(", "PUNCT", [0, 1]], ["Pokra\u010dov\u00e1n\u00ed", "pokra\u010dov\u00e1n\u00ed", "NOUN", [1, 12]], ["z", "z", "ADP", [13, 14]], ["listopadov\u00e9ho", "listopadov\u00fd", "ADJ", [15, 28]], ["\u010d\u00edsla", "\u010d\u00edslo", "NOUN", [29, 34]], [")", ")", "PUNCT", [34, 35]]]], ["calgarske-listy_2003_unor_ocr.txt", "Dal\u0161\u00ed obl\u00edbenou \u010dinnost\u00ed v m\u00e9m ran\u00e9m ml\u00e1d\u00ed bylo sb\u00edr\u00e1n\u00ed lesn\u00edch hub b\u011bhem l\u00e9ta.", [["Dal\u0161\u00ed", "dal\u0161\u00ed", "ADJ", [0, 5]], ["obl\u00edbenou", "obl\u00edben\u00fd", "ADJ", [6, 15]], ["\u010dinnost\u00ed", "\u010dinnost", "NOUN", [16, 24]], ["v", "v", "ADP", [25, 26]], ["m\u00e9m", "m\u016fj", "DET", [27, 30]], ["ran\u00e9m", "ran\u00fd", "ADJ", [31, 36]], ["ml\u00e1d\u00ed", "ml\u00e1d\u00ed", "NOUN", [37, 42]], ["bylo", "b\u00fdt", "AUX", [43, 47]], ["sb\u00edr\u00e1n\u00ed", "sb\u00edr\u00e1n\u00ed", "NOUN", [48, 55]], ["lesn\u00edch", "lesn\u00ed", "ADJ", [56, 63]], ["hub", "houba", "NOUN", [64, 67]], ["b\u011bhem", "b\u011bhem", "ADP", [68, 73]], ["l\u00e9ta", "l\u00e9ta", "NOUN", [74, 78]], [".", ".", "PUNCT", [78, 79]]]], ["calgarske-listy_2003_unor_ocr.txt", "Babi\u010dka chod\u00edvala brzy po r\u00e1nu, ne\u017e bude moc horko a tak\u00e9 ne\u017e n\u00e1s n\u011bkdo dvou stovk\u00e1ch r\u016fzn\u00fdch novin a\u017e do poloviny devades\u00e1t\u00fdch let, kdy si tak ne\u0161\u0165astn\u011b zlomil nohu na led\u011b, \u017ee musel str\u00e1vit n\u011bkolik m\u011bs\u00edc\u016f doma.", [["Babi\u010dka", "babi\u010dka", "NOUN", [0, 7]], ["chod\u00edvala", "chod\u00edvat", "VERB", [8, 17]], ["brzy", "brzy", "ADV", [18, 22]], ["po", "po", "ADP", [23, 25]], ["r\u00e1nu", "r\u00e1na", "NOUN", [26, 30]], [",", ",", "PUNCT", [30, 31]], ["ne\u017e", "ne\u017e", "SCONJ", [32, 35]], ["bude", "b\u00fdt", "AUX", [36, 40]], ["moc", "moc", "ADV", [41, 44]], ["horko", "horko", "ADJ", [45, 50]], ["a", "a", "CCONJ", [51, 52]], ["tak\u00e9", "tak\u00e9", "ADV", [53, 57]], ["ne\u017e", "ne\u017e", "SCONJ", [58, 61]], ["n\u00e1s", "my", "PRON", [62, 65]], ["n\u011bkdo", "n\u011bkdo", "PRON", [66, 71]], ["dvou", "dva", "NUM", [72, 76]], ["stovk\u00e1ch", "stovka", "NOUN", [77, 85]], ["r\u016fzn\u00fdch", "r\u016fzn\u00fd", "ADJ", [86, 93]], ["novin", "noviny", "NOUN", [94, 99]], ["a\u017e", "a\u017e", "PART", [100, 102]], ["do", "do", "ADP", [103, 105]], ["poloviny", "polovina", "NOUN", [106, 114]], ["devades\u00e1t\u00fdch", "devades\u00e1t\u00fd", "ADJ", [115, 127]], ["let", "l\u00e9ta", "NOUN", [128, 131]], [",", ",", "PUNCT", [131, 132]], ["kdy", "kdy", "ADV", [133, 136]], ["si", "se", "PRON", [137, 139]], ["tak", "tak", "ADV", [140, 143]], ["ne\u0161\u0165astn\u011b", "\u0161\u0165astn\u011b", "ADV", [144, 153]], ["zlomil", "zlomit", "VERB", [154, 160]], ["nohu", "noha", "NOUN", [161, 165]], ["na", "na", "ADP", [166, 168]], ["led\u011b", "led", "NOUN", [169, 173]], [",", ",", "PUNCT", [173, 174]], ["\u017ee", "\u017ee", "SCONJ", [175, 177]], ["musel", "muset", "VERB", [178, 183]], ["str\u00e1vit", "str\u00e1vit", "VERB", [184, 191]], ["n\u011bkolik", "n\u011bkolik", "DET", [192, 199]], ["m\u011bs\u00edc\u016f", "m\u011bs\u00edc", "NOUN", [200, 206]], ["doma", "doma", "ADV", [207, 211]], [".", ".", "PUNCT", [211, 212]]]], ["calgarske-listy_2003_unor_ocr.txt", "Po n\u00e1vratu do pr\u00e1ce, kdy\u017e u\u017e si jeho obvykl\u00ed z\u00e1kazn\u00edci mezit\u00edm na\u0161li jin\u00e9 \"zdroje\", u\u017e ani vlastn\u011b ps\u00e1t neza\u010dal.", [["Po", "po", "ADP", [0, 2]], ["n\u00e1vratu", "n\u00e1vrat", "NOUN", [3, 10]], ["do", "do", "ADP", [11, 13]], ["pr\u00e1ce", "pr\u00e1ce", "NOUN", [14, 19]], [",", ",", "PUNCT", [19, 20]], ["kdy\u017e", "kdy\u017e", "SCONJ", [21, 25]], ["u\u017e", "u\u017e", "ADV", [26, 28]], ["si", "se", "PRON", [29, 31]], ["jeho", "jeho", "DET", [32, 36]], ["obvykl\u00ed", "obvykl\u00fd", "ADJ", [37, 44]], ["z\u00e1kazn\u00edci", "z\u00e1kazn\u00edk", "NOUN", [45, 54]], ["mezit\u00edm", "mezit\u00edm", "ADV", [55, 62]], ["na\u0161li", "naj\u00edt", "VERB", [63, 68]], ["jin\u00e9", "jin\u00fd", "ADJ", [69, 73]], ["\"", "\"", "PUNCT", [74, 75]], ["zdroje", "zdroj", "NOUN", [75, 81]], ["\"", "\"", "PUNCT", [81, 82]], [",", ",", "PUNCT", [82, 83]], ["u\u017e", "u\u017e", "ADV", [84, 86]], ["ani", "ani", "CCONJ", [87, 90]], ["vlastn\u011b", "vlastn\u011b", "ADV", [91, 98]], ["ps\u00e1t", "ps\u00e1t", "VERB", [99, 103]], ["neza\u010dal", "za\u010d\u00edt", "VERB", [104, 111]], [".", ".", "PUNCT", [111, 112]]]], ["calgarske-listy_2003_unor_ocr.txt", "Co\u017e ov\u0161em neznamen\u00e1, \u017ee by p\u0159estal chodit do sv\u00e9 kancel\u00e1\u0159e v Penatgonu.", [["Co\u017e", "co\u017e", "PRON", [0, 3]], ["ov\u0161em", "ov\u0161em", "PART", [4, 9]], ["neznamen\u00e1", "znamenat", "VERB", [10, 19]], [",", ",", "PUNCT", [19, 20]], ["\u017ee", "\u017ee", "SCONJ", [21, 23]], ["by", "b\u00fdt", "AUX", [24, 26]], ["p\u0159estal", "p\u0159estat", "VERB", [27, 34]], ["chodit", "chodit", "VERB", [35, 41]], ["do", "do", "ADP", [42, 44]], ["sv\u00e9", "sv\u016fj", "DET", [45, 48]], ["kancel\u00e1\u0159e", "kancel\u00e1\u0159", "NOUN", [49, 58]], ["v", "v", "ADP", [59, 60]], ["Penatgonu", "Penatgon", "PROPN", [61, 70]], [".", ".", "PUNCT", [70, 71]]]], ["calgarske-listy_2003_unor_ocr.txt", "Jeho syn William \u0159\u00edk\u00e1: \"M\u016fj otec nevid\u00ed d\u016fvod p\u0159estat d\u011blat to, co d\u011bl\u00e1, jen proto, \u017ee to p\u0159estal zaznamen\u00e1vat na pap\u00edr.", [["Jeho", "jeho", "DET", [0, 4]], ["syn", "syn", "NOUN", [5, 8]], ["William", "William", "PROPN", [9, 16]], ["\u0159\u00edk\u00e1", "\u0159\u00edkat", "VERB", [17, 21]], [":", ":", "PUNCT", [21, 22]], ["\"", "\"", "PUNCT", [23, 24]], ["M\u016fj", "m\u016fj", "DET", [24, 27]], ["otec", "otec", "NOUN", [28, 32]], ["nevid\u00ed", "vid\u011bt", "VERB", [33, 39]], ["d\u016fvod", "d\u016fvod", "NOUN", [40, 45]], ["p\u0159estat", "p\u0159estat", "VERB", [46, 53]], ["d\u011blat", "d\u011blat", "VERB", [54, 59]], ["to", "ten", "DET", [60, 62]], [",", ",", "PUNCT", [62, 63]], ["co", "co", "PRON", [64, 66]], ["d\u011bl\u00e1", "d\u011blat", "VERB", [67, 71]], [",", ",", "PUNCT", [71, 72]], ["jen", "jen", "PART", [73, 76]], ["proto", "proto", "ADV", [77, 82]], [",", ",", "PUNCT", [82, 83]], ["\u017ee", "\u017ee", "SCONJ", [84, 86]], ["to", "ten", "DET", [87, 89]], ["p\u0159estal", "p\u0159estat", "VERB", [90, 97]], ["zaznamen\u00e1vat", "zaznamen\u00e1vat", "VERB", [98, 110]], ["na", "na", "ADP", [111, 113]], ["pap\u00edr", "pap\u00edr", "NOUN", [114, 119]], [".", ".", "PUNCT", [119, 120]]]], ["calgarske-listy_2003_unor_ocr.txt", "R\u00e1d si popov\u00edd\u00e1, r\u00e1d povzpom\u00edn\u00e1 na n\u011bjak\u00fd sv\u016fj p\u0159\u00edb\u011bh a r\u00e1d si poslechne n\u011bco nov\u00e9ho.", [["R\u00e1d", "r\u00e1d", "ADJ", [0, 3]], ["si", "se", "PRON", [4, 6]], ["popov\u00edd\u00e1", "popov\u00eddat", "VERB", [7, 15]], [",", ",", "PUNCT", [15, 16]], ["r\u00e1d", "r\u00e1d", "ADJ", [17, 20]], ["povzpom\u00edn\u00e1", "povzpom\u00ednat", "VERB", [21, 31]], ["na", "na", "ADP", [32, 34]], ["n\u011bjak\u00fd", "n\u011bjak\u00fd", "DET", [35, 41]], ["sv\u016fj", "sv\u016fj", "DET", [42, 46]], ["p\u0159\u00edb\u011bh", "p\u0159\u00edb\u011bh", "NOUN", [47, 53]], ["a", "a", "CCONJ", [54, 55]], ["r\u00e1d", "r\u00e1d", "ADJ", [56, 59]], ["si", "se", "PRON", [60, 62]], ["poslechne", "poslechnout", "VERB", [63, 72]], ["n\u011bco", "n\u011bco", "PRON", [73, 77]], ["nov\u00e9ho", "nov\u00fd", "ADJ", [78, 84]], [".", ".", "PUNCT", [84, 85]]]], ["calgarske-listy_2003_unor_ocr.txt", "Pentagon mu d\u00e1v\u00e1 n\u011bco o \u010dem m\u016f\u017ee p\u0159em\u00fd\u0161let a mluvit.", [["Pentagon", "pentagon", "PROPN", [0, 8]], ["mu", "on", "PRON", [9, 11]], ["d\u00e1v\u00e1", "d\u00e1vat", "VERB", [12, 16]], ["n\u011bco", "n\u011bco", "PRON", [17, 21]], ["o", "o", "ADP", [22, 23]], ["\u010dem", "co", "PRON", [24, 27]], ["m\u016f\u017ee", "moci", "VERB", [28, 32]], ["p\u0159em\u00fd\u0161let", "p\u0159em\u00fd\u0161let", "VERB", [33, 42]], ["a", "a", "CCONJ", [43, 44]], ["mluvit", "mluvit", "VERB", [45, 51]], [".", ".", "PUNCT", [51, 52]]]], ["calgarske-listy_2003_unor_ocr.txt", "\"Bryan Whitman, kter\u00fd \u0159\u00edd\u00ed tiskov\u00e9 operace Pentagonu, p\u0159id\u011bluje kancel\u00e1\u0159e report\u00e9r\u016fm a vyd\u00e1v\u00e1 novin\u00e1\u0159sk\u00e9 akreditivy, p\u0159izn\u00e1v\u00e1, \u017ee ob\u010das sly\u0161\u00ed, \u017ee by kancel\u00e1\u0159 Raymonda Cromleyho a jeho tiskov\u00e9 opr\u00e1vn\u011bn\u00ed m\u011blo b\u00fdt zru\u0161eno, proto\u017ee u\u017e vlastn\u011b nep\u00ed\u0161e a je d\u016fchodce, a \u0159\u00edk\u00e1 o tom: \"J\u00e1 s\u00e1m nem\u00e1m \u017e\u00e1dn\u00e9 d\u016fkazy o tom, \u017ee by nepsal a ani o tom v\u011bd\u011bt nechci.", [["\"", "\"", "PUNCT", [0, 1]], ["Bryan", "Bryan", "PROPN", [1, 6]], ["Whitman", "Whitman", "PROPN", [7, 14]], [",", ",", "PUNCT", [14, 15]], ["kter\u00fd", "kter\u00fd", "DET", [16, 21]], ["\u0159\u00edd\u00ed", "\u0159\u00eddit", "VERB", [22, 26]], ["tiskov\u00e9", "tiskov\u00fd", "ADJ", [27, 34]], ["operace", "operace", "NOUN", [35, 42]], ["Pentagonu", "Pentagon", "PROPN", [43, 52]], [",", ",", "PUNCT", [52, 53]], ["p\u0159id\u011bluje", "p\u0159id\u011blovat", "VERB", [54, 63]], ["kancel\u00e1\u0159e", "kancel\u00e1\u0159", "NOUN", [64, 73]], ["report\u00e9r\u016fm", "report\u00e9r", "NOUN", [74, 84]], ["a", "a", "CCONJ", [85, 86]], ["vyd\u00e1v\u00e1", "vyd\u00e1vat", "VERB", [87, 93]], ["novin\u00e1\u0159sk\u00e9", "novin\u00e1\u0159sk\u00fd", "ADJ", [94, 104]], ["akreditivy", "akreditiva", "NOUN", [105, 115]], [",", ",", "PUNCT", [115, 116]], ["p\u0159izn\u00e1v\u00e1", "p\u0159izn\u00e1vat", "VERB", [117, 125]], [",", ",", "PUNCT", [125, 126]], ["\u017ee", "\u017ee", "SCONJ", [127, 129]], ["ob\u010das", "ob\u010das", "ADV", [130, 135]], ["sly\u0161\u00ed", "sly\u0161et", "VERB", [136, 141]], [",", ",", "PUNCT", [141, 142]], ["\u017ee", "\u017ee", "SCONJ", [143, 145]], ["by", "b\u00fdt", "AUX", [146, 148]], ["kancel\u00e1\u0159", "kancel\u00e1\u0159", "NOUN", [149, 157]], ["Raymonda", "Raymond", "PROPN", [158, 166]], ["Cromleyho", "Cromley", "PROPN", [167, 176]], ["a", "a", "CCONJ", [177, 178]], ["jeho", "jeho", "DET", [179, 183]], ["tiskov\u00e9", "tiskov\u00fd", "ADJ", [184, 191]], ["opr\u00e1vn\u011bn\u00ed", "opr\u00e1vn\u011bn\u00ed", "NOUN", [192, 201]], ["m\u011blo", "m\u00edt", "VERB", [202, 206]], ["b\u00fdt", "b\u00fdt", "AUX", [207, 210]], ["zru\u0161eno", "zru\u0161en\u00fd", "ADJ", [211, 218]], [",", ",", "PUNCT", [218, 219]], ["proto\u017ee", "proto\u017ee", "SCONJ", [220, 227]], ["u\u017e", "u\u017e", "ADV", [228, 230]], ["vlastn\u011b", "vlastn\u011b", "ADV", [231, 238]], ["nep\u00ed\u0161e", "ps\u00e1t", "VERB", [239, 245]], ["a", "a", "CCONJ", [246, 247]], ["je", "b\u00fdt", "AUX", [248, 250]], ["d\u016fchodce", "d\u016fchodce", "NOUN", [251, 259]], [",", ",", "PUNCT", [259, 260]], ["a", "a", "CCONJ", [261, 262]], ["\u0159\u00edk\u00e1", "\u0159\u00edkat", "VERB", [263, 267]], ["o", "o", "ADP", [268, 269]], ["tom", "ten", "DET", [270, 273]], [":", ":", "PUNCT", [273, 274]], ["\"", "\"", "PUNCT", [275, 276]], ["J\u00e1", "j\u00e1", "PRON", [276, 278]], ["s\u00e1m", "sam\u00fd", "DET", [279, 282]], ["nem\u00e1m", "m\u00edt", "VERB", [283, 288]], ["\u017e\u00e1dn\u00e9", "\u017e\u00e1dn\u00fd", "DET", [289, 294]], ["d\u016fkazy", "d\u016fkaz", "NOUN", [295, 301]], ["o", "o", "ADP", [302, 303]], ["tom", "ten", "DET", [304, 307]], [",", ",", "PUNCT", [307, 308]], ["\u017ee", "\u017ee", "SCONJ", [309, 311]], ["by", "b\u00fdt", "AUX", [312, 314]], ["nepsal", "ps\u00e1t", "VERB", [315, 321]], ["a", "a", "CCONJ", [322, 323]], ["ani", "ani", "CCONJ", [324, 327]], ["o", "o", "ADP", [328, 329]], ["tom", "ten", "DET", [330, 333]], ["v\u011bd\u011bt", "v\u011bd\u011bt", "VERB", [334, 339]], ["nechci", "cht\u00edt", "VERB", [340, 346]], [".", ".", "PUNCT", [346, 347]]]], ["calgarske-listy_2003_unor_ocr.txt", "Jak j\u00e1 to vid\u00edm, Raymond Cromley je pracuj\u00edc\u00ed report\u00e9r, zam\u011bstnan\u00fd firmou Cromley News Service\".", [["Jak", "jak", "ADV", [0, 3]], ["j\u00e1", "j\u00e1", "PRON", [4, 6]], ["to", "ten", "DET", [7, 9]], ["vid\u00edm", "vid\u011bt", "VERB", [10, 15]], [",", ",", "PUNCT", [15, 16]], ["Raymond", "Raymond", "PROPN", [17, 24]], ["Cromley", "Cromley", "PROPN", [25, 32]], ["je", "b\u00fdt", "AUX", [33, 35]], ["pracuj\u00edc\u00ed", "pracuj\u00edc\u00ed", "ADJ", [36, 45]], ["report\u00e9r", "report\u00e9r", "NOUN", [46, 54]], [",", ",", "PUNCT", [54, 55]], ["zam\u011bstnan\u00fd", "zam\u011bstnan\u00fd", "ADJ", [56, 66]], ["firmou", "firma", "NOUN", [67, 73]], ["Cromley", "Cromley", "X", [74, 81]], ["News", "News", "X", [82, 86]], ["Service", "Service", "X", [87, 94]], ["\"", "\"", "PUNCT", [94, 95]], [".", ".", "PUNCT", [95, 96]]]], ["calgarske-listy_2003_unor_ocr.txt", "Tak tohle v\u0161echno zhruba jsem jim vypr\u00e1v\u011bl v tom knihkupectv\u00ed a nikdo do n\u00e1s nevrtal a neptal se, zda si ty kn\u00ed\u017eky, co dr\u017e\u00edme v rukou, koup\u00edme.", [["Tak", "tak", "ADV", [0, 3]], ["tohle", "tenhle", "DET", [4, 9]], ["v\u0161echno", "v\u0161echen", "DET", [10, 17]], ["zhruba", "zhruba", "ADV", [18, 24]], ["jsem", "b\u00fdt", "AUX", [25, 29]], ["jim", "on", "PRON", [30, 33]], ["vypr\u00e1v\u011bl", "vypr\u00e1v\u011bt", "VERB", [34, 42]], ["v", "v", "ADP", [43, 44]], ["tom", "ten", "DET", [45, 48]], ["knihkupectv\u00ed", "knihkupectv\u00ed", "NOUN", [49, 61]], ["a", "a", "CCONJ", [62, 63]], ["nikdo", "nikdo", "PRON", [64, 69]], ["do", "do", "ADP", [70, 72]], ["n\u00e1s", "my", "PRON", [73, 76]], ["nevrtal", "vrtat", "VERB", [77, 84]], ["a", "a", "CCONJ", [85, 86]], ["neptal", "pt\u00e1t", "VERB", [87, 93]], ["se", "se", "PRON", [94, 96]], [",", ",", "PUNCT", [96, 97]], ["zda", "zda", "SCONJ", [98, 101]], ["si", "se", "PRON", [102, 104]], ["ty", "ten", "DET", [105, 107]], ["kn\u00ed\u017eky", "kn\u00ed\u017eka", "NOUN", [108, 114]], [",", ",", "PUNCT", [114, 115]], ["co", "co", "PRON", [116, 118]], ["dr\u017e\u00edme", "dr\u017eet", "VERB", [119, 125]], ["v", "v", "ADP", [126, 127]], ["rukou", "ruka", "NOUN", [128, 133]], [",", ",", "PUNCT", [133, 134]], ["koup\u00edme", "koupit", "VERB", [135, 142]], [".", ".", "PUNCT", [142, 143]]]], ["calgarske-listy_2003_unor_ocr.txt", "A vypr\u00e1v\u011bl jsem jim i o Berl\u00edn\u011b, o berl\u00ednsk\u00e9 zdi, co tam u\u017e nestoj\u00ed, o rostla tam jen vysok\u00e1 tr\u00e1va, kdo by ji asi sekal, a lebeda.", [["A", "a", "CCONJ", [0, 1]], ["vypr\u00e1v\u011bl", "vypr\u00e1v\u011bt", "VERB", [2, 10]], ["jsem", "b\u00fdt", "AUX", [11, 15]], ["jim", "on", "PRON", [16, 19]], ["i", "i", "CCONJ", [20, 21]], ["o", "o", "ADP", [22, 23]], ["Berl\u00edn\u011b", "Berl\u00edn", "PROPN", [24, 31]], [",", ",", "PUNCT", [31, 32]], ["o", "o", "ADP", [33, 34]], ["berl\u00ednsk\u00e9", "berl\u00ednsk\u00fd", "ADJ", [35, 44]], ["zdi", "ze\u010f", "NOUN", [45, 48]], [",", ",", "PUNCT", [48, 49]], ["co", "co", "PRON", [50, 52]], ["tam", "tam", "ADV", [53, 56]], ["u\u017e", "u\u017e", "ADV", [57, 59]], ["nestoj\u00ed", "st\u00e1t", "VERB", [60, 67]], [",", ",", "PUNCT", [67, 68]], ["o", "o", "ADP", [69, 70]], ["rostla", "r\u016fst", "VERB", [71, 77]], ["tam", "tam", "ADV", [78, 81]], ["jen", "jen", "ADV", [82, 85]], ["vysok\u00e1", "vysok\u00fd", "ADJ", [86, 92]], ["tr\u00e1va", "tr\u00e1va", "NOUN", [93, 98]], [",", ",", "PUNCT", [98, 99]], ["kdo", "kdo", "PRON", [100, 103]], ["by", "b\u00fdt", "AUX", [104, 106]], ["ji", "on", "PRON", [107, 109]], ["asi", "asi", "PART", [110, 113]], ["sekal", "sekat", "VERB", [114, 119]], [",", ",", "PUNCT", [119, 120]], ["a", "a", "CCONJ", [121, 122]], ["lebeda", "lebeda", "PROPN", [123, 129]], [".", ".", "PUNCT", [129, 130]]]], ["calgarske-listy_2003_unor_ocr.txt", "V t\u00e9 lebed\u011b se p\u0159emno\u017eili jen mal\u00ed kr\u00e1l\u00edci, kter\u00e9 nikdo neru\u0161il, proto\u017ee v tom p\u00e1smu se je st\u0159\u00edlet nikdo neodv\u00e1\u017eil, p\u0159\u00edmo chodit tam taky nikdo nemohl, kdy\u017e tam byly ty miny a kr\u00e1l\u00edci sami byli tak lehc\u00ed, \u017ee zahraban\u00e9 miny svou vahou neodp\u00e1lili, mohli d\u011blat hop hop hop, cupity dup, jak cht\u011bli a tak tam ti mal\u00ed n\u011bme\u010dt\u00ed kr\u00e1l\u00edci m\u011bli v tom zaminovan\u00e9m p\u00e1smu takov\u00fd neru\u0161en\u00fd surrealistick\u00fd r\u00e1j.", [["V", "v", "ADP", [0, 1]], ["t\u00e9", "ten", "DET", [2, 4]], ["lebed\u011b", "lebed", "NOUN", [5, 11]], ["se", "se", "PRON", [12, 14]], ["p\u0159emno\u017eili", "p\u0159emno\u017eit", "VERB", [15, 25]], ["jen", "jen", "PART", [26, 29]], ["mal\u00ed", "mal\u00fd", "ADJ", [30, 34]], ["kr\u00e1l\u00edci", "kr\u00e1l\u00edk", "NOUN", [35, 42]], [",", ",", "PUNCT", [42, 43]], ["kter\u00e9", "kter\u00fd", "DET", [44, 49]], ["nikdo", "nikdo", "PRON", [50, 55]], ["neru\u0161il", "ru\u0161it", "VERB", [56, 63]], [",", ",", "PUNCT", [63, 64]], ["proto\u017ee", "proto\u017ee", "SCONJ", [65, 72]], ["v", "v", "ADP", [73, 74]], ["tom", "ten", "DET", [75, 78]], ["p\u00e1smu", "p\u00e1smo", "NOUN", [79, 84]], ["se", "se", "PRON", [85, 87]], ["je", "on", "PRON", [88, 90]], ["st\u0159\u00edlet", "st\u0159\u00edlet", "VERB", [91, 98]], ["nikdo", "nikdo", "PRON", [99, 104]], ["neodv\u00e1\u017eil", "odv\u00e1\u017eit", "VERB", [105, 114]], [",", ",", "PUNCT", [114, 115]], ["p\u0159\u00edmo", "p\u0159\u00edmo", "ADV", [116, 121]], ["chodit", "chodit", "VERB", [122, 128]], ["tam", "tam", "ADV", [129, 132]], ["taky", "taky", "ADV", [133, 137]], ["nikdo", "nikdo", "PRON", [138, 143]], ["nemohl", "moci", "VERB", [144, 150]], [",", ",", "PUNCT", [150, 151]], ["kdy\u017e", "kdy\u017e", "SCONJ", [152, 156]], ["tam", "tam", "ADV", [157, 160]], ["byly", "b\u00fdt", "AUX", [161, 165]], ["ty", "ten", "DET", [166, 168]], ["miny", "mina", "NOUN", [169, 173]], ["a", "a", "CCONJ", [174, 175]], ["kr\u00e1l\u00edci", "kr\u00e1l\u00edk", "NOUN", [176, 183]], ["sami", "sam\u00fd", "DET", [184, 188]], ["byli", "b\u00fdt", "AUX", [189, 193]], ["tak", "tak", "ADV", [194, 197]], ["lehc\u00ed", "lehcet", "VERB", [198, 203]], [",", ",", "PUNCT", [203, 204]], ["\u017ee", "\u017ee", "SCONJ", [205, 207]], ["zahraban\u00e9", "zahraban\u00fd", "ADJ", [208, 217]], ["miny", "mina", "NOUN", [218, 222]], ["svou", "sv\u016fj", "DET", [223, 227]], ["vahou", "v\u00e1ha", "NOUN", [228, 233]], ["neodp\u00e1lili", "odp\u00e1lit", "VERB", [234, 244]], [",", ",", "PUNCT", [244, 245]], ["mohli", "moci", "VERB", [246, 251]], ["d\u011blat", "d\u011blat", "VERB", [252, 257]], ["hop", "hop", "X", [258, 261]], ["hop", "hop", "X", [262, 265]], ["hop", "hop", "X", [266, 269]], [",", ",", "PUNCT", [269, 270]], ["cupity", "cupita", "NOUN", [271, 277]], ["dup", "dup", "NOUN", [278, 281]], [",", ",", "PUNCT", [281, 282]], ["jak", "jak", "ADV", [283, 286]], ["cht\u011bli", "cht\u00edt", "VERB", [287, 293]], ["a", "a", "CCONJ", [294, 295]], ["tak", "tak", "ADV", [296, 299]], ["tam", "tam", "ADV", [300, 303]], ["ti", "ten", "DET", [304, 306]], ["mal\u00ed", "mal\u00fd", "ADJ", [307, 311]], ["n\u011bme\u010dt\u00ed", "n\u011bmeck\u00fd", "ADJ", [312, 319]], ["kr\u00e1l\u00edci", "kr\u00e1l\u00edk", "NOUN", [320, 327]], ["m\u011bli", "m\u00edt", "VERB", [328, 332]], ["v", "v", "ADP", [333, 334]], ["tom", "ten", "DET", [335, 338]], ["zaminovan\u00e9m", "zaminovan\u00fd", "ADJ", [339, 350]], ["p\u00e1smu", "p\u00e1smo", "NOUN", [351, 356]], ["takov\u00fd", "takov\u00fd", "DET", [357, 363]], ["neru\u0161en\u00fd", "ru\u0161en\u00fd", "ADJ", [364, 372]], ["surrealistick\u00fd", "surrealistick\u00fd", "ADJ", [373, 387]], ["r\u00e1j", "r\u00e1j", "NOUN", [388, 391]], [".", ".", "PUNCT", [391, 392]]]], ["calgarske-listy_2003_unor_ocr.txt", "Ano, byl jsem tam a dnes nev\u00edm, jak jsme mohli se z toho nezbl\u00e1znit...", [["Ano", "ano", "PART", [0, 3]], [",", ",", "PUNCT", [3, 4]], ["byl", "b\u00fdt", "AUX", [5, 8]], ["jsem", "b\u00fdt", "AUX", [9, 13]], ["tam", "tam", "ADV", [14, 17]], ["a", "a", "CCONJ", [18, 19]], ["dnes", "dnes", "ADV", [20, 24]], ["nev\u00edm", "v\u011bd\u011bt", "VERB", [25, 30]], [",", ",", "PUNCT", [30, 31]], ["jak", "jak", "ADV", [32, 35]], ["jsme", "b\u00fdt", "AUX", [36, 40]], ["mohli", "moci", "VERB", [41, 46]], ["se", "se", "PRON", [47, 49]], ["z", "z", "ADP", [50, 51]], ["toho", "ten", "DET", [52, 56]], ["nezbl\u00e1znit", "zbl\u00e1znit", "VERB", [57, 67]], [".", ".", "PUNCT", [67, 68]], [".", ".", "PUNCT", [68, 69]], [".", ".", "PUNCT", [69, 70]]]], ["calgarske-listy_2003_unor_ocr.txt", "A taky o zaj\u00edmav\u00e9m star\u00e9m \u017eelezn\u00e9m mostu jm\u00e9nem Glienicke Bridge p\u0159es Spr\u00e9vu (p\u0159es Berlin se t\u00e1hne i Havel, jen tenhle net\u00e1hne do Portugalska), kde si civilizovan\u00fd sv\u011bt s \u0159\u00ed\u0161\u00ed zla vym\u011b\u0148ovaly lidi za lidi a jak tam \u0161el i Karel Kocher, a jeho fe\u0161n\u00e1 pan\u00ed v b\u00edl\u00e9m ko\u017eichu a z druh\u00e9 strany p\u0159ich\u00e1zel mal\u00fd \u010dlov\u00ed\u010dek s velkou hlavou v beranici - Anatolij S\u010daranskij, co se dnes jmenuje Nathan Sharansk\u00fd a je ministrem vl\u00e1dy v Izraeli.", [["A", "a", "CCONJ", [0, 1]], ["taky", "taky", "ADV", [2, 6]], ["o", "o", "ADP", [7, 8]], ["zaj\u00edmav\u00e9m", "zaj\u00edmav\u00fd", "ADJ", [9, 18]], ["star\u00e9m", "star\u00fd", "ADJ", [19, 25]], ["\u017eelezn\u00e9m", "\u017eelezn\u00fd", "ADJ", [26, 34]], ["mostu", "most", "NOUN", [35, 40]], ["jm\u00e9nem", "jm\u00e9no", "NOUN", [41, 47]], ["Glienicke", "Glienicke", "X", [48, 57]], ["Bridge", "Bridge", "X", [58, 64]], ["p\u0159es", "p\u0159es", "ADP", [65, 69]], ["Spr\u00e9vu", "Spr\u00e9va", "PROPN", [70, 76]], ["(", "(", "PUNCT", [77, 78]], ["p\u0159es", "p\u0159es", "ADP", [78, 82]], ["Berlin", "Berlin", "PROPN", [83, 89]], ["se", "se", "PRON", [90, 92]], ["t\u00e1hne", "t\u00e1hnout", "VERB", [93, 98]], ["i", "i", "CCONJ", [99, 100]], ["Havel", "Havel", "PROPN", [101, 106]], [",", ",", "PUNCT", [106, 107]], ["jen", "jen", "ADV", [108, 111]], ["tenhle", "tenhle", "DET", [112, 118]], ["net\u00e1hne", "l\u00e1hnout", "VERB", [119, 126]], ["do", "do", "ADP", [127, 129]], ["Portugalska", "Portugalsko", "PROPN", [130, 141]], [")", ")", "PUNCT", [141, 142]], [",", ",", "PUNCT", [142, 143]], ["kde", "kde", "ADV", [144, 147]], ["si", "se", "PRON", [148, 150]], ["civilizovan\u00fd", "civilizovan\u00fd", "ADJ", [151, 163]], ["sv\u011bt", "sv\u011bt", "NOUN", [164, 168]], ["s", "s", "ADP", [169, 170]], ["\u0159\u00ed\u0161\u00ed", "\u0159\u00ed\u0161e", "NOUN", [171, 175]], ["zla", "zlo", "NOUN", [176, 179]], ["vym\u011b\u0148ovaly", "vym\u011b\u0148ovat", "VERB", [180, 190]], ["lidi", "lid\u00e9", "NOUN", [191, 195]], ["za", "za", "ADP", [196, 198]], ["lidi", "lid\u00e9", "NOUN", [199, 203]], ["a", "a", "CCONJ", [204, 205]], ["jak", "jak", "ADV", [206, 209]], ["tam", "tam", "ADV", [210, 213]], ["\u0161el", "j\u00edt", "VERB", [214, 217]], ["i", "i", "CCONJ", [218, 219]], ["Karel", "Karel", "PROPN", [220, 225]], ["Kocher", "Kocher", "PROPN", [226, 232]], [",", ",", "PUNCT", [232, 233]], ["a", "a", "CCONJ", [234, 235]], ["jeho", "jeho", "DET", [236, 240]], ["fe\u0161n\u00e1", "fe\u0161n\u00fd", "ADJ", [241, 246]], ["pan\u00ed", "pan\u00ed", "NOUN", [247, 251]], ["v", "v", "ADP", [252, 253]], ["b\u00edl\u00e9m", "b\u00edl\u00fd", "ADJ", [254, 259]], ["ko\u017eichu", "ko\u017eich", "NOUN", [260, 267]], ["a", "a", "CCONJ", [268, 269]], ["z", "z", "ADP", [270, 271]], ["druh\u00e9", "druh\u00fd", "ADJ", [272, 277]], ["strany", "strana", "NOUN", [278, 284]], ["p\u0159ich\u00e1zel", "p\u0159ich\u00e1zet", "VERB", [285, 294]], ["mal\u00fd", "mal\u00fd", "ADJ", [295, 299]], ["\u010dlov\u00ed\u010dek", "\u010dlov\u00ed\u010dek", "NOUN", [300, 308]], ["s", "s", "ADP", [309, 310]], ["velkou", "velk\u00fd", "ADJ", [311, 317]], ["hlavou", "hlava", "NOUN", [318, 324]], ["v", "v", "ADP", [325, 326]], ["beranici", "beranice", "NOUN", [327, 335]], ["-", "-", "PUNCT", [336, 337]], ["Anatolij", "Anatolij", "PROPN", [338, 346]], ["S\u010daranskij", "S\u010daranskij", "PROPN", [347, 357]], [",", ",", "PUNCT", [357, 358]], ["co", "co", "PRON", [359, 361]], ["se", "se", "PRON", [362, 364]], ["dnes", "dnes", "ADV", [365, 369]], ["jmenuje", "jmenovat", "VERB", [370, 377]], ["Nathan", "Nathan", "PROPN", [378, 384]], ["Sharansk\u00fd", "Sharansk\u00fd", "PROPN", [385, 394]], ["a", "a", "CCONJ", [395, 396]], ["je", "b\u00fdt", "AUX", [397, 399]], ["ministrem", "ministr", "NOUN", [400, 409]], ["vl\u00e1dy", "vl\u00e1da", "NOUN", [410, 415]], ["v", "v", "ADP", [416, 417]], ["Izraeli", "Izrael", "PROPN", [418, 425]], [".", ".", "PUNCT", [425, 426]]]], ["calgarske-listy_2003_unor_ocr.txt", "I tam jsem byl.", [["I", "i", "CCONJ", [0, 1]], ["tam", "tam", "ADV", [2, 5]], ["jsem", "b\u00fdt", "AUX", [6, 10]], ["byl", "b\u00fdt", "AUX", [11, 14]], [".", ".", "PUNCT", [14, 15]]]], ["calgarske-listy_2003_unor_ocr.txt", "Pan\u00ed knihkupcov\u00e1 Barnes Noblova pok\u00fdvala hlavou a pravila: \"There is a great book behind every old man!\"", [["Pan\u00ed", "pan\u00ed", "NOUN", [0, 4]], ["knihkupcov\u00e1", "knihkupcov\u00fd", "ADJ", [5, 16]], ["Barnes", "Barnes", "PROPN", [17, 23]], ["Noblova", "Noblov", "PROPN", [24, 31]], ["pok\u00fdvala", "pok\u00fdvat", "VERB", [32, 40]], ["hlavou", "hlava", "NOUN", [41, 47]], ["a", "a", "CCONJ", [48, 49]], ["pravila", "pravit", "VERB", [50, 57]], [":", ":", "PUNCT", [57, 58]], ["\"", "\"", "PUNCT", [59, 60]], ["There", "There", "X", [60, 65]], ["is", "is", "X", [66, 68]], ["a", "a", "CCONJ", [69, 70]], ["great", "great", "X", [71, 76]], ["book", "book", "X", [77, 81]], ["behind", "behind", "X", [82, 88]], ["every", "every", "X", [89, 94]], ["old", "old", "X", [95, 98]], ["man", "man", "X", [99, 102]], ["!", "!", "PUNCT", [102, 103]], ["\"", "\"", "PUNCT", [103, 104]]]], ["calgarske-listy_2003_unor_ocr.txt", "(Za ka\u017ed\u00fdm d\u016fchodcem je velk\u00e1 kniha).", [["(", "(", "PUNCT", [0, 1]], ["Za", "za", "ADP", [1, 3]], ["ka\u017ed\u00fdm", "ka\u017ed\u00fd", "DET", [4, 10]], ["d\u016fchodcem", "d\u016fchodce", "NOUN", [11, 20]], ["je", "b\u00fdt", "AUX", [21, 23]], ["velk\u00e1", "velk\u00fd", "ADJ", [24, 29]], ["kniha", "kniha", "NOUN", [30, 35]], [")", ")", "PUNCT", [35, 36]], [".", ".", "PUNCT", [36, 37]]]], ["calgarske-listy_2003_unor_ocr.txt", "Oto\u010dil jsem se a za mnou byl akor\u00e1t sloup, reg\u00e1ly s kn\u00ed\u017ekama byly a\u017e o kus d\u00e1l, tak\u017ee ani nev\u00edm, kterou velkou knihu vlastn\u011b myslela.", [["Oto\u010dil", "oto\u010dit", "VERB", [0, 6]], ["jsem", "b\u00fdt", "AUX", [7, 11]], ["se", "se", "PRON", [12, 14]], ["a", "a", "CCONJ", [15, 16]], ["za", "za", "ADP", [17, 19]], ["mnou", "j\u00e1", "PRON", [20, 24]], ["byl", "b\u00fdt", "AUX", [25, 28]], ["akor\u00e1t", "akor\u00e1t", "ADV", [29, 35]], ["sloup", "sloup", "NOUN", [36, 41]], [",", ",", "PUNCT", [41, 42]], ["reg\u00e1ly", "reg\u00e1l", "NOUN", [43, 49]], ["s", "s", "ADP", [50, 51]], ["kn\u00ed\u017ekama", "kn\u00ed\u017ekama", "NOUN", [52, 60]], ["byly", "b\u00fdt", "AUX", [61, 65]], ["a\u017e", "a\u017e", "PART", [66, 68]], ["o", "o", "ADP", [69, 70]], ["kus", "kus", "NOUN", [71, 74]], ["d\u00e1l", "d\u00e1l", "ADV", [75, 78]], [",", ",", "PUNCT", [78, 79]], ["tak\u017ee", "tak\u017ee", "SCONJ", [80, 85]], ["ani", "ani", "CCONJ", [86, 89]], ["nev\u00edm", "v\u011bd\u011bt", "VERB", [90, 95]], [",", ",", "PUNCT", [95, 96]], ["kterou", "kter\u00fd", "DET", [97, 103]], ["velkou", "velk\u00fd", "ADJ", [104, 110]], ["knihu", "kniha", "NOUN", [111, 116]], ["vlastn\u011b", "vlastn\u011b", "ADV", [117, 124]], ["myslela", "myslit", "VERB", [125, 132]], [".", ".", "PUNCT", [132, 133]]]], ["calgarske-listy_2003_unor_ocr.txt", "p\u0159edhon\u00ed.", [["p\u0159edhon\u00ed", "p\u0159edhonit", "VERB", [0, 8]], [".", ".", "PUNCT", [8, 9]]]], ["calgarske-listy_2003_unor_ocr.txt", "Ani si u\u017e nepamatuji, jak snadno jsem se nechal vyl\u00e1kat na ty rann\u00ed v\u00fdpravy, ale jak jsme se dostali do lesa, tak to jsem hned o\u017eil.", [["Ani", "ani", "CCONJ", [0, 3]], ["si", "se", "PRON", [4, 6]], ["u\u017e", "u\u017e", "ADV", [7, 9]], ["nepamatuji", "pamatovat", "VERB", [10, 20]], [",", ",", "PUNCT", [20, 21]], ["jak", "jak", "ADV", [22, 25]], ["snadno", "snadno", "ADV", [26, 32]], ["jsem", "b\u00fdt", "AUX", [33, 37]], ["se", "se", "PRON", [38, 40]], ["nechal", "nechat", "VERB", [41, 47]], ["vyl\u00e1kat", "vyl\u00e1kat", "VERB", [48, 55]], ["na", "na", "ADP", [56, 58]], ["ty", "ten", "DET", [59, 61]], ["rann\u00ed", "rann\u00ed", "ADJ", [62, 67]], ["v\u00fdpravy", "v\u00fdprava", "NOUN", [68, 75]], [",", ",", "PUNCT", [75, 76]], ["ale", "ale", "CCONJ", [77, 80]], ["jak", "jak", "ADV", [81, 84]], ["jsme", "b\u00fdt", "AUX", [85, 89]], ["se", "se", "PRON", [90, 92]], ["dostali", "dostat", "VERB", [93, 100]], ["do", "do", "ADP", [101, 103]], ["lesa", "les", "NOUN", [104, 108]], [",", ",", "PUNCT", [108, 109]], ["tak", "tak", "ADV", [110, 113]], ["to", "ten", "DET", [114, 116]], ["jsem", "b\u00fdt", "AUX", [117, 121]], ["hned", "hned", "ADV", [122, 126]], ["o\u017eil", "o\u017e\u00edt", "VERB", [127, 131]], [".", ".", "PUNCT", [131, 132]]]], ["calgarske-listy_2003_unor_ocr.txt", "Na\u0161\u00ed snahou bylo co nejd\u0159\u00edve prohl\u00e9dnout kus les\u00edka zvan\u00e9ho C\u00edpek.", [["Na\u0161\u00ed", "n\u00e1\u0161", "DET", [0, 4]], ["snahou", "snaha", "NOUN", [5, 11]], ["bylo", "b\u00fdt", "AUX", [12, 16]], ["co", "co", "ADV", [17, 19]], ["nejd\u0159\u00edve", "d\u0159\u00edve", "ADV", [20, 28]], ["prohl\u00e9dnout", "prohl\u00e9dnout", "VERB", [29, 40]], ["kus", "kus", "NOUN", [41, 44]], ["les\u00edka", "les\u00edk", "NOUN", [45, 51]], ["zvan\u00e9ho", "zvan\u00fd", "ADJ", [52, 59]], ["C\u00edpek", "C\u00edpek", "PROPN", [60, 65]], [".", ".", "PUNCT", [65, 66]]]], ["calgarske-listy_2003_unor_ocr.txt", "Z 13  obou stran C\u00edpku vedly cesty a m\u011bl v podstat\u011b tvar troj\u00faheln\u00edku.", [["Z", "z", "ADP", [0, 1]], ["13", "13", "NUM", [2, 4]], ["obou", "oba", "NUM", [6, 10]], ["stran", "strana", "NOUN", [11, 16]], ["C\u00edpku", "C\u00edpek", "PROPN", [17, 22]], ["vedly", "v\u00e9st", "VERB", [23, 28]], ["cesty", "cesta", "NOUN", [29, 34]], ["a", "a", "CCONJ", [35, 36]], ["m\u011bl", "m\u00edt", "VERB", [37, 40]], ["v", "v", "ADP", [41, 42]], ["podstat\u011b", "podstata", "NOUN", [43, 51]], ["tvar", "tvar", "NOUN", [52, 56]], ["troj\u00faheln\u00edku", "troj\u00faheln\u00edk", "NOUN", [57, 69]], [".", ".", "PUNCT", [69, 70]]]], ["calgarske-listy_2003_unor_ocr.txt", "Stromy byly asi 40 let star\u00e9, kdysi zasazen\u00e9 do hust\u00fdch \u0159ad.", [["Stromy", "strom", "NOUN", [0, 6]], ["byly", "b\u00fdt", "AUX", [7, 11]], ["asi", "asi", "PART", [12, 15]], ["40", "40", "NUM", [16, 18]], ["let", "l\u00e9ta", "NOUN", [19, 22]], ["star\u00e9", "star\u00fd", "ADJ", [23, 28]], [",", ",", "PUNCT", [28, 29]], ["kdysi", "kdysi", "ADV", [30, 35]], ["zasazen\u00e9", "zasazen\u00fd", "ADJ", [36, 44]], ["do", "do", "ADP", [45, 47]], ["hust\u00fdch", "hust\u00fd", "ADJ", [48, 55]], ["\u0159ad", "\u0159ada", "NOUN", [56, 59]], [".", ".", "PUNCT", [59, 60]]]], ["calgarske-listy_2003_unor_ocr.txt", "Zde rostly spousty b\u00edl\u00fdch h\u0159\u00edbk\u016f \u010di jak se jim u n\u00e1s doma \u0159\u00edkalo, prav\u00fdch.", [["Zde", "zde", "ADV", [0, 3]], ["rostly", "r\u016fst", "VERB", [4, 10]], ["spousty", "spousta", "NOUN", [11, 18]], ["b\u00edl\u00fdch", "b\u00edl\u00fd", "ADJ", [19, 25]], ["h\u0159\u00edbk\u016f", "h\u0159\u00edbky", "NOUN", [26, 32]], ["\u010di", "\u010di", "CCONJ", [33, 35]], ["jak", "jak", "ADV", [36, 39]], ["se", "se", "PRON", [40, 42]], ["jim", "on", "PRON", [43, 46]], ["u", "u", "ADP", [47, 48]], ["n\u00e1s", "my", "PRON", [49, 52]], ["doma", "doma", "ADV", [53, 57]], ["\u0159\u00edkalo", "\u0159\u00edkat", "VERB", [58, 64]], [",", ",", "PUNCT", [64, 65]], ["prav\u00fdch", "prav\u00fd", "ADJ", [66, 73]], [".", ".", "PUNCT", [73, 74]]]], ["calgarske-listy_2003_unor_ocr.txt", "Brzy jsem pochopil, \u017ee tam kde star\u00e9 jehli\u010d\u00ed tvo\u0159ilo mal\u00fd kope\u010dek, tam bylo nutno se p\u0159esv\u011bd\u010dit.", [["Brzy", "brzy", "ADV", [0, 4]], ["jsem", "b\u00fdt", "AUX", [5, 9]], ["pochopil", "pochopit", "VERB", [10, 18]], [",", ",", "PUNCT", [18, 19]], ["\u017ee", "\u017ee", "SCONJ", [20, 22]], ["tam", "tam", "ADV", [23, 26]], ["kde", "kde", "ADV", [27, 30]], ["star\u00e9", "star\u00fd", "ADJ", [31, 36]], ["jehli\u010d\u00ed", "jehli\u010d\u00ed", "NOUN", [37, 44]], ["tvo\u0159ilo", "tvo\u0159it", "VERB", [45, 52]], ["mal\u00fd", "mal\u00fd", "ADJ", [53, 57]], ["kope\u010dek", "kope\u010dek", "NOUN", [58, 65]], [",", ",", "PUNCT", [65, 66]], ["tam", "tam", "ADV", [67, 70]], ["bylo", "b\u00fdt", "AUX", [71, 75]], ["nutno", "nutn\u00fd", "ADJ", [76, 81]], ["se", "se", "PRON", [82, 84]], ["p\u0159esv\u011bd\u010dit", "p\u0159esv\u011bd\u010dit", "VERB", [85, 95]], [".", ".", "PUNCT", [95, 96]]]], ["calgarske-listy_2003_unor_ocr.txt", "Babi\u010dka v\u017edy \u0159\u00edkala, je po de\u0161ti a tepl\u00e9 noci, dnes jich bude hodn\u011b.", [["Babi\u010dka", "babi\u010dka", "NOUN", [0, 7]], ["v\u017edy", "v\u017edy", "ADV", [8, 12]], ["\u0159\u00edkala", "\u0159\u00edkat", "VERB", [13, 19]], [",", ",", "PUNCT", [19, 20]], ["je", "b\u00fdt", "AUX", [21, 23]], ["po", "po", "ADP", [24, 26]], ["de\u0161ti", "d\u00e9\u0161\u0165", "NOUN", [27, 32]], ["a", "a", "CCONJ", [33, 34]], ["tepl\u00e9", "tepl\u00fd", "ADJ", [35, 40]], ["noci", "noc", "NOUN", [41, 45]], [",", ",", "PUNCT", [45, 46]], ["dnes", "dnes", "ADV", [47, 51]], ["jich", "on", "PRON", [52, 56]], ["bude", "b\u00fdt", "AUX", [57, 61]], ["hodn\u011b", "hodn\u011b", "ADV", [62, 67]], [".", ".", "PUNCT", [67, 68]]]], ["calgarske-listy_2003_unor_ocr.txt", "To pak byly 3 i 4 h\u0159\u00edbe\u010dkov\u00e9 velmi bl\u00edzko sebe.", [["To", "ten", "DET", [0, 2]], ["pak", "pak", "ADV", [3, 6]], ["byly", "b\u00fdt", "AUX", [7, 11]], ["3", "3", "NUM", [12, 13]], ["i", "i", "CCONJ", [14, 15]], ["4", "4", "NUM", [16, 17]], ["h\u0159\u00edbe\u010dkov\u00e9", "h\u0159\u00edbe\u010dkov\u00fd", "ADJ", [18, 28]], ["velmi", "velmi", "ADV", [29, 34]], ["bl\u00edzko", "bl\u00edzko", "ADV", [35, 41]], ["sebe", "se", "PRON", [42, 46]], [".", ".", "PUNCT", [46, 47]]]], ["calgarske-listy_2003_unor_ocr.txt", "Kdy\u017e s n\u00e1mi n\u011bkdy \u0161la na houby moje o 3 roky star\u0161\u00ed sestra Jana, p\u0159irozen\u011b hned jsme z\u00e1vodili kdo jich v\u00edce najde.", [["Kdy\u017e", "kdy\u017e", "SCONJ", [0, 4]], ["s", "s", "ADP", [5, 6]], ["n\u00e1mi", "my", "PRON", [7, 11]], ["n\u011bkdy", "n\u011bkdy", "ADV", [12, 17]], ["\u0161la", "j\u00edt", "VERB", [18, 21]], ["na", "na", "ADP", [22, 24]], ["houby", "houba", "NOUN", [25, 30]], ["moje", "m\u016fj", "DET", [31, 35]], ["o", "o", "ADP", [36, 37]], ["3", "3", "NUM", [38, 39]], ["roky", "rok", "NOUN", [40, 44]], ["star\u0161\u00ed", "star\u00fd", "ADJ", [45, 51]], ["sestra", "sestra", "NOUN", [52, 58]], ["Jana", "Jan", "PROPN", [59, 63]], [",", ",", "PUNCT", [63, 64]], ["p\u0159irozen\u011b", "p\u0159irozen\u011b", "ADV", [65, 74]], ["hned", "hned", "ADV", [75, 79]], ["jsme", "b\u00fdt", "AUX", [80, 84]], ["z\u00e1vodili", "z\u00e1vodit", "VERB", [85, 93]], ["kdo", "kdo", "PRON", [94, 97]], ["jich", "on", "PRON", [98, 102]], ["v\u00edce", "v\u00edce", "ADV", [103, 107]], ["najde", "naj\u00edt", "VERB", [108, 113]], [".", ".", "PUNCT", [113, 114]]]], ["calgarske-listy_2003_unor_ocr.txt", "Kdy\u017e bylo m\u00ed\u0148 t\u011bch prav\u00fdch, b\u00edl\u00fdch, sb\u00edrali jsme komen\u00ed\u010dky s hn\u011bd\u00fdmi \u010di zeleno hn\u011bd\u00fdmi klobou\u010dky.", [["Kdy\u017e", "kdy\u017e", "SCONJ", [0, 4]], ["bylo", "b\u00fdt", "AUX", [5, 9]], ["m\u00ed\u0148", "m\u00e9n\u011b", "ADV", [10, 13]], ["t\u011bch", "ten", "DET", [14, 18]], ["prav\u00fdch", "prav\u00fd", "ADJ", [19, 26]], [",", ",", "PUNCT", [26, 27]], ["b\u00edl\u00fdch", "b\u00edl\u00fd", "ADJ", [28, 34]], [",", ",", "PUNCT", [34, 35]], ["sb\u00edrali", "sb\u00edrat", "VERB", [36, 43]], ["jsme", "b\u00fdt", "AUX", [44, 48]], ["komen\u00ed\u010dky", "komen\u00ed\u010dek", "NOUN", [49, 58]], ["s", "s", "ADP", [59, 60]], ["hn\u011bd\u00fdmi", "hn\u011bd\u00fd", "ADJ", [61, 68]], ["\u010di", "\u010di", "CCONJ", [69, 71]], ["zeleno", "zeleno", "NOUN", [72, 78]], ["hn\u011bd\u00fdmi", "hn\u011bd\u00fd", "ADJ", [79, 86]], ["klobou\u010dky", "klobou\u010dek", "NOUN", [87, 96]], [".", ".", "PUNCT", [96, 97]]]], ["calgarske-listy_2003_unor_ocr.txt", "Do dal\u0161\u00edho ko\u0161\u00edku jsme sb\u00edrali i \u017elut\u00e9 li\u0161ky, kter\u00fdch tam tehd\u00e1 rostly cel\u00e9 kolonie.", [["Do", "do", "ADP", [0, 2]], ["dal\u0161\u00edho", "dal\u0161\u00ed", "ADJ", [3, 10]], ["ko\u0161\u00edku", "ko\u0161\u00edk", "NOUN", [11, 17]], ["jsme", "b\u00fdt", "AUX", [18, 22]], ["sb\u00edrali", "sb\u00edrat", "VERB", [23, 30]], ["i", "i", "CCONJ", [31, 32]], ["\u017elut\u00e9", "\u017elut\u00fd", "ADJ", [33, 38]], ["li\u0161ky", "li\u0161ka", "NOUN", [39, 44]], [",", ",", "PUNCT", [44, 45]], ["kter\u00fdch", "kter\u00fd", "DET", [46, 53]], ["tam", "tam", "ADV", [54, 57]], ["tehd\u00e1", "tehdy", "PRON", [58, 63]], ["rostly", "r\u016fst", "VERB", [64, 70]], ["cel\u00e9", "cel\u00fd", "ADJ", [71, 75]], ["kolonie", "kolonie", "NOUN", [76, 83]], [".", ".", "PUNCT", [83, 84]]]], ["calgarske-listy_2003_unor_ocr.txt", "Ty babi\u010dka pou\u017e\u00edvala do b\u00edl\u00e9 hust\u00e9 pol\u00e9vky, kterou naz\u00fdvala kudla\u010dka a j\u00e1 j\u00ed m\u011bl moc r\u00e1d.", [["Ty", "ten", "DET", [0, 2]], ["babi\u010dka", "babi\u010dka", "NOUN", [3, 10]], ["pou\u017e\u00edvala", "pou\u017e\u00edvat", "VERB", [11, 20]], ["do", "do", "ADP", [21, 23]], ["b\u00edl\u00e9", "b\u00edl\u00fd", "ADJ", [24, 28]], ["hust\u00e9", "hust\u00fd", "ADJ", [29, 34]], ["pol\u00e9vky", "pol\u00e9vka", "NOUN", [35, 42]], [",", ",", "PUNCT", [42, 43]], ["kterou", "kter\u00fd", "DET", [44, 50]], ["naz\u00fdvala", "naz\u00fdvat", "VERB", [51, 59]], ["kudla\u010dka", "kudla\u010dka", "NOUN", [60, 68]], ["a", "a", "CCONJ", [69, 70]], ["j\u00e1", "j\u00e1", "PRON", [71, 73]], ["j\u00ed", "on", "PRON", [74, 76]], ["m\u011bl", "m\u00edt", "VERB", [77, 80]], ["moc", "moc", "ADV", [81, 84]], ["r\u00e1d", "r\u00e1d", "ADJ", [85, 88]], [".", ".", "PUNCT", [88, 89]]]], ["calgarske-listy_2003_unor_ocr.txt", "Pades\u00e1t let pozd\u011bji pak pr\u00fd ty \u017elut\u00e9 li\u0161ky p\u0159estaly r\u016fst \u00fapln\u011b, proto\u017ee jsou citliv\u00e9 na zne\u010di\u0161t\u011bn\u00ed vzduchu \u0161kodlivinami ze spalov\u00e1n\u00ed levn\u00e9ho hn\u011bd\u00e9ho uhl\u00ed, pln\u00e9ho s\u00edry.", [["Pades\u00e1t", "pades\u00e1t", "NUM", [0, 7]], ["let", "l\u00e9ta", "NOUN", [8, 11]], ["pozd\u011bji", "pozd\u011b", "ADV", [12, 19]], ["pak", "pak", "ADV", [20, 23]], ["pr\u00fd", "pr\u00fd", "PART", [24, 27]], ["ty", "ten", "DET", [28, 30]], ["\u017elut\u00e9", "\u017elut\u00fd", "ADJ", [31, 36]], ["li\u0161ky", "li\u0161ka", "NOUN", [37, 42]], ["p\u0159estaly", "p\u0159estat", "VERB", [43, 51]], ["r\u016fst", "r\u016fst", "NOUN", [52, 56]], ["\u00fapln\u011b", "\u00fapln\u011b", "ADV", [57, 62]], [",", ",", "PUNCT", [62, 63]], ["proto\u017ee", "proto\u017ee", "SCONJ", [64, 71]], ["jsou", "b\u00fdt", "AUX", [72, 76]], ["citliv\u00e9", "citliv\u00fd", "ADJ", [77, 84]], ["na", "na", "ADP", [85, 87]], ["zne\u010di\u0161t\u011bn\u00ed", "zne\u010di\u0161t\u011bn\u00ed", "NOUN", [88, 98]], ["vzduchu", "vzduch", "NOUN", [99, 106]], ["\u0161kodlivinami", "\u0161kodlivina", "NOUN", [107, 119]], ["ze", "z", "ADP", [120, 122]], ["spalov\u00e1n\u00ed", "spalov\u00e1n\u00ed", "NOUN", [123, 132]], ["levn\u00e9ho", "levn\u00fd", "ADJ", [133, 140]], ["hn\u011bd\u00e9ho", "hn\u011bd\u00fd", "ADJ", [141, 148]], ["uhl\u00ed", "uhl\u00ed", "NOUN", [149, 153]], [",", ",", "PUNCT", [153, 154]], ["pln\u00e9ho", "pln\u00fd", "ADJ", [155, 161]], ["s\u00edry", "s\u00edra", "NOUN", [162, 166]], [".", ".", "PUNCT", [166, 167]]]], ["calgarske-listy_2003_unor_ocr.txt", "N\u011bkdy bylo hodn\u011b ryzc\u016f, kter\u00e9 babi\u010dka nakl\u00e1dala do octa.", [["N\u011bkdy", "n\u011bkdy", "ADV", [0, 5]], ["bylo", "b\u00fdt", "AUX", [6, 10]], ["hodn\u011b", "hodn\u011b", "ADV", [11, 16]], ["ryzc\u016f", "ryzec", "NOUN", [17, 22]], [",", ",", "PUNCT", [22, 23]], ["kter\u00e9", "kter\u00fd", "DET", [24, 29]], ["babi\u010dka", "babi\u010dka", "NOUN", [30, 37]], ["nakl\u00e1dala", "nakl\u00e1dat", "VERB", [38, 47]], ["do", "do", "ADP", [48, 50]], ["octa", "octa", "NOUN", [51, 55]], [".", ".", "PUNCT", [55, 56]]]], ["calgarske-listy_2003_unor_ocr.txt", "Ten prav\u00fd ryzec se poznal, \u017ee z n\u011bho po \u0159\u00edznut\u00ed vyt\u00e9kalo b\u00edl\u00e9 ml\u00e9ko.", [["Ten", "ten", "DET", [0, 3]], ["prav\u00fd", "prav\u00fd", "ADJ", [4, 9]], ["ryzec", "ryzec", "NOUN", [10, 15]], ["se", "se", "PRON", [16, 18]], ["poznal", "poznat", "VERB", [19, 25]], [",", ",", "PUNCT", [25, 26]], ["\u017ee", "\u017ee", "SCONJ", [27, 29]], ["z", "z", "ADP", [30, 31]], ["n\u011bho", "on", "PRON", [32, 36]], ["po", "po", "ADP", [37, 39]], ["\u0159\u00edznut\u00ed", "\u0159\u00edznut\u00ed", "NOUN", [40, 47]], ["vyt\u00e9kalo", "vyt\u00e9kat", "VERB", [48, 56]], ["b\u00edl\u00e9", "b\u00edl\u00fd", "ADJ", [57, 61]], ["ml\u00e9ko", "ml\u00e9ko", "NOUN", [62, 67]], [".", ".", "PUNCT", [67, 68]]]], ["calgarske-listy_2003_unor_ocr.txt", "Po prohled\u00e1n\u00ed na\u0161eho C\u00edpku jsme pro\u0161li sm\u011brem k domovu vysok\u00fdm borov\u00fdm lesem, kde rostli n\u00e1dhern\u00ed podborov\u00e1ci s hn\u011bd\u00fdmi klobou\u010dky.", [["Po", "po", "ADP", [0, 2]], ["prohled\u00e1n\u00ed", "prohled\u00e1n\u00ed", "NOUN", [3, 13]], ["na\u0161eho", "n\u00e1\u0161", "DET", [14, 20]], ["C\u00edpku", "C\u00edpek", "PROPN", [21, 26]], ["jsme", "b\u00fdt", "AUX", [27, 31]], ["pro\u0161li", "proj\u00edt", "VERB", [32, 38]], ["sm\u011brem", "sm\u011br", "NOUN", [39, 45]], ["k", "k", "ADP", [46, 47]], ["domovu", "domov", "NOUN", [48, 54]], ["vysok\u00fdm", "vysok\u00fd", "ADJ", [55, 62]], ["borov\u00fdm", "borov\u00fd", "ADJ", [63, 70]], ["lesem", "les", "NOUN", [71, 76]], [",", ",", "PUNCT", [76, 77]], ["kde", "kde", "ADV", [78, 81]], ["rostli", "r\u016fst", "VERB", [82, 88]], ["n\u00e1dhern\u00ed", "n\u00e1dhern\u00ed", "ADJ", [89, 97]], ["podborov\u00e1ci", "podborov\u00e1k", "NOUN", [98, 109]], ["s", "s", "ADP", [110, 111]], ["hn\u011bd\u00fdmi", "hn\u011bd\u00fd", "ADJ", [112, 119]], ["klobou\u010dky", "klobou\u010dek", "NOUN", [120, 129]], [".", ".", "PUNCT", [129, 130]]]], ["calgarske-listy_2003_unor_ocr.txt", "Pod t\u00edmto borov\u00fdm lesem pak pokra\u010dovala paseka.", [["Pod", "pod", "ADP", [0, 3]], ["t\u00edmto", "tento", "DET", [4, 9]], ["borov\u00fdm", "borov\u00fd", "ADJ", [10, 17]], ["lesem", "les", "NOUN", [18, 23]], ["pak", "pak", "ADV", [24, 27]], ["pokra\u010dovala", "pokra\u010dovat", "VERB", [28, 39]], ["paseka", "paseka", "NOUN", [40, 46]], [".", ".", "PUNCT", [46, 47]]]], ["calgarske-listy_2003_unor_ocr.txt", "Zde na okraji lesa jsem obdivoval do \u010dervena zbarven\u00e9 brusinky, kter\u00e9 zde rostly v m\u011bkk\u00e9m jasn\u011b zelen\u00e9m mechu.", [["Zde", "zde", "ADV", [0, 3]], ["na", "na", "ADP", [4, 6]], ["okraji", "okraj", "NOUN", [7, 13]], ["lesa", "les", "NOUN", [14, 18]], ["jsem", "b\u00fdt", "AUX", [19, 23]], ["obdivoval", "obdivovat", "VERB", [24, 33]], ["do", "do", "ADP", [34, 36]], ["\u010dervena", "\u010derven", "NOUN", [37, 44]], ["zbarven\u00e9", "zbarven\u00fd", "ADJ", [45, 53]], ["brusinky", "brusinka", "NOUN", [54, 62]], [",", ",", "PUNCT", [62, 63]], ["kter\u00e9", "kter\u00fd", "DET", [64, 69]], ["zde", "zde", "ADV", [70, 73]], ["rostly", "r\u016fst", "VERB", [74, 80]], ["v", "v", "ADP", [81, 82]], ["m\u011bkk\u00e9m", "m\u011bkk\u00fd", "ADJ", [83, 89]], ["jasn\u011b", "jasn\u011b", "ADV", [90, 95]], ["zelen\u00e9m", "zelen\u00fd", "ADJ", [96, 103]], ["mechu", "mech", "NOUN", [104, 109]], [".", ".", "PUNCT", [109, 110]]]], ["calgarske-listy_2003_unor_ocr.txt", "Ten mech m\u011b p\u0159ipom\u00ednal sametov\u00e9 pohovky v babi\u010d\u010din\u011b ob\u00fdv\u00e1ku, na kter\u00e9 jsem m\u011bl zak\u00e1z\u00e1no si i s\u00e1hnout.", [["Ten", "ten", "DET", [0, 3]], ["mech", "mech", "NOUN", [4, 8]], ["m\u011b", "j\u00e1", "PRON", [9, 11]], ["p\u0159ipom\u00ednal", "p\u0159ipom\u00ednat", "VERB", [12, 22]], ["sametov\u00e9", "sametov\u00fd", "ADJ", [23, 31]], ["pohovky", "pohovka", "NOUN", [32, 39]], ["v", "v", "ADP", [40, 41]], ["babi\u010d\u010din\u011b", "babi\u010d\u010dina", "PROPN", [42, 51]], ["ob\u00fdv\u00e1ku", "ob\u00fdv\u00e1k", "NOUN", [52, 59]], [",", ",", "PUNCT", [59, 60]], ["na", "na", "ADP", [61, 63]], ["kter\u00e9", "kter\u00fd", "DET", [64, 69]], ["jsem", "b\u00fdt", "AUX", [70, 74]], ["m\u011bl", "m\u00edt", "VERB", [75, 78]], ["zak\u00e1z\u00e1no", "zak\u00e1zan\u00fd", "ADJ", [79, 87]], ["si", "se", "PRON", [88, 90]], ["i", "i", "CCONJ", [91, 92]], ["s\u00e1hnout", "s\u00e1hnout", "VERB", [93, 100]], [".", ".", "PUNCT", [100, 101]]]], ["calgarske-listy_2003_unor_ocr.txt", "Zde v lese jsem se tedy na mech mohl polo\u017eit a i jen na chvilku se d\u00edvat do pluj\u00edc\u00edch mrak\u016f \u010di modr\u00e9 oblohy.", [["Zde", "zde", "ADV", [0, 3]], ["v", "v", "ADP", [4, 5]], ["lese", "les", "NOUN", [6, 10]], ["jsem", "b\u00fdt", "AUX", [11, 15]], ["se", "se", "PRON", [16, 18]], ["tedy", "tedy", "CCONJ", [19, 23]], ["na", "na", "ADP", [24, 26]], ["mech", "mech", "NOUN", [27, 31]], ["mohl", "moci", "VERB", [32, 36]], ["polo\u017eit", "polo\u017eit", "VERB", [37, 44]], ["a", "a", "CCONJ", [45, 46]], ["i", "i", "CCONJ", [47, 48]], ["jen", "jen", "PART", [49, 52]], ["na", "na", "ADP", [53, 55]], ["chvilku", "chvilka", "NOUN", [56, 63]], ["se", "se", "PRON", [64, 66]], ["d\u00edvat", "d\u00edvat", "VERB", [67, 72]], ["do", "do", "ADP", [73, 75]], ["pluj\u00edc\u00edch", "pluj\u00edc\u00ed", "ADJ", [76, 85]], ["mrak\u016f", "mrak", "NOUN", [86, 91]], ["\u010di", "\u010di", "CCONJ", [92, 94]], ["modr\u00e9", "modr\u00fd", "ADJ", [95, 100]], ["oblohy", "obloha", "NOUN", [101, 107]], [".", ".", "PUNCT", [107, 108]]]], ["calgarske-listy_2003_unor_ocr.txt", "Pak u\u017e se jen p\u0159e\u0161lo na na\u0161i louku, kde d\u011bda nechal nas\u00e1zet n\u00e1dhern\u00e9 vysok\u00e9 b\u0159\u00edzy s b\u00edlou k\u016frou a tady jako na z\u00e1v\u011br na\u0161\u00ed loveck\u00e9 le\u010de se sebralo n\u011bkolik koz\u00e1k\u016f.", [["Pak", "pak", "ADV", [0, 3]], ["u\u017e", "u\u017e", "ADV", [4, 6]], ["se", "se", "PRON", [7, 9]], ["jen", "jen", "PART", [10, 13]], ["p\u0159e\u0161lo", "p\u0159ej\u00edt", "VERB", [14, 20]], ["na", "na", "ADP", [21, 23]], ["na\u0161i", "n\u00e1\u0161", "DET", [24, 28]], ["louku", "louka", "NOUN", [29, 34]], [",", ",", "PUNCT", [34, 35]], ["kde", "kde", "ADV", [36, 39]], ["d\u011bda", "d\u011bda", "NOUN", [40, 44]], ["nechal", "nechat", "VERB", [45, 51]], ["nas\u00e1zet", "nas\u00e1zet", "VERB", [52, 59]], ["n\u00e1dhern\u00e9", "n\u00e1dhern\u00fd", "ADJ", [60, 68]], ["vysok\u00e9", "vysok\u00fd", "ADJ", [69, 75]], ["b\u0159\u00edzy", "b\u0159\u00edza", "NOUN", [76, 81]], ["s", "s", "ADP", [82, 83]], ["b\u00edlou", "b\u00edl\u00fd", "ADJ", [84, 89]], ["k\u016frou", "k\u016fra", "NOUN", [90, 95]], ["a", "a", "CCONJ", [96, 97]], ["tady", "tady", "ADV", [98, 102]], ["jako", "jako", "SCONJ", [103, 107]], ["na", "na", "ADP", [108, 110]], ["z\u00e1v\u011br", "z\u00e1v\u011br", "NOUN", [111, 116]], ["na\u0161\u00ed", "n\u00e1\u0161", "DET", [117, 121]], ["loveck\u00e9", "loveck\u00fd", "ADJ", [122, 129]], ["le\u010de", "le\u010d", "NOUN", [130, 134]], ["se", "se", "PRON", [135, 137]], ["sebralo", "sebrat", "VERB", [138, 145]], ["n\u011bkolik", "n\u011bkolik", "DET", [146, 153]], ["koz\u00e1k\u016f", "koz\u00e1k", "NOUN", [154, 160]], [".", ".", "PUNCT", [160, 161]]]], ["calgarske-listy_2003_unor_ocr.txt", "M\u011bli bu\u010f hn\u011bd\u00e9 \u010di oran\u017eov\u00e9 hlavy.", [["M\u011bli", "m\u00edt", "VERB", [0, 4]], ["bu\u010f", "bu\u010f", "CCONJ", [5, 8]], ["hn\u011bd\u00e9", "hn\u011bd\u00fd", "ADJ", [9, 14]], ["\u010di", "\u010di", "CCONJ", [15, 17]], ["oran\u017eov\u00e9", "oran\u017eov\u00fd", "ADJ", [18, 26]], ["hlavy", "hlava", "NOUN", [27, 32]], [".", ".", "PUNCT", [32, 33]]]], ["calgarske-listy_2003_unor_ocr.txt", "To u\u017e bylo jen asi 100 metr\u016f od na\u0161eho domu.", [["To", "ten", "DET", [0, 2]], ["u\u017e", "u\u017e", "ADV", [3, 5]], ["bylo", "b\u00fdt", "AUX", [6, 10]], ["jen", "jen", "ADV", [11, 14]], ["asi", "asi", "PART", [15, 18]], ["100", "100", "NUM", [19, 22]], ["metr\u016f", "metr", "NOUN", [23, 28]], ["od", "od", "ADP", [29, 31]], ["na\u0161eho", "n\u00e1\u0161", "DET", [32, 38]], ["domu", "d\u016fm", "NOUN", [39, 43]], [".", ".", "PUNCT", [43, 44]]]], ["calgarske-listy_2003_unor_ocr.txt", "Kdy\u017e babi\u010dka va\u0159ila bramborovou pol\u00e9vku, tak jen \u0159ekla, Mirku sko\u010d na Bob\u00edcku pro p\u00e1r koz\u00e1k\u016f.", [["Kdy\u017e", "kdy\u017e", "SCONJ", [0, 4]], ["babi\u010dka", "babi\u010dka", "NOUN", [5, 12]], ["va\u0159ila", "va\u0159it", "VERB", [13, 19]], ["bramborovou", "bramborov\u00fd", "ADJ", [20, 31]], ["pol\u00e9vku", "pol\u00e9vka", "NOUN", [32, 39]], [",", ",", "PUNCT", [39, 40]], ["tak", "tak", "ADV", [41, 44]], ["jen", "jen", "ADV", [45, 48]], ["\u0159ekla", "\u0159\u00edci", "VERB", [49, 54]], [",", ",", "PUNCT", [54, 55]], ["Mirku", "Mirk", "PROPN", [56, 61]], ["sko\u010d", "sko\u010dit", "VERB", [62, 66]], ["na", "na", "ADP", [67, 69]], ["Bob\u00edcku", "Bob\u00edcko", "PROPN", [70, 77]], ["pro", "pro", "ADP", [78, 81]], ["p\u00e1r", "p\u00e1r", "DET", [82, 85]], ["koz\u00e1k\u016f", "koz\u00e1k", "NOUN", [86, 92]], [".", ".", "PUNCT", [92, 93]]]], ["calgarske-listy_2003_unor_ocr.txt", "Tam v hust\u00e9 tr\u00e1v\u011b jsem je v\u017edy velmi snadno na\u0161el.", [["Tam", "tam", "ADV", [0, 3]], ["v", "v", "ADP", [4, 5]], ["hust\u00e9", "hust\u00fd", "ADJ", [6, 11]], ["tr\u00e1v\u011b", "tr\u00e1va", "NOUN", [12, 17]], ["jsem", "b\u00fdt", "AUX", [18, 22]], ["je", "on", "PRON", [23, 25]], ["v\u017edy", "v\u017edy", "ADV", [26, 30]], ["velmi", "velmi", "ADV", [31, 36]], ["snadno", "snadno", "ADV", [37, 43]], ["na\u0161el", "naj\u00edt", "VERB", [44, 49]], [".", ".", "PUNCT", [49, 50]]]], ["calgarske-listy_2003_unor_ocr.txt", "Po n\u00e1vratu z hub jsme byli velmi hladov\u00ed a tak byla nejd\u0159\u00edve sva\u010dinka, a pak nastala ta m\u00e9n\u011b zaj\u00edmav\u00e1 f\u00e1ze houba\u0159en\u00ed.", [["Po", "po", "ADP", [0, 2]], ["n\u00e1vratu", "n\u00e1vrat", "NOUN", [3, 10]], ["z", "z", "ADP", [11, 12]], ["hub", "houba", "NOUN", [13, 16]], ["jsme", "b\u00fdt", "AUX", [17, 21]], ["byli", "b\u00fdt", "AUX", [22, 26]], ["velmi", "velmi", "ADV", [27, 32]], ["hladov\u00ed", "hladov\u00fd", "ADJ", [33, 40]], ["a", "a", "CCONJ", [41, 42]], ["tak", "tak", "ADV", [43, 46]], ["byla", "b\u00fdt", "AUX", [47, 51]], ["nejd\u0159\u00edve", "d\u0159\u00edve", "ADV", [52, 60]], ["sva\u010dinka", "sva\u010dinka", "NOUN", [61, 69]], [",", ",", "PUNCT", [69, 70]], ["a", "a", "CCONJ", [71, 72]], ["pak", "pak", "ADV", [73, 76]], ["nastala", "nastat", "VERB", [77, 84]], ["ta", "ten", "DET", [85, 87]], ["m\u00e9n\u011b", "m\u00e9n\u011b", "ADV", [88, 92]], ["zaj\u00edmav\u00e1", "zaj\u00edmav\u00fd", "ADJ", [93, 101]], ["f\u00e1ze", "f\u00e1ze", "NOUN", [102, 106]], ["houba\u0159en\u00ed", "houba\u0159en\u00ed", "NOUN", [107, 116]], [".", ".", "PUNCT", [116, 117]]]], ["calgarske-listy_2003_unor_ocr.txt", "P\u011bkn\u011b ka\u017edou houbu o\u010distit a pokr\u00e1jet bu\u010f na sma\u017eenici \u010di pro su\u0161en\u00ed na zimu.", [["P\u011bkn\u011b", "p\u011bkn\u011b", "ADV", [0, 5]], ["ka\u017edou", "ka\u017ed\u00fd", "DET", [6, 12]], ["houbu", "houba", "NOUN", [13, 18]], ["o\u010distit", "o\u010distit", "VERB", [19, 26]], ["a", "a", "CCONJ", [27, 28]], ["pokr\u00e1jet", "pokr\u00e1jet", "VERB", [29, 37]], ["bu\u010f", "bu\u010f", "CCONJ", [38, 41]], ["na", "na", "ADP", [42, 44]], ["sma\u017eenici", "sma\u017eenice", "NOUN", [45, 54]], ["\u010di", "\u010di", "CCONJ", [55, 57]], ["pro", "pro", "ADP", [58, 61]], ["su\u0161en\u00ed", "su\u0161en\u00ed", "NOUN", [62, 68]], ["na", "na", "ADP", [69, 71]], ["zimu", "zima", "NOUN", [72, 76]], [".", ".", "PUNCT", [76, 77]]]], ["calgarske-listy_2003_unor_ocr.txt", "K su\u0161en\u00ed se pou\u017e\u00edvala velik\u00e1 kulat\u00e1 \u0159e\u0161eta, kdysi slou\u017e\u00edc\u00ed pro pros\u00edv\u00e1n\u00ed obil\u00ed.", [["K", "k", "ADP", [0, 1]], ["su\u0161en\u00ed", "su\u0161en\u00ed", "NOUN", [2, 8]], ["se", "se", "PRON", [9, 11]], ["pou\u017e\u00edvala", "pou\u017e\u00edvat", "VERB", [12, 21]], ["velik\u00e1", "velik\u00fd", "ADJ", [22, 28]], ["kulat\u00e1", "kulat\u00fd", "ADJ", [29, 35]], ["\u0159e\u0161eta", "\u0159e\u0161e\u0165", "NOUN", [36, 42]], [",", ",", "PUNCT", [42, 43]], ["kdysi", "kdysi", "ADV", [44, 49]], ["slou\u017e\u00edc\u00ed", "slou\u017e\u00edc\u00ed", "ADJ", [50, 58]], ["pro", "pro", "ADP", [59, 62]], ["pros\u00edv\u00e1n\u00ed", "pros\u00edv\u00e1n\u00ed", "NOUN", [63, 72]], ["obil\u00ed", "obil\u00ed", "NOUN", [73, 78]], [".", ".", "PUNCT", [78, 79]]]], ["calgarske-listy_2003_unor_ocr.txt", "Na s\u00ed\u0165ovou plochu se polo\u017eil balic\u00ed pap\u00edr, a na tenk\u00e9 pl\u00e1tky pokr\u00e1jen\u00e9 houby se tam rozlo\u017eily.", [["Na", "na", "ADP", [0, 2]], ["s\u00ed\u0165ovou", "s\u00ed\u0165ov\u00fd", "ADJ", [3, 10]], ["plochu", "plocha", "NOUN", [11, 17]], ["se", "se", "PRON", [18, 20]], ["polo\u017eil", "polo\u017eit", "VERB", [21, 28]], ["balic\u00ed", "balic\u00ed", "ADJ", [29, 35]], ["pap\u00edr", "pap\u00edr", "NOUN", [36, 41]], [",", ",", "PUNCT", [41, 42]], ["a", "a", "CCONJ", [43, 44]], ["na", "na", "ADP", [45, 47]], ["tenk\u00e9", "tenk\u00fd", "ADJ", [48, 53]], ["pl\u00e1tky", "pl\u00e1tek", "NOUN", [54, 60]], ["pokr\u00e1jen\u00e9", "pokr\u00e1jen\u00fd", "ADJ", [61, 70]], ["houby", "houba", "NOUN", [71, 76]], ["se", "se", "PRON", [77, 79]], ["tam", "tam", "ADV", [80, 83]], ["rozlo\u017eily", "rozlo\u017eit", "VERB", [84, 93]], [".", ".", "PUNCT", [93, 94]]]], ["calgarske-listy_2003_unor_ocr.txt", "M\u011bli jsme kryt\u00e9 z\u00e1pra\u017e\u00ed a tam se pak \u0159e\u0161eta p\u011bkn\u011b ulo\u017eila ke su\u0161en\u00ed.", [["M\u011bli", "m\u00edt", "VERB", [0, 4]], ["jsme", "b\u00fdt", "AUX", [5, 9]], ["kryt\u00e9", "kryt\u00fd", "ADJ", [10, 15]], ["z\u00e1pra\u017e\u00ed", "z\u00e1pra\u017e\u00ed", "NOUN", [16, 23]], ["a", "a", "CCONJ", [24, 25]], ["tam", "tam", "ADV", [26, 29]], ["se", "se", "PRON", [30, 32]], ["pak", "pak", "ADV", [33, 36]], ["\u0159e\u0161eta", "\u0159e\u0161e\u0165", "NOUN", [37, 43]], ["p\u011bkn\u011b", "p\u011bkn\u011b", "ADV", [44, 49]], ["ulo\u017eila", "ulo\u017eit", "VERB", [50, 57]], ["ke", "k", "ADP", [58, 60]], ["su\u0161en\u00ed", "su\u0161en\u00ed", "NOUN", [61, 67]], [".", ".", "PUNCT", [67, 68]]]], ["calgarske-listy_2003_unor_ocr.txt", "Dal\u0161\u00ed den pak uschl\u00e9 houby se d\u00e1valy do v\u011bt\u0161\u00edch pap\u00edrov\u00fdch pytl\u00edk\u016f pro ulo\u017een\u00ed v suchu.", [["Dal\u0161\u00ed", "dal\u0161\u00ed", "ADJ", [0, 5]], ["den", "den", "NOUN", [6, 9]], ["pak", "pak", "ADV", [10, 13]], ["uschl\u00e9", "uschl\u00fd", "ADJ", [14, 20]], ["houby", "houba", "NOUN", [21, 26]], ["se", "se", "PRON", [27, 29]], ["d\u00e1valy", "d\u00e1vat", "VERB", [30, 36]], ["do", "do", "ADP", [37, 39]], ["v\u011bt\u0161\u00edch", "velk\u00fd", "ADJ", [40, 47]], ["pap\u00edrov\u00fdch", "pap\u00edrov\u00fd", "ADJ", [48, 58]], ["pytl\u00edk\u016f", "pytl\u00edk", "NOUN", [59, 66]], ["pro", "pro", "ADP", [67, 70]], ["ulo\u017een\u00ed", "ulo\u017een\u00ed", "NOUN", [71, 78]], ["v", "v", "ADP", [79, 80]], ["suchu", "sucho", "NOUN", [81, 86]], [".", ".", "PUNCT", [86, 87]]]], ["calgarske-listy_2003_unor_ocr.txt", "Ta v\u016fn\u011b su\u0161en\u00fdch hub byla mnohdy a\u017e omamn\u00e1.", [["Ta", "ten", "DET", [0, 2]], ["v\u016fn\u011b", "v\u016fn\u011b", "NOUN", [3, 7]], ["su\u0161en\u00fdch", "su\u0161en\u00fd", "ADJ", [8, 16]], ["hub", "houba", "NOUN", [17, 20]], ["byla", "b\u00fdt", "AUX", [21, 25]], ["mnohdy", "mnohdy", "ADV", [26, 32]], ["a\u017e", "a\u017e", "PART", [33, 35]], ["omamn\u00e1", "omamn\u00fd", "ADJ", [36, 42]], [".", ".", "PUNCT", [42, 43]]]], ["calgarske-listy_2003_unor_ocr.txt", "Sma\u017eenice s trochou vaj\u00ed\u010dek byla tak\u00e9 ohromn\u00e1 pochoutka.", [["Sma\u017eenice", "sma\u017eenice", "NOUN", [0, 9]], ["s", "s", "ADP", [10, 11]], ["trochou", "trocha", "NOUN", [12, 19]], ["vaj\u00ed\u010dek", "vaj\u00ed\u010dko", "NOUN", [20, 27]], ["byla", "b\u00fdt", "AUX", [28, 32]], ["tak\u00e9", "tak\u00e9", "ADV", [33, 37]], ["ohromn\u00e1", "ohromn\u00fd", "ADJ", [38, 45]], ["pochoutka", "pochoutka", "NOUN", [46, 55]], [".", ".", "PUNCT", [55, 56]]]], ["calgarske-listy_2003_unor_ocr.txt", "J\u00e1 si pamatuji, \u017ee ta vaj\u00ed\u010dka u babi\u010dky m\u011bla n\u00e1dhern\u011b oran\u017eov\u00fd \u017eloutek.", [["J\u00e1", "j\u00e1", "PRON", [0, 2]], ["si", "se", "PRON", [3, 5]], ["pamatuji", "pamatovat", "VERB", [6, 14]], [",", ",", "PUNCT", [14, 15]], ["\u017ee", "\u017ee", "SCONJ", [16, 18]], ["ta", "ten", "DET", [19, 21]], ["vaj\u00ed\u010dka", "vaj\u00ed\u010dko", "NOUN", [22, 29]], ["u", "u", "ADP", [30, 31]], ["babi\u010dky", "babi\u010dka", "NOUN", [32, 39]], ["m\u011bla", "m\u00edt", "VERB", [40, 44]], ["n\u00e1dhern\u011b", "n\u00e1dhern\u011b", "ADV", [45, 53]], ["oran\u017eov\u00fd", "oran\u017eov\u00fd", "ADJ", [54, 62]], ["\u017eloutek", "\u017eloutek", "NOUN", [63, 70]], [".", ".", "PUNCT", [70, 71]]]], ["calgarske-listy_2003_unor_ocr.txt", "Babi\u010dka sma\u017eila houby na s\u00e1dle, tak i ta sma\u017eenice chutnala \u00fapln\u011b jinak, ne\u017e kdy\u017e je dnes d\u011bl\u00e1me na oleji.", [["Babi\u010dka", "babi\u010dka", "NOUN", [0, 7]], ["sma\u017eila", "sma\u017eit", "VERB", [8, 15]], ["houby", "houba", "NOUN", [16, 21]], ["na", "na", "ADP", [22, 24]], ["s\u00e1dle", "s\u00e1dlo", "NOUN", [25, 30]], [",", ",", "PUNCT", [30, 31]], ["tak", "tak", "ADV", [32, 35]], ["i", "i", "CCONJ", [36, 37]], ["ta", "ten", "DET", [38, 40]], ["sma\u017eenice", "sma\u017eenice", "NOUN", [41, 50]], ["chutnala", "chutnat", "VERB", [51, 59]], ["\u00fapln\u011b", "\u00fapln\u011b", "ADV", [60, 65]], ["jinak", "jinak", "ADV", [66, 71]], [",", ",", "PUNCT", [71, 72]], ["ne\u017e", "ne\u017e", "SCONJ", [73, 76]], ["kdy\u017e", "kdy\u017e", "SCONJ", [77, 81]], ["je", "on", "PRON", [82, 84]], ["dnes", "dnes", "ADV", [85, 89]], ["d\u011bl\u00e1me", "d\u011blat", "VERB", [90, 96]], ["na", "na", "ADP", [97, 99]], ["oleji", "olej", "NOUN", [100, 105]], [".", ".", "PUNCT", [105, 106]]]], ["calgarske-listy_2003_unor_ocr.txt", "Jednoho dne v parn\u00e9m l\u00e9t\u011b se konala velik\u00e1 v\u00fdprava na sb\u011br malin do lesa zvan\u00fd Radov.", [["Jednoho", "jeden", "NUM", [0, 7]], ["dne", "den", "NOUN", [8, 11]], ["v", "v", "ADP", [12, 13]], ["parn\u00e9m", "parn\u00fd", "ADJ", [14, 20]], ["l\u00e9t\u011b", "l\u00e9to", "NOUN", [21, 25]], ["se", "se", "PRON", [26, 28]], ["konala", "konat", "VERB", [29, 35]], ["velik\u00e1", "velik\u00fd", "ADJ", [36, 42]], ["v\u00fdprava", "v\u00fdprava", "NOUN", [43, 50]], ["na", "na", "ADP", [51, 53]], ["sb\u011br", "sb\u011br", "NOUN", [54, 58]], ["malin", "malina", "NOUN", [59, 64]], ["do", "do", "ADP", [65, 67]], ["lesa", "les", "NOUN", [68, 72]], ["zvan\u00fd", "zvan\u00fd", "ADJ", [73, 78]], ["Radov", "Radov", "PROPN", [79, 84]], [".", ".", "PUNCT", [84, 85]]]], ["calgarske-listy_2003_unor_ocr.txt", "Hust\u00e9 malinov\u00e9 ke\u0159e byly cel\u00e9 obsypan\u00e9 \u010derven\u00fdmi malinami.", [["Hust\u00e9", "hust\u00fd", "ADJ", [0, 5]], ["malinov\u00e9", "malinov\u00fd", "ADJ", [6, 14]], ["ke\u0159e", "ke\u0159", "NOUN", [15, 19]], ["byly", "b\u00fdt", "AUX", [20, 24]], ["cel\u00e9", "cel\u00fd", "ADJ", [25, 29]], ["obsypan\u00e9", "obsypan\u00fd", "ADJ", [30, 38]], ["\u010derven\u00fdmi", "\u010derven\u00fd", "ADJ", [39, 48]], ["malinami", "malina", "NOUN", [49, 57]], [".", ".", "PUNCT", [57, 58]]]], ["calgarske-listy_2003_unor_ocr.txt", "Nejv\u011bt\u0161\u00ed ke\u0159e rostly pr\u00e1v\u011b tam, kde byla lesn\u00ed p\u016fda po\u0161kozena p\u0159i tah\u00e1n\u00ed osekan\u00fdch kl\u00e1d z lesa ven pomoc\u00ed velk\u00fdch kon\u00ed.", [["Nejv\u011bt\u0161\u00ed", "velk\u00fd", "ADJ", [0, 8]], ["ke\u0159e", "ke\u0159", "NOUN", [9, 13]], ["rostly", "r\u016fst", "VERB", [14, 20]], ["pr\u00e1v\u011b", "pr\u00e1v\u011b", "PART", [21, 26]], ["tam", "tam", "ADV", [27, 30]], [",", ",", "PUNCT", [30, 31]], ["kde", "kde", "ADV", [32, 35]], ["byla", "b\u00fdt", "AUX", [36, 40]], ["lesn\u00ed", "lesn\u00ed", "ADJ", [41, 46]], ["p\u016fda", "p\u016fda", "NOUN", [47, 51]], ["po\u0161kozena", "po\u0161kozen\u00fd", "ADJ", [52, 61]], ["p\u0159i", "p\u0159i", "ADP", [62, 65]], ["tah\u00e1n\u00ed", "tah\u00e1n\u00ed", "NOUN", [66, 72]], ["osekan\u00fdch", "osekan\u00fd", "ADJ", [73, 82]], ["kl\u00e1d", "kl\u00e1d", "NOUN", [83, 87]], ["z", "z", "ADP", [88, 89]], ["lesa", "les", "NOUN", [90, 94]], ["ven", "ven", "ADV", [95, 98]], ["pomoc\u00ed", "pomoc\u00ed", "ADP", [99, 105]], ["velk\u00fdch", "velk\u00fd", "ADJ", [106, 113]], ["kon\u00ed", "k\u016f\u0148", "NOUN", [114, 118]], [".", ".", "PUNCT", [118, 119]]]], ["calgarske-listy_2003_unor_ocr.txt", "Tehd\u00e1 se \u017e\u00e1dn\u00e9 traktory a housenkov\u00e9 ma\u0161iny nepou\u017e\u00edvaly a vyk\u00e1cen\u00fd les vypadal jako park.", [["Tehd\u00e1", "tehdat", "VERB", [0, 5]], ["se", "se", "PRON", [6, 8]], ["\u017e\u00e1dn\u00e9", "\u017e\u00e1dn\u00fd", "DET", [9, 14]], ["traktory", "traktor", "NOUN", [15, 23]], ["a", "a", "CCONJ", [24, 25]], ["housenkov\u00e9", "housenkov\u00fd", "ADJ", [26, 36]], ["ma\u0161iny", "ma\u0161ina", "NOUN", [37, 43]], ["nepou\u017e\u00edvaly", "pou\u017e\u00edvat", "VERB", [44, 55]], ["a", "a", "CCONJ", [56, 57]], ["vyk\u00e1cen\u00fd", "vyk\u00e1cen\u00fd", "ADJ", [58, 66]], ["les", "les", "NOUN", [67, 70]], ["vypadal", "vypadat", "VERB", [71, 78]], ["jako", "jako", "SCONJ", [79, 83]], ["park", "park", "NOUN", [84, 88]], [".", ".", "PUNCT", [88, 89]]]], ["calgarske-listy_2003_unor_ocr.txt", "Tady v Kanad\u011b to po k\u00e1cen\u00ed lesa vypad\u00e1 jako po ekologick\u00e9 katastrof\u011b.", [["Tady", "tady", "ADV", [0, 4]], ["v", "v", "ADP", [5, 6]], ["Kanad\u011b", "Kanada", "PROPN", [7, 13]], ["to", "ten", "DET", [14, 16]], ["po", "po", "ADP", [17, 19]], ["k\u00e1cen\u00ed", "k\u00e1cen\u00ed", "NOUN", [20, 26]], ["lesa", "les", "NOUN", [27, 31]], ["vypad\u00e1", "vypadat", "VERB", [32, 38]], ["jako", "jako", "SCONJ", [39, 43]], ["po", "po", "ADP", [44, 46]], ["ekologick\u00e9", "ekologick\u00fd", "ADJ", [47, 57]], ["katastrof\u011b", "katastrofa", "NOUN", [58, 68]], [".", ".", "PUNCT", [68, 69]]]], ["calgarske-listy_2003_unor_ocr.txt", "Dom\u016f z lesa n\u00e1s dost unaven\u00e9, vezl p\u00e1r velk\u00fdch volk\u016f.", [["Dom\u016f", "dom\u016f", "ADV", [0, 4]], ["z", "z", "ADP", [5, 6]], ["lesa", "les", "NOUN", [7, 11]], ["n\u00e1s", "my", "PRON", [12, 15]], ["dost", "dost", "ADV", [16, 20]], ["unaven\u00e9", "unaven\u00fd", "ADJ", [21, 28]], [",", ",", "PUNCT", [28, 29]], ["vezl", "v\u00e9zt", "VERB", [30, 34]], ["p\u00e1r", "p\u00e1r", "DET", [35, 38]], ["velk\u00fdch", "velk\u00fd", "ADJ", [39, 46]], ["volk\u016f", "volky", "NOUN", [47, 52]], [".", ".", "PUNCT", [52, 53]]]], ["calgarske-listy_2003_unor_ocr.txt", "Babi\u010dka asi najala na pomoc n\u011bjak\u00e9 \u010des\u00e1\u010de a tak jsme vezli 12 v\u011bder pln\u00fdch malin.", [["Babi\u010dka", "babi\u010dka", "NOUN", [0, 7]], ["asi", "asi", "PART", [8, 11]], ["najala", "najmout", "VERB", [12, 18]], ["na", "na", "ADP", [19, 21]], ["pomoc", "pomoc", "NOUN", [22, 27]], ["n\u011bjak\u00e9", "n\u011bjak\u00fd", "DET", [28, 34]], ["\u010des\u00e1\u010de", "\u010des\u00e1\u010d", "NOUN", [35, 41]], ["a", "a", "CCONJ", [42, 43]], ["tak", "tak", "ADV", [44, 47]], ["jsme", "b\u00fdt", "AUX", [48, 52]], ["vezli", "v\u00e9zt", "VERB", [53, 58]], ["12", "12", "NUM", [59, 61]], ["v\u011bder", "v\u011bdero", "NOUN", [62, 67]], ["pln\u00fdch", "pln\u00fd", "ADJ", [68, 74]], ["malin", "malina", "NOUN", [75, 80]], [".", ".", "PUNCT", [80, 81]]]], ["calgarske-listy_2003_unor_ocr.txt", "Na druh\u00fd den se doma maliny rozma\u010dkaly a pomoc\u00ed v\u011bt\u0161\u00edch pl\u00e1t\u011bn\u00fdch pytl\u00edk\u016f se \u0161t\u00e1va cedila.", [["Na", "na", "ADP", [0, 2]], ["druh\u00fd", "druh\u00fd", "ADJ", [3, 8]], ["den", "den", "NOUN", [9, 12]], ["se", "se", "PRON", [13, 15]], ["doma", "doma", "ADV", [16, 20]], ["maliny", "malina", "NOUN", [21, 27]], ["rozma\u010dkaly", "rozma\u010dkat", "VERB", [28, 38]], ["a", "a", "CCONJ", [39, 40]], ["pomoc\u00ed", "pomoc\u00ed", "ADP", [41, 47]], ["v\u011bt\u0161\u00edch", "velk\u00fd", "ADJ", [48, 55]], ["pl\u00e1t\u011bn\u00fdch", "pl\u00e1t\u011bn\u00fd", "ADJ", [56, 65]], ["pytl\u00edk\u016f", "pytl\u00edk", "NOUN", [66, 73]], ["se", "se", "PRON", [74, 76]], ["\u0161t\u00e1va", "\u0161t\u00e1vo", "NOUN", [77, 82]], ["cedila", "cedit", "VERB", [83, 89]], [".", ".", "PUNCT", [89, 90]]]], ["calgarske-listy_2003_unor_ocr.txt", "Po n\u011bkolika dnech se pak je\u0161t\u011b pomoc\u00ed speci\u00e1ln\u00edch \u017e\u00edn\u011bn\u00fdch s\u00edt zbytek propas\u00edroval.", [["Po", "po", "ADP", [0, 2]], ["n\u011bkolika", "n\u011bkolik", "DET", [3, 11]], ["dnech", "den", "NOUN", [12, 17]], ["se", "se", "PRON", [18, 20]], ["pak", "pak", "ADV", [21, 24]], ["je\u0161t\u011b", "je\u0161t\u011b", "ADV", [25, 30]], ["pomoc\u00ed", "pomoc\u00ed", "ADP", [31, 37]], ["speci\u00e1ln\u00edch", "speci\u00e1ln\u00ed", "ADJ", [38, 49]], ["\u017e\u00edn\u011bn\u00fdch", "\u017e\u00edn\u011bn\u00fd", "ADJ", [50, 58]], ["s\u00edt", "s\u00edt", "NOUN", [59, 62]], ["zbytek", "zbytek", "NOUN", [63, 69]], ["propas\u00edroval", "propas\u00edrovat", "VERB", [70, 82]], [".", ".", "PUNCT", [82, 83]]]], ["calgarske-listy_2003_unor_ocr.txt", "\u0160t\u00e1va se na plotn\u011b odpa\u0159ovala na velik\u00fdch ploch\u00fdch smaltovan\u00fdch pek\u00e1\u010d\u00edch a pak sv\u00e1\u0159ela s cukrem.", [["\u0160t\u00e1va", "\u0161t\u00e1va", "NOUN", [0, 5]], ["se", "se", "PRON", [6, 8]], ["na", "na", "ADP", [9, 11]], ["plotn\u011b", "plotna", "NOUN", [12, 18]], ["odpa\u0159ovala", "odpa\u0159ovat", "VERB", [19, 29]], ["na", "na", "ADP", [30, 32]], ["velik\u00fdch", "velik\u00fd", "ADJ", [33, 41]], ["ploch\u00fdch", "ploch\u00fd", "ADJ", [42, 50]], ["smaltovan\u00fdch", "smaltovan\u00fd", "ADJ", [51, 63]], ["pek\u00e1\u010d\u00edch", "pek\u00e1\u010d", "NOUN", [64, 72]], ["a", "a", "CCONJ", [73, 74]], ["pak", "pak", "ADV", [75, 78]], ["sv\u00e1\u0159ela", "sv\u00e1\u0159et", "VERB", [79, 86]], ["s", "s", "ADP", [87, 88]], ["cukrem", "cukr", "NOUN", [89, 95]], [".", ".", "PUNCT", [95, 96]]]], ["calgarske-listy_2003_unor_ocr.txt", "V zim\u011b se pak p\u0159id\u00e1vala do \u010daje a jedli se k tomu v\u00e1no\u010dky \u010di mazance.", [["V", "v", "ADP", [0, 1]], ["zim\u011b", "zima", "NOUN", [2, 6]], ["se", "se", "PRON", [7, 9]], ["pak", "pak", "ADV", [10, 13]], ["p\u0159id\u00e1vala", "p\u0159id\u00e1vat", "VERB", [14, 23]], ["do", "do", "ADP", [24, 26]], ["\u010daje", "\u010daj", "NOUN", [27, 31]], ["a", "a", "CCONJ", [32, 33]], ["jedli", "j\u00edst", "VERB", [34, 39]], ["se", "se", "PRON", [40, 42]], ["k", "k", "ADP", [43, 44]], ["tomu", "ten", "DET", [45, 49]], ["v\u00e1no\u010dky", "v\u00e1no\u010dek", "NOUN", [50, 57]], ["\u010di", "\u010di", "CCONJ", [58, 60]], ["mazance", "mazance", "NOUN", [61, 68]], [".", ".", "PUNCT", [68, 69]]]], ["calgarske-listy_2003_unor_ocr.txt", "Mus\u00edm se je\u0161t\u011b vr\u00e1tit k tomu p\u00e1ru na\u0161ich volk\u016f.", [["Mus\u00edm", "muset", "VERB", [0, 5]], ["se", "se", "PRON", [6, 8]], ["je\u0161t\u011b", "je\u0161t\u011b", "ADV", [9, 14]], ["vr\u00e1tit", "vr\u00e1tit", "VERB", [15, 21]], ["k", "k", "ADP", [22, 23]], ["tomu", "ten", "DET", [24, 28]], ["p\u00e1ru", "p\u00e1r", "NOUN", [29, 33]], ["na\u0161ich", "n\u00e1\u0161", "DET", [34, 40]], ["volk\u016f", "volky", "NOUN", [41, 46]], [".", ".", "PUNCT", [46, 47]]]], ["calgarske-listy_2003_unor_ocr.txt", "Byla to dv\u011b obrovsk\u00e1 zv\u00ed\u0159ata, ka\u017ed\u00fd v\u00e1\u017eil asi 10 metr\u00e1k\u016f \u010dili jednu tunu.", [["Byla", "b\u00fdt", "AUX", [0, 4]], ["to", "ten", "DET", [5, 7]], ["dv\u011b", "dva", "NUM", [8, 11]], ["obrovsk\u00e1", "obrovsk\u00fd", "ADJ", [12, 20]], ["zv\u00ed\u0159ata", "zv\u00ed\u0159e", "NOUN", [21, 28]], [",", ",", "PUNCT", [28, 29]], ["ka\u017ed\u00fd", "ka\u017ed\u00fd", "DET", [30, 35]], ["v\u00e1\u017eil", "v\u00e1\u017eit", "VERB", [36, 41]], ["asi", "asi", "PART", [42, 45]], ["10", "10", "NUM", [46, 48]], ["metr\u00e1k\u016f", "metr\u00e1k", "NOUN", [49, 56]], ["\u010dili", "\u010dili", "CCONJ", [57, 61]], ["jednu", "jeden", "NUM", [62, 67]], ["tunu", "tuna", "NOUN", [68, 72]], [".", ".", "PUNCT", [72, 73]]]], ["calgarske-listy_2003_unor_ocr.txt", "M\u011bli ohromn\u00e9 rohy a pou\u017e\u00edvali se pro tah\u00e1n\u00ed voz\u016f.", [["M\u011bli", "m\u00edt", "VERB", [0, 4]], ["ohromn\u00e9", "ohromn\u00fd", "ADJ", [5, 12]], ["rohy", "roh", "NOUN", [13, 17]], ["a", "a", "CCONJ", [18, 19]], ["pou\u017e\u00edvali", "pou\u017e\u00edvat", "VERB", [20, 29]], ["se", "se", "PRON", [30, 32]], ["pro", "pro", "ADP", [33, 36]], ["tah\u00e1n\u00ed", "tah\u00e1n\u00ed", "NOUN", [37, 43]], ["voz\u016f", "v\u016fz", "NOUN", [44, 48]], [".", ".", "PUNCT", [48, 49]]]], ["calgarske-listy_2003_unor_ocr.txt", "Pohybovali se zvolna ale ut\u00e1hli velk\u00e9 n\u00e1klady.", [["Pohybovali", "pohybovat", "VERB", [0, 10]], ["se", "se", "PRON", [11, 13]], ["zvolna", "zvolna", "ADV", [14, 20]], ["ale", "ale", "CCONJ", [21, 24]], ["ut\u00e1hli", "ut\u00e1hnout", "VERB", [25, 31]], ["velk\u00e9", "velk\u00fd", "ADJ", [32, 37]], ["n\u00e1klady", "n\u00e1klad", "NOUN", [38, 45]], [".", ".", "PUNCT", [45, 46]]]], ["calgarske-listy_2003_unor_ocr.txt", "V na\u0161em hospod\u00e1\u0159sv\u00ed jsme je pou\u017e\u00edvali i na \u0159ez\u00e1n\u00ed \u0159ezanky \u010di ml\u00e1cen\u00ed obil\u00ed.", [["V", "v", "ADP", [0, 1]], ["na\u0161em", "n\u00e1\u0161", "DET", [2, 7]], ["hospod\u00e1\u0159sv\u00ed", "hospod\u00e1\u0159sv\u00ed", "NOUN", [8, 19]], ["jsme", "b\u00fdt", "AUX", [20, 24]], ["je", "on", "PRON", [25, 27]], ["pou\u017e\u00edvali", "pou\u017e\u00edvat", "VERB", [28, 37]], ["i", "i", "CCONJ", [38, 39]], ["na", "na", "ADP", [40, 42]], ["\u0159ez\u00e1n\u00ed", "\u0159ez\u00e1n\u00ed", "NOUN", [43, 49]], ["\u0159ezanky", "\u0159ezanka", "NOUN", [50, 57]], ["\u010di", "\u010di", "CCONJ", [58, 60]], ["ml\u00e1cen\u00ed", "ml\u00e1cen\u00ed", "NOUN", [61, 68]], ["obil\u00ed", "obil\u00ed", "NOUN", [69, 74]], [".", ".", "PUNCT", [74, 75]]]], ["calgarske-listy_2003_unor_ocr.txt", "To se zap\u0159\u00e1hli k tak zvan\u00e9mu \u017eentouru a tahali za sebou st\u00e1le dokola tr\u00e1mec, kter\u00fd byl sou\u010d\u00e1st\u00ed hnac\u00edho za\u0159\u00edzen\u00ed pro pohon t\u0159eba \u0159eza\u010dky na p\u0159\u00edpravu krmen\u00ed.", [["To", "ten", "DET", [0, 2]], ["se", "se", "PRON", [3, 5]], ["zap\u0159\u00e1hli", "zap\u0159\u00e1hnout", "VERB", [6, 14]], ["k", "k", "ADP", [15, 16]], ["tak", "tak", "ADV", [17, 20]], ["zvan\u00e9mu", "zvan\u00fd", "ADJ", [21, 28]], ["\u017eentouru", "\u017eentour", "NOUN", [29, 37]], ["a", "a", "CCONJ", [38, 39]], ["tahali", "tahat", "VERB", [40, 46]], ["za", "za", "ADP", [47, 49]], ["sebou", "se", "PRON", [50, 55]], ["st\u00e1le", "st\u00e1le", "ADV", [56, 61]], ["dokola", "dokola", "ADV", [62, 68]], ["tr\u00e1mec", "tr\u00e1mec", "NOUN", [69, 75]], [",", ",", "PUNCT", [75, 76]], ["kter\u00fd", "kter\u00fd", "DET", [77, 82]], ["byl", "b\u00fdt", "AUX", [83, 86]], ["sou\u010d\u00e1st\u00ed", "sou\u010d\u00e1st", "NOUN", [87, 95]], ["hnac\u00edho", "hnac\u00ed", "ADJ", [96, 103]], ["za\u0159\u00edzen\u00ed", "za\u0159\u00edzen\u00ed", "NOUN", [104, 112]], ["pro", "pro", "ADP", [113, 116]], ["pohon", "pohon", "NOUN", [117, 122]], ["t\u0159eba", "t\u0159eba", "ADV", [123, 128]], ["\u0159eza\u010dky", "\u0159eza\u010dka", "NOUN", [129, 136]], ["na", "na", "ADP", [137, 139]], ["p\u0159\u00edpravu", "p\u0159\u00edprava", "NOUN", [140, 148]], ["krmen\u00ed", "krmen\u00ed", "NOUN", [149, 155]], [".", ".", "PUNCT", [155, 156]]]], ["calgarske-listy_2003_unor_ocr.txt", "Tento primitivn\u00ed p\u0159\u00edstroj p\u0159ev\u00e1d\u011bl s\u00edlu na\u0161ich volk\u016f na to\u010div\u00fd moment \u0159eza\u010dky.", [["Tento", "tento", "DET", [0, 5]], ["primitivn\u00ed", "primitivn\u00ed", "ADJ", [6, 16]], ["p\u0159\u00edstroj", "p\u0159\u00edstroj", "NOUN", [17, 25]], ["p\u0159ev\u00e1d\u011bl", "p\u0159ev\u00e1d\u011bt", "VERB", [26, 34]], ["s\u00edlu", "s\u00edla", "NOUN", [35, 39]], ["na\u0161ich", "n\u00e1\u0161", "DET", [40, 46]], ["volk\u016f", "volky", "NOUN", [47, 52]], ["na", "na", "ADP", [53, 55]], ["to\u010div\u00fd", "to\u010div\u00fd", "ADJ", [56, 62]], ["moment", "moment", "NOUN", [63, 69]], ["\u0159eza\u010dky", "\u0159eza\u010dka", "NOUN", [70, 77]], [".", ".", "PUNCT", [77, 78]]]], ["calgarske-listy_2003_unor_ocr.txt", "Podobn\u00fd princip se pou\u017e\u00edv\u00e1 i dodnes u ka\u017ed\u00e9ho modern\u00edho automobilu v zadn\u00edm n\u00e1honu, tedy diferenci\u00e1lu na kola.", [["Podobn\u00fd", "podobn\u00fd", "ADJ", [0, 7]], ["princip", "princip", "NOUN", [8, 15]], ["se", "se", "PRON", [16, 18]], ["pou\u017e\u00edv\u00e1", "pou\u017e\u00edvat", "VERB", [19, 26]], ["i", "i", "CCONJ", [27, 28]], ["dodnes", "dodnes", "ADV", [29, 35]], ["u", "u", "ADP", [36, 37]], ["ka\u017ed\u00e9ho", "ka\u017ed\u00fd", "DET", [38, 45]], ["modern\u00edho", "modern\u00ed", "ADJ", [46, 55]], ["automobilu", "automobil", "NOUN", [56, 66]], ["v", "v", "ADP", [67, 68]], ["zadn\u00edm", "zadn\u00ed", "ADJ", [69, 75]], ["n\u00e1honu", "n\u00e1hon", "NOUN", [76, 82]], [",", ",", "PUNCT", [82, 83]], ["tedy", "tedy", "CCONJ", [84, 88]], ["diferenci\u00e1lu", "diferenci\u00e1l", "NOUN", [89, 101]], ["na", "na", "ADP", [102, 104]], ["kola", "kolo", "NOUN", [105, 109]], [".", ".", "PUNCT", [109, 110]]]], ["calgarske-listy_2003_unor_ocr.txt", "U\u017e se mi asi nikdy nepoda\u0159\u00ed zjistit zda tento pohon tam nechal postavit m\u016fj d\u011bda Anton\u00edn \u010di to bylo ji\u017e sou\u010d\u00e1st\u00ed b\u00fdval\u00e9ho z\u00e1jezdn\u00edho hostince.", [["U\u017e", "u\u017e", "ADV", [0, 2]], ["se", "se", "PRON", [3, 5]], ["mi", "j\u00e1", "PRON", [6, 8]], ["asi", "asi", "PART", [9, 12]], ["nikdy", "nikdy", "ADV", [13, 18]], ["nepoda\u0159\u00ed", "poda\u0159it", "VERB", [19, 27]], ["zjistit", "zjistit", "VERB", [28, 35]], ["zda", "zda", "SCONJ", [36, 39]], ["tento", "tento", "DET", [40, 45]], ["pohon", "pohon", "NOUN", [46, 51]], ["tam", "tam", "ADV", [52, 55]], ["nechal", "nechat", "VERB", [56, 62]], ["postavit", "postavit", "VERB", [63, 71]], ["m\u016fj", "m\u016fj", "DET", [72, 75]], ["d\u011bda", "d\u011bda", "NOUN", [76, 80]], ["Anton\u00edn", "Anton\u00edn", "PROPN", [81, 88]], ["\u010di", "\u010di", "CCONJ", [89, 91]], ["to", "ten", "DET", [92, 94]], ["bylo", "b\u00fdt", "AUX", [95, 99]], ["ji\u017e", "ji\u017e", "ADV", [100, 103]], ["sou\u010d\u00e1st\u00ed", "sou\u010d\u00e1st", "NOUN", [104, 112]], ["b\u00fdval\u00e9ho", "b\u00fdval\u00fd", "ADJ", [113, 121]], ["z\u00e1jezdn\u00edho", "z\u00e1jezdn\u00ed", "ADJ", [122, 132]], ["hostince", "hostinec", "NOUN", [133, 141]], [".", ".", "PUNCT", [141, 142]]]], ["calgarske-listy_2003_unor_ocr.txt", "Asi to hostinec pot\u0159eboval pro zna\u010dn\u00e9 mno\u017estv\u00ed krmiva pro kon\u011b, kter\u00e9 tu formani jen vym\u011bnili a hned pokra\u010dovali v j\u00edzd\u011b z V\u00eddn\u011b do Prahy \u010di naopak.", [["Asi", "asi", "PART", [0, 3]], ["to", "ten", "DET", [4, 6]], ["hostinec", "hostinec", "NOUN", [7, 15]], ["pot\u0159eboval", "pot\u0159ebovat", "VERB", [16, 26]], ["pro", "pro", "ADP", [27, 30]], ["zna\u010dn\u00e9", "zna\u010dn\u00fd", "ADJ", [31, 37]], ["mno\u017estv\u00ed", "mno\u017estv\u00ed", "NOUN", [38, 46]], ["krmiva", "krmivo", "NOUN", [47, 53]], ["pro", "pro", "ADP", [54, 57]], ["kon\u011b", "k\u016f\u0148", "NOUN", [58, 62]], [",", ",", "PUNCT", [62, 63]], ["kter\u00e9", "kter\u00fd", "DET", [64, 69]], ["tu", "tu", "ADV", [70, 72]], ["formani", "forman", "NOUN", [73, 80]], ["jen", "jen", "PART", [81, 84]], ["vym\u011bnili", "vym\u011bnit", "VERB", [85, 93]], ["a", "a", "CCONJ", [94, 95]], ["hned", "hned", "ADV", [96, 100]], ["pokra\u010dovali", "pokra\u010dovat", "VERB", [101, 112]], ["v", "v", "ADP", [113, 114]], ["j\u00edzd\u011b", "j\u00edzda", "NOUN", [115, 120]], ["z", "z", "ADP", [121, 122]], ["V\u00eddn\u011b", "V\u00edde\u0148", "PROPN", [123, 128]], ["do", "do", "ADP", [129, 131]], ["Prahy", "Praha", "PROPN", [132, 137]], ["\u010di", "\u010di", "CCONJ", [138, 140]], ["naopak", "naopak", "ADV", [141, 147]], [".", ".", "PUNCT", [147, 148]]]], ["calgarske-listy_2003_unor_ocr.txt", "Je\u0161t\u011b jsem tam tak\u00e9 vid\u011bl pou\u017e\u00edvat malou mechanickou ml\u00e1ti\u010dku na obil\u00ed.", [["Je\u0161t\u011b", "je\u0161t\u011b", "ADV", [0, 5]], ["jsem", "b\u00fdt", "AUX", [6, 10]], ["tam", "tam", "ADV", [11, 14]], ["tak\u00e9", "tak\u00e9", "ADV", [15, 19]], ["vid\u011bl", "vid\u011bt", "VERB", [20, 25]], ["pou\u017e\u00edvat", "pou\u017e\u00edvat", "VERB", [26, 34]], ["malou", "mal\u00fd", "ADJ", [35, 40]], ["mechanickou", "mechanick\u00fd", "ADJ", [41, 52]], ["ml\u00e1ti\u010dku", "ml\u00e1ti\u010dka", "NOUN", [53, 61]], ["na", "na", "ADP", [62, 64]], ["obil\u00ed", "obil\u00ed", "NOUN", [65, 70]], [".", ".", "PUNCT", [70, 71]]]], ["calgarske-listy_2003_unor_ocr.txt", "\u017dito se ale ml\u00e1tilo pomoc\u00ed cep\u016f.", [["\u017dito", "\u017eito", "NOUN", [0, 4]], ["se", "se", "PRON", [5, 7]], ["ale", "ale", "CCONJ", [8, 11]], ["ml\u00e1tilo", "ml\u00e1tit", "VERB", [12, 19]], ["pomoc\u00ed", "pomoc\u00ed", "ADP", [20, 26]], ["cep\u016f", "cep", "NOUN", [27, 31]], [".", ".", "PUNCT", [31, 32]]]], ["calgarske-listy_2003_unor_ocr.txt", "To se rozv\u00e1zan\u00e9 snopy \u017eita rozlo\u017eily na ten\u0161\u00ed vrstvu na udusan\u00e9 a tvrd\u00e9 podlaze mlatu a v\u011bt\u0161inou 4 a\u017e 6 mlatc\u016f s cepy velmi obratn\u011b vytloukalo zrno z klas\u016f.", [["To", "ten", "DET", [0, 2]], ["se", "se", "PRON", [3, 5]], ["rozv\u00e1zan\u00e9", "rozv\u00e1zan\u00fd", "ADJ", [6, 15]], ["snopy", "snopa", "NOUN", [16, 21]], ["\u017eita", "\u017eito", "NOUN", [22, 26]], ["rozlo\u017eily", "rozlo\u017eit", "VERB", [27, 36]], ["na", "na", "ADP", [37, 39]], ["ten\u0161\u00ed", "tan\u00fd", "ADJ", [40, 45]], ["vrstvu", "vrstva", "NOUN", [46, 52]], ["na", "na", "ADP", [53, 55]], ["udusan\u00e9", "udusan\u00fd", "ADJ", [56, 63]], ["a", "a", "CCONJ", [64, 65]], ["tvrd\u00e9", "tvrd\u00fd", "ADJ", [66, 71]], ["podlaze", "podlaha", "NOUN", [72, 79]], ["mlatu", "mlato", "NOUN", [80, 85]], ["a", "a", "CCONJ", [86, 87]], ["v\u011bt\u0161inou", "v\u011bt\u0161inou", "ADV", [88, 96]], ["4", "4", "NUM", [97, 98]], ["a\u017e", "a\u017e", "CCONJ", [99, 101]], ["6", "6", "NUM", [102, 103]], ["mlatc\u016f", "mlatec", "NOUN", [104, 110]], ["s", "s", "ADP", [111, 112]], ["cepy", "cepa", "NOUN", [113, 117]], ["velmi", "velmi", "ADV", [118, 123]], ["obratn\u011b", "obratn\u011b", "ADV", [124, 131]], ["vytloukalo", "vytloukat", "VERB", [132, 142]], ["zrno", "zrno", "NOUN", [143, 147]], ["z", "z", "ADP", [148, 149]], ["klas\u016f", "klas", "NOUN", [150, 155]], [".", ".", "PUNCT", [155, 156]]]], ["calgarske-listy_2003_unor_ocr.txt", "Horn\u00ed \u010d\u00e1st cepu p\u0159ipevn\u011bn\u00e1 \u0159em\u00ednky k n\u00e1sad\u011b se nech\u00e1vala dopadat na klasy, z v\u00fd\u0161ky asi 150 cm.", [["Horn\u00ed", "horn\u00ed", "ADJ", [0, 5]], ["\u010d\u00e1st", "\u010d\u00e1st", "NOUN", [6, 10]], ["cepu", "cep", "NOUN", [11, 15]], ["p\u0159ipevn\u011bn\u00e1", "p\u0159ipevn\u011bn\u00fd", "ADJ", [16, 26]], ["\u0159em\u00ednky", "\u0159em\u00ednek", "NOUN", [27, 34]], ["k", "k", "ADP", [35, 36]], ["n\u00e1sad\u011b", "n\u00e1sada", "NOUN", [37, 43]], ["se", "se", "PRON", [44, 46]], ["nech\u00e1vala", "nech\u00e1vat", "VERB", [47, 56]], ["dopadat", "dopadat", "VERB", [57, 64]], ["na", "na", "ADP", [65, 67]], ["klasy", "klas", "NOUN", [68, 73]], [",", ",", "PUNCT", [73, 74]], ["z", "z", "ADP", [75, 76]], ["v\u00fd\u0161ky", "v\u00fd\u0161ka", "NOUN", [77, 82]], ["asi", "asi", "PART", [83, 86]], ["150", "150", "NUM", [87, 90]], ["cm", "centimetr", "NOUN", [91, 93]], [".", ".", "PUNCT", [93, 94]]]], ["calgarske-listy_2003_unor_ocr.txt", "Mlatci zdv\u00edhali a prot\u00e1\u010deli cepy v ur\u010dit\u00e9, st\u00e1l\u00e9 rychlosti a zvuk dopadaj\u00edc\u00edch cep\u016f m\u011bl podmaniv\u00fd rytmus.", [["Mlatci", "Mlatec", "PROPN", [0, 6]], ["zdv\u00edhali", "zdv\u00edhat", "VERB", [7, 15]], ["a", "a", "CCONJ", [16, 17]], ["prot\u00e1\u010deli", "prot\u00e1\u010det", "VERB", [18, 27]], ["cepy", "cepa", "NOUN", [28, 32]], ["v", "v", "ADP", [33, 34]], ["ur\u010dit\u00e9", "ur\u010dit\u00fd", "ADJ", [35, 41]], [",", ",", "PUNCT", [41, 42]], ["st\u00e1l\u00e9", "st\u00e1l\u00fd", "ADJ", [43, 48]], ["rychlosti", "rychlost", "NOUN", [49, 58]], ["a", "a", "CCONJ", [59, 60]], ["zvuk", "zvuk", "NOUN", [61, 65]], ["dopadaj\u00edc\u00edch", "dopadaj\u00edc\u00ed", "ADJ", [66, 78]], ["cep\u016f", "cep", "NOUN", [79, 83]], ["m\u011bl", "m\u00edt", "VERB", [84, 87]], ["podmaniv\u00fd", "podmaniv\u00fd", "ADJ", [88, 97]], ["rytmus", "rytmus", "NOUN", [98, 104]], [".", ".", "PUNCT", [104, 105]]]], ["calgarske-listy_2003_unor_ocr.txt", "Ta, ta, ta, - ta, ta, ta.", [["Ta", "ten", "DET", [0, 2]], [",", ",", "PUNCT", [2, 3]], ["ta", "ten", "DET", [4, 6]], [",", ",", "PUNCT", [6, 7]], ["ta", "ten", "DET", [8, 10]], [",", ",", "PUNCT", [10, 11]], ["-", "-", "PUNCT", [12, 13]], ["ta", "ten", "DET", [14, 16]], [",", ",", "PUNCT", [16, 17]], ["ta", "ten", "DET", [18, 20]], [",", ",", "PUNCT", [20, 21]], ["ta", "ten", "DET", [22, 24]], [".", ".", "PUNCT", [24, 25]]]], ["calgarske-listy_2003_unor_ocr.txt", "Po odstran\u011bn\u00ed vyml\u00e1cen\u00e9 \u017eitn\u00e9 sl\u00e1my se zrno a plevy smetly a pros\u00edvaly na \u0159e\u0161etech a pak dokonale vyt\u0159\u00eddily v\u011btr\u00e1kov\u00fdm ml\u00fdnkem, kter\u00fd se ji\u017e poh\u00e1n\u011bl ru\u010dn\u011b pomoc\u00ed kliky.", [["Po", "po", "ADP", [0, 2]], ["odstran\u011bn\u00ed", "odstran\u011bn\u00ed", "NOUN", [3, 13]], ["vyml\u00e1cen\u00e9", "vyml\u00e1cen\u00fd", "ADJ", [14, 23]], ["\u017eitn\u00e9", "\u017eitn\u00fd", "ADJ", [24, 29]], ["sl\u00e1my", "sl\u00e1ma", "NOUN", [30, 35]], ["se", "se", "PRON", [36, 38]], ["zrno", "zrno", "NOUN", [39, 43]], ["a", "a", "CCONJ", [44, 45]], ["plevy", "pleva", "NOUN", [46, 51]], ["smetly", "sm\u00e9st", "VERB", [52, 58]], ["a", "a", "CCONJ", [59, 60]], ["pros\u00edvaly", "pros\u00edvat", "VERB", [61, 70]], ["na", "na", "ADP", [71, 73]], ["\u0159e\u0161etech", "\u0159e\u0161e\u0165", "NOUN", [74, 82]], ["a", "a", "CCONJ", [83, 84]], ["pak", "pak", "ADV", [85, 88]], ["dokonale", "dokonale", "ADV", [89, 97]], ["vyt\u0159\u00eddily", "vyt\u0159\u00eddit", "VERB", [98, 107]], ["v\u011btr\u00e1kov\u00fdm", "v\u011btr\u00e1kov\u00fd", "ADJ", [108, 118]], ["ml\u00fdnkem", "ml\u00fdnek", "NOUN", [119, 126]], [",", ",", "PUNCT", [126, 127]], ["kter\u00fd", "kter\u00fd", "DET", [128, 133]], ["se", "se", "PRON", [134, 136]], ["ji\u017e", "ji\u017e", "ADV", [137, 140]], ["poh\u00e1n\u011bl", "poh\u00e1n\u011bt", "VERB", [141, 148]], ["ru\u010dn\u011b", "ru\u010dn\u011b", "ADV", [149, 154]], ["pomoc\u00ed", "pomoc\u00ed", "ADP", [155, 161]], ["kliky", "klika", "NOUN", [162, 167]], [".", ".", "PUNCT", [167, 168]]]], ["calgarske-listy_2003_unor_ocr.txt", "Dlouh\u00e1 \u017eitn\u00e1 sl\u00e1ma se pak pou\u017e\u00edvala na d\u011bl\u00e1n\u00ed pov\u0159\u00edsel, pro v\u00e1zan\u00ed ovsa \u010di je\u010dmene.", [["Dlouh\u00e1", "dlouh\u00fd", "ADJ", [0, 6]], ["\u017eitn\u00e1", "\u017eitn\u00fd", "ADJ", [7, 12]], ["sl\u00e1ma", "sl\u00e1ma", "NOUN", [13, 18]], ["se", "se", "PRON", [19, 21]], ["pak", "pak", "ADV", [22, 25]], ["pou\u017e\u00edvala", "pou\u017e\u00edvat", "VERB", [26, 35]], ["na", "na", "ADP", [36, 38]], ["d\u011bl\u00e1n\u00ed", "d\u011bl\u00e1n\u00ed", "NOUN", [39, 45]], ["pov\u0159\u00edsel", "pov\u0159\u00edset", "VERB", [46, 54]], [",", ",", "PUNCT", [54, 55]], ["pro", "pro", "ADP", [56, 59]], ["v\u00e1zan\u00ed", "v\u00e1zan\u00fd", "ADJ", [60, 66]], ["ovsa", "oves", "NOUN", [67, 71]], ["\u010di", "\u010di", "CCONJ", [72, 74]], ["je\u010dmene", "je\u010dmen", "NOUN", [75, 82]], [".", ".", "PUNCT", [82, 83]]]], ["calgarske-listy_2003_unor_ocr.txt", "\u017ditn\u00e9 zrno se ukl\u00e1dalo na s\u00fdpce, co\u017e byla nej su\u0161\u0161\u00ed \u010d\u00e1st domu nad hlavn\u00edm pokojem.", [["\u017ditn\u00e9", "\u017eitn\u00fd", "ADJ", [0, 5]], ["zrno", "zrno", "NOUN", [6, 10]], ["se", "se", "PRON", [11, 13]], ["ukl\u00e1dalo", "ukl\u00e1dat", "VERB", [14, 22]], ["na", "na", "ADP", [23, 25]], ["s\u00fdpce", "s\u00fdpec", "NOUN", [26, 31]], [",", ",", "PUNCT", [31, 32]], ["co\u017e", "co\u017e", "PRON", [33, 36]], ["byla", "b\u00fdt", "AUX", [37, 41]], ["nej", "nej", "NOUN", [42, 45]], ["su\u0161\u0161\u00ed", "such\u00fd", "ADJ", [46, 51]], ["\u010d\u00e1st", "\u010d\u00e1st", "NOUN", [52, 56]], ["domu", "d\u016fm", "NOUN", [57, 61]], ["nad", "nad", "ADP", [62, 65]], ["hlavn\u00edm", "hlavn\u00ed", "ADJ", [66, 73]], ["pokojem", "pokoj", "NOUN", [74, 81]], [".", ".", "PUNCT", [81, 82]]]], ["calgarske-listy_2003_unor_ocr.txt", "Vedly tam d\u0159ev\u011bn\u00e9 \u00fazk\u00e9 schody, 14  moc jsem se jich b\u00e1l, n\u011bkolikr\u00e1te jsem z nich spadnul.", [["Vedly", "v\u00e9st", "VERB", [0, 5]], ["tam", "tam", "ADV", [6, 9]], ["d\u0159ev\u011bn\u00e9", "d\u0159ev\u011bn\u00fd", "ADJ", [10, 17]], ["\u00fazk\u00e9", "\u00fazk\u00fd", "ADJ", [18, 22]], ["schody", "schod", "NOUN", [23, 29]], [",", ",", "PUNCT", [29, 30]], ["14", "14", "NUM", [31, 33]], ["moc", "moc", "ADV", [35, 38]], ["jsem", "b\u00fdt", "AUX", [39, 43]], ["se", "se", "PRON", [44, 46]], ["jich", "on", "PRON", [47, 51]], ["b\u00e1l", "b\u00e1t", "VERB", [52, 55]], [",", ",", "PUNCT", [55, 56]], ["n\u011bkolikr\u00e1te", "n\u011bkolikr\u00e1t", "ADV", [57, 68]], ["jsem", "b\u00fdt", "AUX", [69, 73]], ["z", "z", "ADP", [74, 75]], ["nich", "on", "PRON", [76, 80]], ["spadnul", "spadnout", "VERB", [81, 88]], [".", ".", "PUNCT", [88, 89]]]], ["calgarske-listy_2003_unor_ocr.txt", "V zim\u011b se postupn\u011b zrno nosilo do ml\u00fdna p\u0159es potok, k semlet\u00ed na \u017eitnou mouku.", [["V", "v", "ADP", [0, 1]], ["zim\u011b", "zima", "NOUN", [2, 6]], ["se", "se", "PRON", [7, 9]], ["postupn\u011b", "postupn\u011b", "ADV", [10, 18]], ["zrno", "zrno", "NOUN", [19, 23]], ["nosilo", "nosit", "VERB", [24, 30]], ["do", "do", "ADP", [31, 33]], ["ml\u00fdna", "ml\u00fdn", "NOUN", [34, 39]], ["p\u0159es", "p\u0159es", "ADP", [40, 44]], ["potok", "potok", "NOUN", [45, 50]], [",", ",", "PUNCT", [50, 51]], ["k", "k", "ADP", [52, 53]], ["semlet\u00ed", "semlet\u00ed", "NOUN", [54, 61]], ["na", "na", "ADP", [62, 64]], ["\u017eitnou", "\u017eitn\u00fd", "ADJ", [65, 71]], ["mouku", "mouka", "NOUN", [72, 77]], [".", ".", "PUNCT", [77, 78]]]], ["calgarske-listy_2003_unor_ocr.txt", "Z \u017eitn\u00e9 mouky se p\u0159ev\u00e1\u017en\u011b pekl chleba.", [["Z", "z", "ADP", [0, 1]], ["\u017eitn\u00e9", "\u017eitn\u00fd", "ADJ", [2, 7]], ["mouky", "mouka", "NOUN", [8, 13]], ["se", "se", "PRON", [14, 16]], ["p\u0159ev\u00e1\u017en\u011b", "p\u0159ev\u00e1\u017en\u011b", "ADV", [17, 25]], ["pekl", "p\u00e9ci", "VERB", [26, 30]], ["chleba", "chl\u00e9b", "NOUN", [31, 37]], [".", ".", "PUNCT", [37, 38]]]], ["calgarske-listy_2003_unor_ocr.txt", "To jsem ale pozd\u011bji u\u017e jako star\u0161\u00ed hoch vid\u011bl a i pom\u00e1hal m\u00e9 dal\u0161\u00ed babi\u010dce Cecilii v Divi\u0161ov\u011b.", [["To", "ten", "DET", [0, 2]], ["jsem", "b\u00fdt", "AUX", [3, 7]], ["ale", "ale", "CCONJ", [8, 11]], ["pozd\u011bji", "pozd\u011b", "ADV", [12, 19]], ["u\u017e", "u\u017e", "ADV", [20, 22]], ["jako", "jako", "SCONJ", [23, 27]], ["star\u0161\u00ed", "star\u00fd", "ADJ", [28, 34]], ["hoch", "hocha", "NOUN", [35, 39]], ["vid\u011bl", "vid\u011bt", "VERB", [40, 45]], ["a", "a", "CCONJ", [46, 47]], ["i", "i", "CCONJ", [48, 49]], ["pom\u00e1hal", "pom\u00e1hat", "VERB", [50, 57]], ["m\u00e9", "m\u016fj", "DET", [58, 60]], ["dal\u0161\u00ed", "dal\u0161\u00ed", "ADJ", [61, 66]], ["babi\u010dce", "babi\u010dka", "NOUN", [67, 74]], ["Cecilii", "Cecilie", "PROPN", [75, 82]], ["v", "v", "ADP", [83, 84]], ["Divi\u0161ov\u011b", "Divi\u0161ov", "PROPN", [85, 93]], [".", ".", "PUNCT", [93, 94]]]], ["calgarske-listy_2003_unor_ocr.txt", "Po kr\u00e1sn\u00e9m l\u00e9tu 1935 p\u0159i\u0161la zima, n\u00e1m napadnul sn\u00edh a jezdilo se na s\u00e1\u0148k\u00e1ch.", [["Po", "po", "ADP", [0, 2]], ["kr\u00e1sn\u00e9m", "kr\u00e1sn\u00fd", "ADJ", [3, 10]], ["l\u00e9tu", "l\u00e9ta", "NOUN", [11, 15]], ["1935", "1935", "NUM", [16, 20]], ["p\u0159i\u0161la", "p\u0159ij\u00edt", "VERB", [21, 27]], ["zima", "zima", "NOUN", [28, 32]], [",", ",", "PUNCT", [32, 33]], ["n\u00e1m", "my", "PRON", [34, 37]], ["napadnul", "napadnout", "VERB", [38, 46]], ["sn\u00edh", "sn\u00edh", "NOUN", [47, 51]], ["a", "a", "CCONJ", [52, 53]], ["jezdilo", "jezdit", "VERB", [54, 61]], ["se", "se", "PRON", [62, 64]], ["na", "na", "ADP", [65, 67]], ["s\u00e1\u0148k\u00e1ch", "s\u00e1\u0148ka", "NOUN", [68, 75]], [".", ".", "PUNCT", [75, 76]]]], ["calgarske-listy_2003_unor_ocr.txt", "N\u00e1\u0161 dv\u016fr byl cel\u00fd p\u011bkn\u011b z kope\u010dka a tak se zase v\u0161echna ml\u00e1de\u017e ze ml\u00fdna p\u0159ist\u011bhovala k n\u00e1m na klouz\u00e1n\u00ed.", [["N\u00e1\u0161", "n\u00e1\u0161", "DET", [0, 3]], ["dv\u016fr", "dv\u016fr", "NOUN", [4, 8]], ["byl", "b\u00fdt", "AUX", [9, 12]], ["cel\u00fd", "cel\u00fd", "ADJ", [13, 17]], ["p\u011bkn\u011b", "p\u011bkn\u011b", "ADV", [18, 23]], ["z", "z", "ADP", [24, 25]], ["kope\u010dka", "kope\u010dka", "NOUN", [26, 33]], ["a", "a", "CCONJ", [34, 35]], ["tak", "tak", "ADV", [36, 39]], ["se", "se", "PRON", [40, 42]], ["zase", "zase", "ADV", [43, 47]], ["v\u0161echna", "v\u0161echen", "DET", [48, 55]], ["ml\u00e1de\u017e", "ml\u00e1de\u017e", "NOUN", [56, 62]], ["ze", "z", "ADP", [63, 65]], ["ml\u00fdna", "ml\u00fdn", "NOUN", [66, 71]], ["p\u0159ist\u011bhovala", "p\u0159ist\u011bhovat", "VERB", [72, 84]], ["k", "k", "ADP", [85, 86]], ["n\u00e1m", "my", "PRON", [87, 90]], ["na", "na", "ADP", [91, 93]], ["klouz\u00e1n\u00ed", "klouz\u00e1n\u00ed", "NOUN", [94, 102]], [".", ".", "PUNCT", [102, 103]]]], ["calgarske-listy_2003_unor_ocr.txt", "Byly to vcelku troje s\u00e1\u0148ky, ale \u0159evu n\u00e1s p\u011bt d\u011bt\u00ed nad\u011blalo hodn\u011b.", [["Byly", "b\u00fdt", "AUX", [0, 4]], ["to", "ten", "DET", [5, 7]], ["vcelku", "vcelku", "ADV", [8, 14]], ["troje", "troj\u00ed", "ADJ", [15, 20]], ["s\u00e1\u0148ky", "s\u00e1\u0148ka", "NOUN", [21, 26]], [",", ",", "PUNCT", [26, 27]], ["ale", "ale", "CCONJ", [28, 31]], ["\u0159evu", "\u0159ev", "NOUN", [32, 36]], ["n\u00e1s", "my", "PRON", [37, 40]], ["p\u011bt", "p\u011bt", "NUM", [41, 44]], ["d\u011bt\u00ed", "d\u00edt\u011b", "NOUN", [45, 49]], ["nad\u011blalo", "nad\u011blat", "VERB", [50, 58]], ["hodn\u011b", "hodn\u011b", "ADV", [59, 64]], [".", ".", "PUNCT", [64, 65]]]], ["calgarske-listy_2003_unor_ocr.txt", "Pak se nastaly V\u00e1noce a babi\u010dka pro m\u011b p\u0159istrojila strome\u010dek.", [["Pak", "pak", "ADV", [0, 3]], ["se", "se", "PRON", [4, 6]], ["nastaly", "nastat", "VERB", [7, 14]], ["V\u00e1noce", "V\u00e1noce", "NOUN", [15, 21]], ["a", "a", "CCONJ", [22, 23]], ["babi\u010dka", "babi\u010dka", "NOUN", [24, 31]], ["pro", "pro", "ADP", [32, 35]], ["m\u011b", "j\u00e1", "PRON", [36, 38]], ["p\u0159istrojila", "p\u0159istrojit", "VERB", [39, 50]], ["strome\u010dek", "strome\u010dek", "NOUN", [51, 60]], [".", ".", "PUNCT", [60, 61]]]], ["calgarske-listy_2003_unor_ocr.txt", "Strome\u010dek byl asi metrov\u00fd na 120 cm vysok\u00e9m d\u0159ev\u011bn\u00e9m podstavci.", [["Strome\u010dek", "strome\u010dek", "NOUN", [0, 9]], ["byl", "b\u00fdt", "AUX", [10, 13]], ["asi", "asi", "PART", [14, 17]], ["metrov\u00fd", "metrov\u00fd", "ADJ", [18, 25]], ["na", "na", "ADP", [26, 28]], ["120", "120", "NUM", [29, 32]], ["cm", "centimetr", "NOUN", [33, 35]], ["vysok\u00e9m", "vysok\u00fd", "ADJ", [36, 43]], ["d\u0159ev\u011bn\u00e9m", "d\u0159ev\u011bn\u00fd", "ADJ", [44, 52]], ["podstavci", "podstavec", "NOUN", [53, 62]], [".", ".", "PUNCT", [62, 63]]]], ["calgarske-listy_2003_unor_ocr.txt", "To asi aby se tam ve\u0161lo hodn\u011b d\u00e1rk\u016f.", [["To", "ten", "DET", [0, 2]], ["asi", "asi", "PART", [3, 6]], ["aby", "aby", "SCONJ", [-14285, -14285]], ["by", "b\u00fdt", "AUX", [-14285, -14285]], ["se", "se", "PRON", [11, 13]], ["tam", "tam", "ADV", [14, 17]], ["ve\u0161lo", "vej\u00edt", "VERB", [18, 23]], ["hodn\u011b", "hodn\u011b", "ADV", [24, 29]], ["d\u00e1rk\u016f", "d\u00e1rek", "NOUN", [30, 35]], [".", ".", "PUNCT", [35, 36]]]], ["calgarske-listy_2003_unor_ocr.txt", "Takov\u00e9 se u\u017e dnes ned\u011blaj\u00ed, ale d\u00e1rk\u016f se d\u00e1v\u00e1 5x tolik.", [["Takov\u00e9", "takov\u00fd", "DET", [0, 6]], ["se", "se", "PRON", [7, 9]], ["u\u017e", "u\u017e", "ADV", [10, 12]], ["dnes", "dnes", "ADV", [13, 17]], ["ned\u011blaj\u00ed", "d\u011blat", "VERB", [18, 26]], [",", ",", "PUNCT", [26, 27]], ["ale", "ale", "CCONJ", [28, 31]], ["d\u00e1rk\u016f", "d\u00e1rek", "NOUN", [32, 37]], ["se", "se", "PRON", [38, 40]], ["d\u00e1v\u00e1", "d\u00e1vat", "VERB", [41, 45]], ["5", "5", "NUM", [46, 47]], ["x", "x", "SYM", [47, 48]], ["tolik", "tolik", "DET", [49, 54]], [".", ".", "PUNCT", [54, 55]]]], ["calgarske-listy_2003_unor_ocr.txt", "Cukrov\u00ed bylo v\u011bt\u0161inou doma pe\u010den\u00e9, zlatost\u0159\u00edbrn\u00e9 \u0159et\u011bzy, a naho\u0159e na \u0161pici pom\u011brn\u011b velik\u00e1, pest\u0159e barevn\u00e1 sklen\u011bn\u00e1 hv\u011bzda i s ohonem.", [["Cukrov\u00ed", "cukrov\u00ed", "NOUN", [0, 7]], ["bylo", "b\u00fdt", "AUX", [8, 12]], ["v\u011bt\u0161inou", "v\u011bt\u0161inou", "ADV", [13, 21]], ["doma", "doma", "ADV", [22, 26]], ["pe\u010den\u00e9", "pe\u010den\u00fd", "ADJ", [27, 33]], [",", ",", "PUNCT", [33, 34]], ["zlatost\u0159\u00edbrn\u00e9", "zlatost\u0159\u00edbrn\u00fd", "ADJ", [35, 48]], ["\u0159et\u011bzy", "\u0159et\u011bz", "NOUN", [49, 55]], [",", ",", "PUNCT", [55, 56]], ["a", "a", "CCONJ", [57, 58]], ["naho\u0159e", "naho\u0159e", "ADV", [59, 65]], ["na", "na", "ADP", [66, 68]], ["\u0161pici", "\u0161pice", "NOUN", [69, 74]], ["pom\u011brn\u011b", "pom\u011brn\u011b", "ADV", [75, 82]], ["velik\u00e1", "velik\u00fd", "ADJ", [83, 89]], [",", ",", "PUNCT", [89, 90]], ["pest\u0159e", "pest\u0159e", "ADV", [91, 97]], ["barevn\u00e1", "barevn\u00fd", "ADJ", [98, 105]], ["sklen\u011bn\u00e1", "sklen\u011bn\u00fd", "ADJ", [106, 114]], ["hv\u011bzda", "hv\u011bzda", "NOUN", [115, 121]], ["i", "i", "CCONJ", [122, 123]], ["s", "s", "ADP", [124, 125]], ["ohonem", "ohon", "NOUN", [126, 132]], [".", ".", "PUNCT", [132, 133]]]], ["calgarske-listy_2003_unor_ocr.txt", "Takov\u00e9 se u\u017e asi ned\u011blaj\u00ed.", [["Takov\u00e9", "takov\u00fd", "DET", [0, 6]], ["se", "se", "PRON", [7, 9]], ["u\u017e", "u\u017e", "ADV", [10, 12]], ["asi", "asi", "PART", [13, 16]], ["ned\u011blaj\u00ed", "d\u011blat", "VERB", [17, 25]], [".", ".", "PUNCT", [25, 26]]]], ["calgarske-listy_2003_unor_ocr.txt", "D\u00e1le tam bylo 10 prav\u00fdch barevn\u00fdch sv\u00ed\u010dek a tak\u00e9 prskavky.", [["D\u00e1le", "d\u00e1le", "ADV", [0, 4]], ["tam", "tam", "ADV", [5, 8]], ["bylo", "b\u00fdt", "AUX", [9, 13]], ["10", "10", "NUM", [14, 16]], ["prav\u00fdch", "prav\u00fd", "ADJ", [17, 24]], ["barevn\u00fdch", "barevn\u00fd", "ADJ", [25, 34]], ["sv\u00ed\u010dek", "sv\u00ed\u010dka", "NOUN", [35, 41]], ["a", "a", "CCONJ", [42, 43]], ["tak\u00e9", "tak\u00e9", "ADV", [44, 48]], ["prskavky", "prskavek", "NOUN", [49, 57]], [".", ".", "PUNCT", [57, 58]]]], ["calgarske-listy_2003_unor_ocr.txt", "J\u00e1 si pamatuji, \u017ee strome\u010dek st\u00e1l v n\u00e1dhern\u00e9m ob\u00fdvac\u00edm pokoji, kam jsem prakticky nikdy ne\u0161el.", [["J\u00e1", "j\u00e1", "PRON", [0, 2]], ["si", "se", "PRON", [3, 5]], ["pamatuji", "pamatovat", "VERB", [6, 14]], [",", ",", "PUNCT", [14, 15]], ["\u017ee", "\u017ee", "SCONJ", [16, 18]], ["strome\u010dek", "strome\u010dek", "NOUN", [19, 28]], ["st\u00e1l", "st\u00e1t", "VERB", [29, 33]], ["v", "v", "ADP", [34, 35]], ["n\u00e1dhern\u00e9m", "n\u00e1dhern\u00fd", "ADJ", [36, 45]], ["ob\u00fdvac\u00edm", "ob\u00fdvac\u00ed", "ADJ", [46, 54]], ["pokoji", "pokoj", "NOUN", [55, 61]], [",", ",", "PUNCT", [61, 62]], ["kam", "kam", "ADV", [63, 66]], ["jsem", "b\u00fdt", "AUX", [67, 71]], ["prakticky", "prakticky", "ADV", [72, 81]], ["nikdy", "nikdy", "ADV", [82, 87]], ["ne\u0161el", "j\u00edt", "VERB", [88, 93]], [".", ".", "PUNCT", [93, 94]]]], ["calgarske-listy_2003_unor_ocr.txt", "Tam byl n\u00e1dhern\u00fd st\u016fl a 6 pomp\u00e9zn\u011b zdoben\u00fdch sametov\u00fdch \u017eidl\u00ed, velk\u00e1 pohovka pro 4 lidi s n\u00e1dhern\u00fdm rud\u00fdm sametem a men\u0161\u00ed pohovka.", [["Tam", "tam", "ADV", [0, 3]], ["byl", "b\u00fdt", "AUX", [4, 7]], ["n\u00e1dhern\u00fd", "n\u00e1dhern\u00fd", "ADJ", [8, 16]], ["st\u016fl", "st\u016fl", "NOUN", [17, 21]], ["a", "a", "CCONJ", [22, 23]], ["6", "6", "NUM", [24, 25]], ["pomp\u00e9zn\u011b", "pomp\u00e9zn\u011b", "ADV", [26, 34]], ["zdoben\u00fdch", "zdoben\u00fd", "ADJ", [35, 44]], ["sametov\u00fdch", "sametov\u00fd", "ADJ", [45, 55]], ["\u017eidl\u00ed", "\u017eidle", "NOUN", [56, 61]], [",", ",", "PUNCT", [61, 62]], ["velk\u00e1", "velk\u00fd", "ADJ", [63, 68]], ["pohovka", "pohovka", "NOUN", [69, 76]], ["pro", "pro", "ADP", [77, 80]], ["4", "4", "NUM", [81, 82]], ["lidi", "lid\u00e9", "NOUN", [83, 87]], ["s", "s", "ADP", [88, 89]], ["n\u00e1dhern\u00fdm", "n\u00e1dhern\u00fd", "ADJ", [90, 99]], ["rud\u00fdm", "rud\u00fd", "ADJ", [100, 105]], ["sametem", "samet", "NOUN", [106, 113]], ["a", "a", "CCONJ", [114, 115]], ["men\u0161\u00ed", "mal\u00fd", "ADJ", [116, 121]], ["pohovka", "pohovka", "NOUN", [122, 129]], [".", ".", "PUNCT", [129, 130]]]], ["calgarske-listy_2003_unor_ocr.txt", "Na dlouh\u00e9 st\u011bn\u011b pak byly police pln\u00e9 kn\u00ed\u017eek, v\u0161echny \u00fahledn\u011b ve stejn\u00e9 velkosti.", [["Na", "na", "ADP", [0, 2]], ["dlouh\u00e9", "dlouh\u00fd", "ADJ", [3, 9]], ["st\u011bn\u011b", "st\u011bna", "NOUN", [10, 15]], ["pak", "pak", "ADV", [16, 19]], ["byly", "b\u00fdt", "AUX", [20, 24]], ["police", "police", "NOUN", [25, 31]], ["pln\u00e9", "pln\u00fd", "ADJ", [32, 36]], ["kn\u00ed\u017eek", "kn\u00ed\u017eka", "NOUN", [37, 43]], [",", ",", "PUNCT", [43, 44]], ["v\u0161echny", "v\u0161echen", "DET", [45, 52]], ["\u00fahledn\u011b", "\u00fahledn\u011b", "ADV", [53, 60]], ["ve", "v", "ADP", [61, 63]], ["stejn\u00e9", "stejn\u00fd", "ADJ", [64, 70]], ["velkosti", "velkost", "NOUN", [71, 79]], [".", ".", "PUNCT", [79, 80]]]], ["calgarske-listy_2003_unor_ocr.txt", "To byla d\u011bdova p\u00fdcha.", [["To", "ten", "DET", [0, 2]], ["byla", "b\u00fdt", "AUX", [3, 7]], ["d\u011bdova", "d\u011bd\u016fv", "ADJ", [8, 14]], ["p\u00fdcha", "p\u00fdcha", "NOUN", [15, 20]], [".", ".", "PUNCT", [20, 21]]]], ["calgarske-listy_2003_unor_ocr.txt", "Musel do toho nacpat asi hodn\u011b pen\u011bz, nikdy jsem ale nikoho nevid\u011bl n\u011bjakou tu kn\u00ed\u017eku \u010d\u00edst.", [["Musel", "muset", "VERB", [0, 5]], ["do", "do", "ADP", [6, 8]], ["toho", "ten", "DET", [9, 13]], ["nacpat", "nacpat", "VERB", [14, 20]], ["asi", "asi", "PART", [21, 24]], ["hodn\u011b", "hodn\u011b", "NOUN", [25, 30]], ["pen\u011bz", "pen\u00edze", "NOUN", [31, 36]], [",", ",", "PUNCT", [36, 37]], ["nikdy", "nikdy", "ADV", [38, 43]], ["jsem", "b\u00fdt", "AUX", [44, 48]], ["ale", "ale", "CCONJ", [49, 52]], ["nikoho", "nikdo", "PRON", [53, 59]], ["nevid\u011bl", "vid\u011bt", "VERB", [60, 67]], ["n\u011bjakou", "n\u011bjak\u00fd", "DET", [68, 75]], ["tu", "ten", "DET", [76, 78]], ["kn\u00ed\u017eku", "kn\u00ed\u017eka", "NOUN", [79, 85]], ["\u010d\u00edst", "\u010d\u00edst", "VERB", [86, 90]], [".", ".", "PUNCT", [90, 91]]]], ["calgarske-listy_2003_unor_ocr.txt", "V roce 1935 u\u017e se cpal do pop\u0159ed\u00ed v N\u011bmecku Hitler, a tak lidi v\u00edce \u010detli denn\u00ed noviny, ne\u017e n\u011bjakou starou literaturu.", [["V", "v", "ADP", [0, 1]], ["roce", "rok", "NOUN", [2, 6]], ["1935", "1935", "NUM", [7, 11]], ["u\u017e", "u\u017e", "ADV", [12, 14]], ["se", "se", "PRON", [15, 17]], ["cpal", "cp\u00e1t", "VERB", [18, 22]], ["do", "do", "ADP", [23, 25]], ["pop\u0159ed\u00ed", "pop\u0159ed\u00ed", "NOUN", [26, 33]], ["v", "v", "ADP", [34, 35]], ["N\u011bmecku", "N\u011bmecko", "PROPN", [36, 43]], ["Hitler", "Hitler", "PROPN", [44, 50]], [",", ",", "PUNCT", [50, 51]], ["a", "a", "CCONJ", [52, 53]], ["tak", "tak", "ADV", [54, 57]], ["lidi", "lid\u00e9", "NOUN", [58, 62]], ["v\u00edce", "v\u00edce", "ADV", [63, 67]], ["\u010detli", "\u010d\u00edst", "VERB", [68, 73]], ["denn\u00ed", "denn\u00ed", "ADJ", [74, 79]], ["noviny", "noviny", "NOUN", [80, 86]], [",", ",", "PUNCT", [86, 87]], ["ne\u017e", "ne\u017e", "SCONJ", [88, 91]], ["n\u011bjakou", "n\u011bjak\u00fd", "DET", [92, 99]], ["starou", "star\u00fd", "ADJ", [100, 106]], ["literaturu", "literatura", "NOUN", [107, 117]], [".", ".", "PUNCT", [117, 118]]]], ["calgarske-listy_2003_unor_ocr.txt", "Tak je\u0161t\u011b k t\u011bm v\u00e1noc\u016fm.", [["Tak", "tak", "ADV", [0, 3]], ["je\u0161t\u011b", "je\u0161t\u011b", "ADV", [4, 9]], ["k", "k", "ADP", [10, 11]], ["t\u011bm", "ten", "DET", [12, 15]], ["v\u00e1noc\u016fm", "v\u00e1noce", "NOUN", [16, 23]], [".", ".", "PUNCT", [23, 24]]]], ["calgarske-listy_2003_unor_ocr.txt", "V pokoji byla k ve\u010deru tma, pak n\u011bco n\u011bkde zazvonilo a tak jsem byl ubezpe\u010den, \u017ee to byl Je\u017e\u00ed\u0161ek a \u0161li jsme se pod\u00edvat co mi nad\u011blil.", [["V", "v", "ADP", [0, 1]], ["pokoji", "pokoj", "NOUN", [2, 8]], ["byla", "b\u00fdt", "AUX", [9, 13]], ["k", "k", "ADP", [14, 15]], ["ve\u010deru", "ve\u010der", "NOUN", [16, 22]], ["tma", "tma", "NOUN", [23, 26]], [",", ",", "PUNCT", [26, 27]], ["pak", "pak", "ADV", [28, 31]], ["n\u011bco", "n\u011bco", "PRON", [32, 36]], ["n\u011bkde", "n\u011bkde", "ADV", [37, 42]], ["zazvonilo", "zazvonit", "VERB", [43, 52]], ["a", "a", "CCONJ", [53, 54]], ["tak", "tak", "ADV", [55, 58]], ["jsem", "b\u00fdt", "AUX", [59, 63]], ["byl", "b\u00fdt", "AUX", [64, 67]], ["ubezpe\u010den", "ubezpe\u010den\u00fd", "ADJ", [68, 77]], [",", ",", "PUNCT", [77, 78]], ["\u017ee", "\u017ee", "SCONJ", [79, 81]], ["to", "ten", "DET", [82, 84]], ["byl", "b\u00fdt", "AUX", [85, 88]], ["Je\u017e\u00ed\u0161ek", "je\u017e\u00ed\u0161ek", "NOUN", [89, 96]], ["a", "a", "CCONJ", [97, 98]], ["\u0161li", "j\u00edt", "VERB", [99, 102]], ["jsme", "b\u00fdt", "AUX", [103, 107]], ["se", "se", "PRON", [108, 110]], ["pod\u00edvat", "pod\u00edvat", "VERB", [111, 118]], ["co", "co", "PRON", [119, 121]], ["mi", "j\u00e1", "PRON", [122, 124]], ["nad\u011blil", "nad\u011blit", "VERB", [125, 132]], [".", ".", "PUNCT", [132, 133]]]], ["calgarske-listy_2003_unor_ocr.txt", "Babi\u010dka rozsv\u00edtila na chvilku sv\u00ed\u010dky, aby netekl vosk na podlahu, tak jen na kr\u00e1tkou dobu.", [["Babi\u010dka", "babi\u010dka", "NOUN", [0, 7]], ["rozsv\u00edtila", "rozsv\u00edtit", "VERB", [8, 18]], ["na", "na", "ADP", [19, 21]], ["chvilku", "chvilka", "NOUN", [22, 29]], ["sv\u00ed\u010dky", "sv\u00ed\u010dka", "NOUN", [30, 36]], [",", ",", "PUNCT", [36, 37]], ["aby", "aby", "SCONJ", [-15297, -15297]], ["by", "b\u00fdt", "AUX", [-15297, -15297]], ["netekl", "t\u00e9ci", "VERB", [42, 48]], ["vosk", "vosk", "NOUN", [49, 53]], ["na", "na", "ADP", [54, 56]], ["podlahu", "podlaha", "NOUN", [57, 64]], [",", ",", "PUNCT", [64, 65]], ["tak", "tak", "ADV", [66, 69]], ["jen", "jen", "PART", [70, 73]], ["na", "na", "ADP", [74, 76]], ["kr\u00e1tkou", "kr\u00e1tk\u00fd", "ADJ", [77, 84]], ["dobu", "doba", "NOUN", [85, 89]], [".", ".", "PUNCT", [89, 90]]]], ["calgarske-listy_2003_unor_ocr.txt", "Pak prskly prskavky, ten smrad mi ale moc ne\u0161el pod nos, u\u017e za mlada jsem m\u011bl \u010dich velmi citliv\u00fd.", [["Pak", "pak", "ADV", [0, 3]], ["prskly", "prsknout", "VERB", [4, 10]], ["prskavky", "prskavek", "NOUN", [11, 19]], [",", ",", "PUNCT", [19, 20]], ["ten", "ten", "DET", [21, 24]], ["smrad", "smrad", "NOUN", [25, 30]], ["mi", "j\u00e1", "PRON", [31, 33]], ["ale", "ale", "CCONJ", [34, 37]], ["moc", "moc", "ADV", [38, 41]], ["ne\u0161el", "j\u00edt", "VERB", [42, 47]], ["pod", "pod", "ADP", [48, 51]], ["nos", "nos", "NOUN", [52, 55]], [",", ",", "PUNCT", [55, 56]], ["u\u017e", "u\u017e", "ADV", [57, 59]], ["za", "za", "ADP", [60, 62]], ["mlada", "mlado", "NOUN", [63, 68]], ["jsem", "b\u00fdt", "AUX", [69, 73]], ["m\u011bl", "m\u00edt", "VERB", [74, 77]], ["\u010dich", "\u010dich", "NOUN", [78, 82]], ["velmi", "velmi", "ADV", [83, 88]], ["citliv\u00fd", "citliv\u00fd", "ADJ", [89, 96]], [".", ".", "PUNCT", [96, 97]]]], ["calgarske-listy_2003_unor_ocr.txt", "Dostal jsem s\u00e1\u0148ky, proto\u017ee ty star\u00e9 jsme, dvakr\u00e1t nabourali a ne\u0161ly spravit.", [["Dostal", "dostat", "VERB", [0, 6]], ["jsem", "b\u00fdt", "AUX", [7, 11]], ["s\u00e1\u0148ky", "s\u00e1\u0148ka", "NOUN", [12, 17]], [",", ",", "PUNCT", [17, 18]], ["proto\u017ee", "proto\u017ee", "SCONJ", [19, 26]], ["ty", "ten", "DET", [27, 29]], ["star\u00e9", "star\u00fd", "ADJ", [30, 35]], ["jsme", "b\u00fdt", "AUX", [36, 40]], [",", ",", "PUNCT", [40, 41]], ["dvakr\u00e1t", "dvakr\u00e1t", "ADV", [42, 49]], ["nabourali", "nabourat", "VERB", [50, 59]], ["a", "a", "CCONJ", [60, 61]], ["ne\u0161ly", "j\u00edt", "VERB", [62, 67]], ["spravit", "spravit", "VERB", [68, 75]], [".", ".", "PUNCT", [75, 76]]]], ["calgarske-listy_2003_unor_ocr.txt", "V\u00edc toho asi nebylo, tehd\u00e1 se \u0161et\u0159ilo, a jestli tam bylo n\u011bco pro babi\u010dku \u010di pro d\u011bdu, si v\u016fbec nepamatuji.", [["V\u00edc", "v\u00edce", "ADV", [0, 3]], ["toho", "ten", "DET", [4, 8]], ["asi", "asi", "PART", [9, 12]], ["nebylo", "b\u00fdt", "AUX", [13, 19]], [",", ",", "PUNCT", [19, 20]], ["tehd\u00e1", "tehd\u00e1", "SCONJ", [21, 26]], ["se", "se", "PRON", [27, 29]], ["\u0161et\u0159ilo", "\u0161et\u0159it", "VERB", [30, 37]], [",", ",", "PUNCT", [37, 38]], ["a", "a", "CCONJ", [39, 40]], ["jestli", "jestli", "SCONJ", [41, 47]], ["tam", "tam", "ADV", [48, 51]], ["bylo", "b\u00fdt", "AUX", [52, 56]], ["n\u011bco", "n\u011bco", "PRON", [57, 61]], ["pro", "pro", "ADP", [62, 65]], ["babi\u010dku", "babi\u010dka", "NOUN", [66, 73]], ["\u010di", "\u010di", "CCONJ", [74, 76]], ["pro", "pro", "ADP", [77, 80]], ["d\u011bdu", "d\u011bda", "NOUN", [81, 85]], [",", ",", "PUNCT", [85, 86]], ["si", "se", "PRON", [87, 89]], ["v\u016fbec", "v\u016fbec", "PART", [90, 95]], ["nepamatuji", "pamatovat", "VERB", [96, 106]], [".", ".", "PUNCT", [106, 107]]]], ["calgarske-listy_2003_unor_ocr.txt", "Pak se zhasly sv\u00ed\u010dky a odnesla petrolejov\u00e1 lampa do ob\u00fdvac\u00ed kuchyn\u011b a \u0161la se j\u00edst \u0161t\u011bdrove\u010dern\u00ed ve\u010de\u0159e.", [["Pak", "pak", "ADV", [0, 3]], ["se", "se", "PRON", [4, 6]], ["zhasly", "zhasnout", "VERB", [7, 13]], ["sv\u00ed\u010dky", "sv\u00ed\u010dka", "NOUN", [14, 20]], ["a", "a", "CCONJ", [21, 22]], ["odnesla", "odn\u00e9st", "VERB", [23, 30]], ["petrolejov\u00e1", "petrolejov\u00fd", "ADJ", [31, 42]], ["lampa", "lampa", "NOUN", [43, 48]], ["do", "do", "ADP", [49, 51]], ["ob\u00fdvac\u00ed", "ob\u00fdvac\u00ed", "ADJ", [52, 59]], ["kuchyn\u011b", "kuchy\u0148", "NOUN", [60, 67]], ["a", "a", "CCONJ", [68, 69]], ["\u0161la", "j\u00edt", "VERB", [70, 73]], ["se", "se", "PRON", [74, 76]], ["j\u00edst", "j\u00edst", "VERB", [77, 81]], ["\u0161t\u011bdrove\u010dern\u00ed", "\u0161t\u011bdrove\u010dern\u00ed", "ADJ", [82, 95]], ["ve\u010de\u0159e", "ve\u010de\u0159e", "NOUN", [96, 102]], [".", ".", "PUNCT", [102, 103]]]], ["calgarske-listy_2003_unor_ocr.txt", "Babi\u010dka uva\u0159ila dobrou krupi\u010dkovou pol\u00e9vku s p\u00f3rkem a do toho krutony osma\u017een\u00e9 na m\u00e1sle.", [["Babi\u010dka", "babi\u010dka", "NOUN", [0, 7]], ["uva\u0159ila", "uva\u0159it", "VERB", [8, 15]], ["dobrou", "dobr\u00fd", "ADJ", [16, 22]], ["krupi\u010dkovou", "krupi\u010dkov\u00fd", "ADJ", [23, 34]], ["pol\u00e9vku", "pol\u00e9vka", "NOUN", [35, 42]], ["s", "s", "ADP", [43, 44]], ["p\u00f3rkem", "p\u00f3rko", "NOUN", [45, 51]], ["a", "a", "CCONJ", [52, 53]], ["do", "do", "ADP", [54, 56]], ["toho", "ten", "DET", [57, 61]], ["krutony", "kruton", "NOUN", [62, 69]], ["osma\u017een\u00e9", "osma\u017een\u00fd", "ADJ", [70, 78]], ["na", "na", "ADP", [79, 81]], ["m\u00e1sle", "m\u00e1slo", "NOUN", [82, 87]], [".", ".", "PUNCT", [87, 88]]]], ["calgarske-listy_2003_unor_ocr.txt", "Tu chu\u0165 si je\u0161t\u011b dnes po 68 letech st\u00e1le pamatuji.", [["Tu", "ten", "DET", [0, 2]], ["chu\u0165", "chu\u0165", "NOUN", [3, 7]], ["si", "se", "PRON", [8, 10]], ["je\u0161t\u011b", "je\u0161t\u011b", "ADV", [11, 16]], ["dnes", "dnes", "ADV", [17, 21]], ["po", "po", "ADP", [22, 24]], ["68", "68", "NUM", [25, 27]], ["letech", "l\u00e9ta", "NOUN", [28, 34]], ["st\u00e1le", "st\u00e1le", "ADV", [35, 40]], ["pamatuji", "pamatovat", "VERB", [41, 49]], [".", ".", "PUNCT", [49, 50]]]], ["calgarske-listy_2003_unor_ocr.txt", "Pak byly obalovan\u00e9 \u0159\u00edzky z kapra i z kr\u00e1l\u00edka a k tomu v\u00fdborn\u00fd bramborov\u00fd sal\u00e1t.", [["Pak", "pak", "ADV", [0, 3]], ["byly", "b\u00fdt", "AUX", [4, 8]], ["obalovan\u00e9", "obalovan\u00fd", "ADJ", [9, 18]], ["\u0159\u00edzky", "\u0159\u00edzek", "NOUN", [19, 24]], ["z", "z", "ADP", [25, 26]], ["kapra", "kapr", "NOUN", [27, 32]], ["i", "i", "CCONJ", [33, 34]], ["z", "z", "ADP", [35, 36]], ["kr\u00e1l\u00edka", "kr\u00e1l\u00edk", "NOUN", [37, 44]], ["a", "a", "CCONJ", [45, 46]], ["k", "k", "ADP", [47, 48]], ["tomu", "ten", "DET", [49, 53]], ["v\u00fdborn\u00fd", "v\u00fdborn\u00fd", "ADJ", [54, 61]], ["bramborov\u00fd", "bramborov\u00fd", "ADJ", [62, 72]], ["sal\u00e1t", "sal\u00e1t", "NOUN", [73, 78]], [".", ".", "PUNCT", [78, 79]]]], ["calgarske-listy_2003_unor_ocr.txt", "D\u00e1le se pod\u00e1val \u010daj a v\u00fdborn\u00fd jablkov\u00fd \u0161tr\u016fdl s rozinkami a o\u0159\u00ed\u0161ky a sko\u0159ic\u00ed.", [["D\u00e1le", "d\u00e1le", "ADV", [0, 4]], ["se", "se", "PRON", [5, 7]], ["pod\u00e1val", "pod\u00e1vat", "VERB", [8, 15]], ["\u010daj", "\u010daj", "NOUN", [16, 19]], ["a", "a", "CCONJ", [20, 21]], ["v\u00fdborn\u00fd", "v\u00fdborn\u00fd", "ADJ", [22, 29]], ["jablkov\u00fd", "jablkov\u00fd", "ADJ", [30, 38]], ["\u0161tr\u016fdl", "\u0161tr\u016fdl", "NOUN", [39, 45]], ["s", "s", "ADP", [46, 47]], ["rozinkami", "rozinka", "NOUN", [48, 57]], ["a", "a", "CCONJ", [58, 59]], ["o\u0159\u00ed\u0161ky", "o\u0159\u00ed\u0161ek", "NOUN", [60, 66]], ["a", "a", "CCONJ", [67, 68]], ["sko\u0159ic\u00ed", "sko\u0159ice", "NOUN", [69, 76]], [".", ".", "PUNCT", [76, 77]]]], ["calgarske-listy_2003_unor_ocr.txt", "Do \u010daje mi asi babi\u010dka cmrndla trochu rumu a vys\u00edlen\u00fd jsem \u0161el sp\u00e1t.", [["Do", "do", "ADP", [0, 2]], ["\u010daje", "\u010daj", "NOUN", [3, 7]], ["mi", "j\u00e1", "PRON", [8, 10]], ["asi", "asi", "PART", [11, 14]], ["babi\u010dka", "babi\u010dka", "NOUN", [15, 22]], ["cmrndla", "cmrnst", "VERB", [23, 30]], ["trochu", "trochu", "ADV", [31, 37]], ["rumu", "rum", "NOUN", [38, 42]], ["a", "a", "CCONJ", [43, 44]], ["vys\u00edlen\u00fd", "vys\u00edlen\u00fd", "ADJ", [45, 53]], ["jsem", "b\u00fdt", "AUX", [54, 58]], ["\u0161el", "j\u00edt", "VERB", [59, 62]], ["sp\u00e1t", "sp\u00e1t", "VERB", [63, 67]], [".", ".", "PUNCT", [67, 68]]]], ["calgarske-listy_2003_unor_ocr.txt", "Na druh\u00fd a dal\u0161\u00ed dny se pak jedlo hodn\u011b v\u00e1no\u010dn\u00edho cukrov\u00ed.", [["Na", "na", "ADP", [0, 2]], ["druh\u00fd", "druh\u00fd", "ADJ", [3, 8]], ["a", "a", "CCONJ", [9, 10]], ["dal\u0161\u00ed", "dal\u0161\u00ed", "ADJ", [11, 16]], ["dny", "den", "NOUN", [17, 20]], ["se", "se", "PRON", [21, 23]], ["pak", "pak", "ADV", [24, 27]], ["jedlo", "jet", "VERB", [28, 33]], ["hodn\u011b", "hodn\u011b", "ADV", [34, 39]], ["v\u00e1no\u010dn\u00edho", "v\u00e1no\u010dn\u00ed", "ADJ", [40, 49]], ["cukrov\u00ed", "cukrov\u00ed", "NOUN", [50, 57]], [".", ".", "PUNCT", [57, 58]]]], ["calgarske-listy_2003_unor_ocr.txt", "Babi\u010dka d\u011blala \u0161kvarkov\u00e9 o\u0159\u00ed\u0161kov\u00e9 pracn\u00fd do poc\u00ednovan\u00fdch plechov\u00fdch formi\u010dek.", [["Babi\u010dka", "babi\u010dka", "NOUN", [0, 7]], ["d\u011blala", "d\u011blat", "VERB", [8, 14]], ["\u0161kvarkov\u00e9", "\u0161kvarkov\u00fd", "ADJ", [15, 24]], ["o\u0159\u00ed\u0161kov\u00e9", "o\u0159\u00ed\u0161kov\u00fd", "ADJ", [25, 33]], ["pracn\u00fd", "pracn\u00fd", "ADJ", [34, 40]], ["do", "do", "ADP", [41, 43]], ["poc\u00ednovan\u00fdch", "poc\u00ednovan\u00fd", "ADJ", [44, 56]], ["plechov\u00fdch", "plechov\u00fd", "ADJ", [57, 67]], ["formi\u010dek", "formi\u010dka", "NOUN", [68, 76]], [".", ".", "PUNCT", [76, 77]]]], ["calgarske-listy_2003_unor_ocr.txt", "To mal\u00e9mu \u010dlov\u011bku sta\u010dily dva takov\u00e9 kousky a byl najeden\u00fd na cel\u00fd den.", [["To", "ten", "DET", [0, 2]], ["mal\u00e9mu", "mal\u00fd", "ADJ", [3, 9]], ["\u010dlov\u011bku", "\u010dlov\u011bk", "NOUN", [10, 17]], ["sta\u010dily", "sta\u010dit", "VERB", [18, 25]], ["dva", "dva", "NUM", [26, 29]], ["takov\u00e9", "takov\u00fd", "DET", [30, 36]], ["kousky", "kousek", "NOUN", [37, 43]], ["a", "a", "CCONJ", [44, 45]], ["byl", "b\u00fdt", "AUX", [46, 49]], ["najeden\u00fd", "najeden\u00fd", "ADJ", [50, 58]], ["na", "na", "ADP", [59, 61]], ["cel\u00fd", "cel\u00fd", "ADJ", [62, 66]], ["den", "den", "NOUN", [67, 70]], [".", ".", "PUNCT", [70, 71]]]], ["calgarske-listy_2003_unor_ocr.txt", "D\u00e1le d\u011blala o\u0159\u00ed\u0161kov\u00e9 rohl\u00ed\u010dky s pr\u00e1\u0161kov\u00fdm cukrem, pln\u011bn\u00e9 kakaov\u00e9 kuli\u010dky s prav\u00fdm tuzemsk\u00fdm rumem, a takov\u00e9 sv\u011btl\u00e9 kol\u00e1\u010dky uprost\u0159ed s kulat\u00fdm ok\u00e9nkem a byly pln\u011bn\u00e9 asi malinovou marmel\u00e1dou.", [["D\u00e1le", "d\u00e1le", "ADV", [0, 4]], ["d\u011blala", "d\u011blat", "VERB", [5, 11]], ["o\u0159\u00ed\u0161kov\u00e9", "o\u0159\u00ed\u0161kov\u00fd", "ADJ", [12, 20]], ["rohl\u00ed\u010dky", "rohl\u00ed\u010dek", "NOUN", [21, 29]], ["s", "s", "ADP", [30, 31]], ["pr\u00e1\u0161kov\u00fdm", "pr\u00e1\u0161kov\u00fd", "ADJ", [32, 41]], ["cukrem", "cukr", "NOUN", [42, 48]], [",", ",", "PUNCT", [48, 49]], ["pln\u011bn\u00e9", "pln\u011bn\u00fd", "ADJ", [50, 56]], ["kakaov\u00e9", "kakaov\u00fd", "ADJ", [57, 64]], ["kuli\u010dky", "kuli\u010dka", "NOUN", [65, 72]], ["s", "s", "ADP", [73, 74]], ["prav\u00fdm", "prav\u00fd", "ADJ", [75, 81]], ["tuzemsk\u00fdm", "tuzemsk\u00fd", "ADJ", [82, 91]], ["rumem", "rum", "NOUN", [92, 97]], [",", ",", "PUNCT", [97, 98]], ["a", "a", "CCONJ", [99, 100]], ["takov\u00e9", "takov\u00fd", "DET", [101, 107]], ["sv\u011btl\u00e9", "sv\u011btl\u00fd", "ADJ", [108, 114]], ["kol\u00e1\u010dky", "kol\u00e1\u010dek", "NOUN", [115, 122]], ["uprost\u0159ed", "uprost\u0159ed", "ADP", [123, 132]], ["s", "s", "ADP", [133, 134]], ["kulat\u00fdm", "kulat\u00fd", "ADJ", [135, 142]], ["ok\u00e9nkem", "ok\u00e9nko", "NOUN", [143, 150]], ["a", "a", "CCONJ", [151, 152]], ["byly", "b\u00fdt", "AUX", [153, 157]], ["pln\u011bn\u00e9", "pln\u011bn\u00fd", "ADJ", [158, 164]], ["asi", "asi", "PART", [165, 168]], ["malinovou", "malinov\u00fd", "ADJ", [169, 178]], ["marmel\u00e1dou", "marmel\u00e1da", "NOUN", [179, 189]], [".", ".", "PUNCT", [189, 190]]]], ["calgarske-listy_2003_unor_ocr.txt", "Pak p\u0159i\u0161el leden a d\u011bti od naproti ze ml\u00fdna musely chodit do bl\u00edzk\u00e9 vsi T\u0159emo\u0161nice do \u0161koly.", [["Pak", "pak", "ADV", [0, 3]], ["p\u0159i\u0161el", "p\u0159ij\u00edt", "VERB", [4, 10]], ["leden", "leden", "NOUN", [11, 16]], ["a", "a", "CCONJ", [17, 18]], ["d\u011bti", "d\u00edt\u011b", "NOUN", [19, 23]], ["od", "od", "ADP", [24, 26]], ["naproti", "naproti", "ADP", [27, 34]], ["ze", "z", "ADP", [35, 37]], ["ml\u00fdna", "ml\u00fdn", "NOUN", [38, 43]], ["musely", "muset", "VERB", [44, 50]], ["chodit", "chodit", "VERB", [51, 57]], ["do", "do", "ADP", [58, 60]], ["bl\u00edzk\u00e9", "bl\u00edzk\u00fd", "ADJ", [61, 67]], ["vsi", "ves", "NOUN", [68, 71]], ["T\u0159emo\u0161nice", "T\u0159emo\u0161nice", "PROPN", [72, 82]], ["do", "do", "ADP", [83, 85]], ["\u0161koly", "\u0161kola", "NOUN", [86, 91]], [".", ".", "PUNCT", [91, 92]]]], ["calgarske-listy_2003_unor_ocr.txt", "Tehd\u00e1 se mi to zd\u00e1lo jako hrozn\u00e1 d\u00e1lka.", [["Tehd\u00e1", "tehd\u00e1", "ADV", [0, 5]], ["se", "se", "PRON", [6, 8]], ["mi", "j\u00e1", "PRON", [9, 11]], ["to", "ten", "DET", [12, 14]], ["zd\u00e1lo", "zd\u00e1t", "VERB", [15, 20]], ["jako", "jako", "SCONJ", [21, 25]], ["hrozn\u00e1", "hrozn\u00fd", "ADJ", [26, 32]], ["d\u00e1lka", "d\u00e1lka", "NOUN", [33, 38]], [".", ".", "PUNCT", [38, 39]]]], ["calgarske-listy_2003_unor_ocr.txt", "Kdysi tam do t\u00e9 dvojt\u0159\u00eddky chodila moje matka a jej\u00ed bratr V\u00e1clav Str\u00e1nsk\u00fd.", [["Kdysi", "kdysi", "ADV", [0, 5]], ["tam", "tam", "ADV", [6, 9]], ["do", "do", "ADP", [10, 12]], ["t\u00e9", "ten", "DET", [13, 15]], ["dvojt\u0159\u00eddky", "dvojt\u0159\u00eddka", "NOUN", [16, 26]], ["chodila", "chodit", "VERB", [27, 34]], ["moje", "m\u016fj", "DET", [35, 39]], ["matka", "matka", "NOUN", [40, 45]], ["a", "a", "CCONJ", [46, 47]], ["jej\u00ed", "jeho", "DET", [48, 52]], ["bratr", "bratr", "NOUN", [53, 58]], ["V\u00e1clav", "V\u00e1clav", "PROPN", [59, 65]], ["Str\u00e1nsk\u00fd", "Str\u00e1nsk\u00fd", "PROPN", [66, 74]], [".", ".", "PUNCT", [74, 75]]]], ["calgarske-listy_2003_unor_ocr.txt", "Ve ml\u00fdn\u011b byla doma je\u0161t\u011b p\u0159ed\u0161koln\u00ed L\u00edda, byla je\u0161t\u011b men\u0161\u00ed ne\u017e j\u00e1, a tak s n\u00ed nebyla \u017e\u00e1dn\u00e1 z\u00e1bava.", [["Ve", "v", "ADP", [0, 2]], ["ml\u00fdn\u011b", "ml\u00fdn", "NOUN", [3, 8]], ["byla", "b\u00fdt", "AUX", [9, 13]], ["doma", "doma", "ADV", [14, 18]], ["je\u0161t\u011b", "je\u0161t\u011b", "ADV", [19, 24]], ["p\u0159ed\u0161koln\u00ed", "p\u0159ed\u0161koln\u00ed", "ADJ", [25, 35]], ["L\u00edda", "L\u00edda", "PROPN", [36, 40]], [",", ",", "PUNCT", [40, 41]], ["byla", "b\u00fdt", "AUX", [42, 46]], ["je\u0161t\u011b", "je\u0161t\u011b", "ADV", [47, 52]], ["men\u0161\u00ed", "mal\u00fd", "ADJ", [53, 58]], ["ne\u017e", "ne\u017e", "SCONJ", [59, 62]], ["j\u00e1", "j\u00e1", "PRON", [63, 65]], [",", ",", "PUNCT", [65, 66]], ["a", "a", "CCONJ", [67, 68]], ["tak", "tak", "ADV", [69, 72]], ["s", "s", "ADP", [73, 74]], ["n\u00ed", "on", "PRON", [75, 77]], ["nebyla", "b\u00fdt", "AUX", [78, 84]], ["\u017e\u00e1dn\u00e1", "\u017e\u00e1dn\u00fd", "DET", [85, 90]], ["z\u00e1bava", "z\u00e1bava", "NOUN", [91, 97]], [".", ".", "PUNCT", [97, 98]]]], ["calgarske-listy_2003_unor_ocr.txt", "Samotn\u00e9ho m\u011b s\u00e1\u0148kov\u00e1n\u00ed moc nebavilo.", [["Samotn\u00e9ho", "samotn\u00fd", "ADJ", [0, 9]], ["m\u011b", "j\u00e1", "PRON", [10, 12]], ["s\u00e1\u0148kov\u00e1n\u00ed", "s\u00e1\u0148kov\u00e1n\u00ed", "NOUN", [13, 22]], ["moc", "moc", "ADV", [23, 26]], ["nebavilo", "bavit", "VERB", [27, 35]], [".", ".", "PUNCT", [35, 36]]]], ["calgarske-listy_2003_unor_ocr.txt", "Ale na \u0159adu p\u0159i\u0161la velice zaj\u00edmav\u00e1 operace.", [["Ale", "ale", "CCONJ", [0, 3]], ["na", "na", "ADP", [4, 6]], ["\u0159adu", "\u0159ada", "NOUN", [7, 11]], ["p\u0159i\u0161la", "p\u0159ij\u00edt", "VERB", [12, 18]], ["velice", "velice", "ADV", [19, 25]], ["zaj\u00edmav\u00e1", "zaj\u00edmav\u00fd", "ADJ", [26, 34]], ["operace", "operace", "NOUN", [35, 42]], [".", ".", "PUNCT", [42, 43]]]], ["calgarske-listy_2003_unor_ocr.txt", "Mrzlo jen to pra\u0161t\u011blo, a tak na ml\u00fdnsk\u00e9m n\u00e1honu se vytvo\u0159il asi 30 cm siln\u00fd led.", [["Mrzlo", "mrznout", "VERB", [0, 5]], ["jen", "jen", "ADV", [6, 9]], ["to", "ten", "DET", [10, 12]], ["pra\u0161t\u011blo", "pra\u0161t\u011bt", "VERB", [13, 21]], [",", ",", "PUNCT", [21, 22]], ["a", "a", "CCONJ", [23, 24]], ["tak", "tak", "ADV", [25, 28]], ["na", "na", "ADP", [29, 31]], ["ml\u00fdnsk\u00e9m", "ml\u00fdnsk\u00fd", "ADJ", [32, 40]], ["n\u00e1honu", "n\u00e1hon", "NOUN", [41, 47]], ["se", "se", "PRON", [48, 50]], ["vytvo\u0159il", "vytvo\u0159it", "VERB", [51, 59]], ["asi", "asi", "PART", [60, 63]], ["30", "30", "NUM", [64, 66]], ["cm", "centimetr", "NOUN", [67, 69]], ["siln\u00fd", "siln\u00fd", "ADJ", [70, 75]], ["led", "led", "NOUN", [76, 79]], [".", ".", "PUNCT", [79, 80]]]], ["calgarske-listy_2003_unor_ocr.txt", "D\u011bda najal \u010detu pomocn\u00edk\u016f ze vsi, na ledov\u00e1n\u00ed.", [["D\u011bda", "d\u011bda", "NOUN", [0, 4]], ["najal", "najmout", "VERB", [5, 10]], ["\u010detu", "\u010deta", "NOUN", [11, 15]], ["pomocn\u00edk\u016f", "pomocn\u00edk", "NOUN", [16, 25]], ["ze", "z", "ADP", [26, 28]], ["vsi", "ves", "NOUN", [29, 32]], [",", ",", "PUNCT", [32, 33]], ["na", "na", "ADP", [34, 36]], ["ledov\u00e1n\u00ed", "ledov\u00e1n\u00ed", "NOUN", [37, 45]], [".", ".", "PUNCT", [45, 46]]]], ["calgarske-listy_2003_unor_ocr.txt", "Pod na\u0161\u00edm velik\u00fdm staven\u00edm a i pod st\u00e1jemi byly ohromn\u00e9 klenut\u00e9 sklepy, do kter\u00fdch bylo t\u0159eba v zim\u011b navozit ledov\u00e9 kry.", [["Pod", "pod", "ADP", [0, 3]], ["na\u0161\u00edm", "n\u00e1\u0161", "DET", [4, 9]], ["velik\u00fdm", "velik\u00fd", "ADJ", [10, 17]], ["staven\u00edm", "staven\u00ed", "NOUN", [18, 26]], ["a", "a", "CCONJ", [27, 28]], ["i", "i", "CCONJ", [29, 30]], ["pod", "pod", "ADP", [31, 34]], ["st\u00e1jemi", "st\u00e1j", "NOUN", [35, 42]], ["byly", "b\u00fdt", "AUX", [43, 47]], ["ohromn\u00e9", "ohromn\u00fd", "ADJ", [48, 55]], ["klenut\u00e9", "klenut\u00fd", "ADJ", [56, 63]], ["sklepy", "sklep", "NOUN", [64, 70]], [",", ",", "PUNCT", [70, 71]], ["do", "do", "ADP", [72, 74]], ["kter\u00fdch", "kter\u00fd", "DET", [75, 82]], ["bylo", "b\u00fdt", "AUX", [83, 87]], ["t\u0159eba", "t\u0159eba", "ADV", [88, 93]], ["v", "v", "ADP", [94, 95]], ["zim\u011b", "zima", "NOUN", [96, 100]], ["navozit", "navozit", "VERB", [101, 108]], ["ledov\u00e9", "ledov\u00fd", "ADJ", [109, 115]], ["kry", "kra", "NOUN", [116, 119]], [".", ".", "PUNCT", [119, 120]]]], ["calgarske-listy_2003_unor_ocr.txt", "Tyto ohromn\u00e9 sklepy zde byly postaveny pro pot\u0159ebu z\u00e1jezdn\u00edho hostince, kde se u ledu v l\u00e9t\u011b chladilo pivo a potraviny pro cestuj\u00edc\u00ed a formany.", [["Tyto", "tento", "DET", [0, 4]], ["ohromn\u00e9", "ohromn\u00fd", "ADJ", [5, 12]], ["sklepy", "sklep", "NOUN", [13, 19]], ["zde", "zde", "ADV", [20, 23]], ["byly", "b\u00fdt", "AUX", [24, 28]], ["postaveny", "postaven\u00fd", "ADJ", [29, 38]], ["pro", "pro", "ADP", [39, 42]], ["pot\u0159ebu", "pot\u0159eba", "NOUN", [43, 50]], ["z\u00e1jezdn\u00edho", "z\u00e1jezdn\u00ed", "ADJ", [51, 61]], ["hostince", "hostinec", "NOUN", [62, 70]], [",", ",", "PUNCT", [70, 71]], ["kde", "kde", "ADV", [72, 75]], ["se", "se", "PRON", [76, 78]], ["u", "u", "ADP", [79, 80]], ["ledu", "led", "NOUN", [81, 85]], ["v", "v", "ADP", [86, 87]], ["l\u00e9t\u011b", "l\u00e9to", "NOUN", [88, 92]], ["chladilo", "chladit", "VERB", [93, 101]], ["pivo", "pivo", "NOUN", [102, 106]], ["a", "a", "CCONJ", [107, 108]], ["potraviny", "potravina", "NOUN", [109, 118]], ["pro", "pro", "ADP", [119, 122]], ["cestuj\u00edc\u00ed", "cestuj\u00edc\u00ed", "ADJ", [123, 132]], ["a", "a", "CCONJ", [133, 134]], ["formany", "formana", "NOUN", [135, 142]], [".", ".", "PUNCT", [142, 143]]]], ["calgarske-listy_2003_unor_ocr.txt", "Speci\u00e1ln\u00edmi zob\u00e1kovit\u00fdmi pilami se led na\u0159ezal do pravideln\u00fdch \u010dtverc\u016f, nalo\u017eil na san\u011b a p\u0159ivezl k na\u0161im sklep\u016fm.", [["Speci\u00e1ln\u00edmi", "speci\u00e1ln\u00ed", "ADJ", [0, 11]], ["zob\u00e1kovit\u00fdmi", "zob\u00e1kovit\u00fd", "ADJ", [12, 24]], ["pilami", "pila", "NOUN", [25, 31]], ["se", "se", "PRON", [32, 34]], ["led", "led", "NOUN", [35, 38]], ["na\u0159ezal", "na\u0159ezat", "VERB", [39, 46]], ["do", "do", "ADP", [47, 49]], ["pravideln\u00fdch", "pravideln\u00fd", "ADJ", [50, 62]], ["\u010dtverc\u016f", "\u010dtverec", "NOUN", [63, 70]], [",", ",", "PUNCT", [70, 71]], ["nalo\u017eil", "nalo\u017eit", "VERB", [72, 79]], ["na", "na", "ADP", [80, 82]], ["san\u011b", "san\u011b", "NOUN", [83, 87]], ["a", "a", "CCONJ", [88, 89]], ["p\u0159ivezl", "p\u0159iv\u00e9zt", "VERB", [90, 97]], ["k", "k", "ADP", [98, 99]], ["na\u0161im", "n\u00e1\u0161", "DET", [100, 105]], ["sklep\u016fm", "sklep", "NOUN", [106, 113]], [".", ".", "PUNCT", [113, 114]]]], ["calgarske-listy_2003_unor_ocr.txt", "Po ramp\u011b se kry spustily dol\u016f a ukl\u00e1daly do v\u00fd\u0161e 150 cm a izolovaly posypem slam\u011bn\u00e9 \u0159ezanky, na zpomalen\u00ed t\u00e1n\u00ed ledu.", [["Po", "po", "ADP", [0, 2]], ["ramp\u011b", "rampa", "NOUN", [3, 8]], ["se", "se", "PRON", [9, 11]], ["kry", "kra", "NOUN", [12, 15]], ["spustily", "spustit", "VERB", [16, 24]], ["dol\u016f", "dol\u016f", "ADV", [25, 29]], ["a", "a", "CCONJ", [30, 31]], ["ukl\u00e1daly", "ukl\u00e1dat", "VERB", [32, 40]], ["do", "do", "ADP", [41, 43]], ["v\u00fd\u0161e", "v\u00fd\u0161e", "NOUN", [44, 48]], ["150", "150", "NUM", [49, 52]], ["cm", "centimetr", "NOUN", [53, 55]], ["a", "a", "CCONJ", [56, 57]], ["izolovaly", "izolovat", "VERB", [58, 67]], ["posypem", "posyp", "NOUN", [68, 75]], ["slam\u011bn\u00e9", "slam\u011bn\u00fd", "ADJ", [76, 83]], ["\u0159ezanky", "\u0159ezanka", "NOUN", [84, 91]], [",", ",", "PUNCT", [91, 92]], ["na", "na", "ADP", [93, 95]], ["zpomalen\u00ed", "zpomalen\u00ed", "NOUN", [96, 105]], ["t\u00e1n\u00ed", "t\u00e1n\u00ed", "NOUN", [106, 110]], ["ledu", "led", "NOUN", [111, 115]], [".", ".", "PUNCT", [115, 116]]]], ["calgarske-listy_2003_unor_ocr.txt", "I pro n\u00e1s tato ohromn\u00e1 lednice slou\u017eila cel\u00e9 l\u00e9to.", [["I", "i", "CCONJ", [0, 1]], ["pro", "pro", "ADP", [2, 5]], ["n\u00e1s", "my", "PRON", [6, 9]], ["tato", "tento", "DET", [10, 14]], ["ohromn\u00e1", "ohromn\u00fd", "ADJ", [15, 22]], ["lednice", "lednice", "NOUN", [23, 30]], ["slou\u017eila", "slou\u017eit", "VERB", [31, 39]], ["cel\u00e9", "cel\u00fd", "ADJ", [40, 44]], ["l\u00e9to", "l\u00e9to", "NOUN", [45, 49]], [".", ".", "PUNCT", [49, 50]]]], ["calgarske-listy_2003_unor_ocr.txt", "V\u00edm, \u017ee tam babi\u010dka m\u011bla hlin\u011bn\u00e9 glazovan\u00e9 kraj\u00e1\u010de pln\u00e9 ml\u00e9ka a smetany.", [["V\u00edm", "v\u011bd\u011bt", "VERB", [0, 3]], [",", ",", "PUNCT", [3, 4]], ["\u017ee", "\u017ee", "SCONJ", [5, 7]], ["tam", "tam", "ADV", [8, 11]], ["babi\u010dka", "babi\u010dka", "NOUN", [12, 19]], ["m\u011bla", "m\u00edt", "VERB", [20, 24]], ["hlin\u011bn\u00e9", "hlin\u011bn\u00fd", "ADJ", [25, 32]], ["glazovan\u00e9", "glazovan\u00fd", "ADJ", [33, 42]], ["kraj\u00e1\u010de", "kraj\u00e1\u010d", "NOUN", [43, 50]], ["pln\u00e9", "pln\u00fd", "ADJ", [51, 55]], ["ml\u00e9ka", "ml\u00e9ko", "NOUN", [56, 61]], ["a", "a", "CCONJ", [62, 63]], ["smetany", "smetana", "NOUN", [64, 71]], [".", ".", "PUNCT", [71, 72]]]], ["calgarske-listy_2003_unor_ocr.txt", "Ze smetany se stloukalo v d\u0159ev\u011bn\u00e9 m\u00e1selnici m\u00e1slo.", [["Ze", "z", "ADP", [0, 2]], ["smetany", "smetana", "NOUN", [3, 10]], ["se", "se", "PRON", [11, 13]], ["stloukalo", "stloukat", "VERB", [14, 23]], ["v", "v", "ADP", [24, 25]], ["d\u0159ev\u011bn\u00e9", "d\u0159ev\u011bn\u00fd", "ADJ", [26, 33]], ["m\u00e1selnici", "m\u00e1selnice", "NOUN", [34, 43]], ["m\u00e1slo", "m\u00e1slo", "NOUN", [44, 49]], [".", ".", "PUNCT", [49, 50]]]], ["calgarske-listy_2003_unor_ocr.txt", "Kdy\u017e d\u011bda p\u0159inesl na ned\u011bli z Divi\u0161ova n\u011bjak\u00e9 maso, tak se tam ukl\u00e1dalo spolu s m\u00e1slem.", [["Kdy\u017e", "kdy\u017e", "SCONJ", [0, 4]], ["d\u011bda", "d\u011bda", "NOUN", [5, 9]], ["p\u0159inesl", "p\u0159in\u00e9st", "VERB", [10, 17]], ["na", "na", "ADP", [18, 20]], ["ned\u011bli", "ned\u011ble", "NOUN", [21, 27]], ["z", "z", "ADP", [28, 29]], ["Divi\u0161ova", "Divi\u0161\u016fv", "ADJ", [30, 38]], ["n\u011bjak\u00e9", "n\u011bjak\u00fd", "DET", [39, 45]], ["maso", "maso", "NOUN", [46, 50]], [",", ",", "PUNCT", [50, 51]], ["tak", "tak", "ADV", [52, 55]], ["se", "se", "PRON", [56, 58]], ["tam", "tam", "ADV", [59, 62]], ["ukl\u00e1dalo", "ukl\u00e1dat", "VERB", [63, 71]], ["spolu", "spolu", "ADV", [72, 77]], ["s", "s", "ADP", [78, 79]], ["m\u00e1slem", "m\u00e1slo", "NOUN", [80, 86]], [".", ".", "PUNCT", [86, 87]]]], ["calgarske-listy_2003_unor_ocr.txt", "V letn\u00ed dob\u011b se tam ukl\u00e1dalo pivo v hn\u011bd\u00fdch p\u016fllitrov\u00fdch lahv\u00edch s dr\u00e1t\u011bn\u00fdm patentn\u00edm uz\u00e1v\u011brem.", [["V", "v", "ADP", [0, 1]], ["letn\u00ed", "letn\u00ed", "ADJ", [2, 7]], ["dob\u011b", "doba", "NOUN", [8, 12]], ["se", "se", "PRON", [13, 15]], ["tam", "tam", "ADV", [16, 19]], ["ukl\u00e1dalo", "ukl\u00e1dat", "VERB", [20, 28]], ["pivo", "pivo", "NOUN", [29, 33]], ["v", "v", "ADP", [34, 35]], ["hn\u011bd\u00fdch", "hn\u011bd\u00fd", "ADJ", [36, 43]], ["p\u016fllitrov\u00fdch", "p\u016fllitrov\u00fd", "ADJ", [44, 56]], ["lahv\u00edch", "lahev", "NOUN", [57, 64]], ["s", "s", "ADP", [65, 66]], ["dr\u00e1t\u011bn\u00fdm", "dr\u00e1t\u011bn\u00fd", "ADJ", [67, 75]], ["patentn\u00edm", "patentn\u00ed", "ADJ", [76, 85]], ["uz\u00e1v\u011brem", "uz\u00e1v\u011br", "NOUN", [86, 94]], [".", ".", "PUNCT", [94, 95]]]], ["calgarske-listy_2003_unor_ocr.txt", "Pivo se pod\u00e1valo na poli k sva\u010din\u00e1m a ob\u011bd\u016fm p\u0159i sek\u00e1n\u00ed sena, jetele a ve \u017en\u00edch.", [["Pivo", "pivo", "NOUN", [0, 4]], ["se", "se", "PRON", [5, 7]], ["pod\u00e1valo", "pod\u00e1vat", "VERB", [8, 16]], ["na", "na", "ADP", [17, 19]], ["poli", "pole", "NOUN", [20, 24]], ["k", "k", "ADP", [25, 26]], ["sva\u010din\u00e1m", "sva\u010dina", "NOUN", [27, 35]], ["a", "a", "CCONJ", [36, 37]], ["ob\u011bd\u016fm", "ob\u011bd", "NOUN", [38, 44]], ["p\u0159i", "p\u0159i", "ADP", [45, 48]], ["sek\u00e1n\u00ed", "sek\u00e1n\u00ed", "NOUN", [49, 55]], ["sena", "seno", "NOUN", [56, 60]], [",", ",", "PUNCT", [60, 61]], ["jetele", "jetel", "NOUN", [62, 68]], ["a", "a", "CCONJ", [69, 70]], ["ve", "v", "ADP", [71, 73]], ["\u017en\u00edch", "\u017en\u00edch", "NOUN", [74, 79]], [".", ".", "PUNCT", [79, 80]]]], ["calgarske-listy_2003_unor_ocr.txt", "Pamatuji se, \u017ee n\u00e1mezdn\u00ed pracovn\u00edci z nedalek\u00e9 vsi, r\u00e1di p\u0159ich\u00e1zeli pracovat u d\u011bdy na pol\u00edch, proto\u017ee je dob\u0159e platili a hostili.", [["Pamatuji", "pamatovat", "VERB", [0, 8]], ["se", "se", "PRON", [9, 11]], [",", ",", "PUNCT", [11, 12]], ["\u017ee", "\u017ee", "SCONJ", [13, 15]], ["n\u00e1mezdn\u00ed", "n\u00e1mezdn\u00ed", "ADJ", [16, 24]], ["pracovn\u00edci", "pracovn\u00edk", "NOUN", [25, 35]], ["z", "z", "ADP", [36, 37]], ["nedalek\u00e9", "dalek\u00fd", "ADJ", [38, 46]], ["vsi", "ves", "NOUN", [47, 50]], [",", ",", "PUNCT", [50, 51]], ["r\u00e1di", "r\u00e1d", "ADJ", [52, 56]], ["p\u0159ich\u00e1zeli", "p\u0159ich\u00e1zet", "VERB", [57, 67]], ["pracovat", "pracovat", "VERB", [68, 76]], ["u", "u", "ADP", [77, 78]], ["d\u011bdy", "d\u011bda", "NOUN", [79, 83]], ["na", "na", "ADP", [84, 86]], ["pol\u00edch", "pole", "NOUN", [87, 93]], [",", ",", "PUNCT", [93, 94]], ["proto\u017ee", "proto\u017ee", "SCONJ", [95, 102]], ["je", "on", "PRON", [103, 105]], ["dob\u0159e", "dob\u0159e", "ADV", [106, 111]], ["platili", "platit", "VERB", [112, 119]], ["a", "a", "CCONJ", [120, 121]], ["hostili", "hostit", "VERB", [122, 129]], [".", ".", "PUNCT", [129, 130]]]], ["calgarske-listy_2003_unor_ocr.txt", "D\u011bda m\u011bl velmi vysokou penzi.", [["D\u011bda", "d\u011bda", "NOUN", [0, 4]], ["m\u011bl", "m\u00edt", "VERB", [5, 8]], ["velmi", "velmi", "ADV", [9, 14]], ["vysokou", "vysok\u00fd", "ADJ", [15, 22]], ["penzi", "penze", "NOUN", [23, 28]], [".", ".", "PUNCT", [28, 29]]]], ["calgarske-listy_2003_unor_ocr.txt", "Pracoval kdysi v jedn\u00e9 pra\u017esk\u00e9 bance jako prokurista, co\u017e byla velmi vysok\u00e1 funkce, asi jako dne\u0161n\u00ed mana\u017e\u00e9r.", [["Pracoval", "pracovat", "VERB", [0, 8]], ["kdysi", "kdysi", "ADV", [9, 14]], ["v", "v", "ADP", [15, 16]], ["jedn\u00e9", "jeden", "NUM", [17, 22]], ["pra\u017esk\u00e9", "pra\u017esk\u00fd", "ADJ", [23, 30]], ["bance", "banka", "NOUN", [31, 36]], ["jako", "jako", "SCONJ", [37, 41]], ["prokurista", "prokurista", "NOUN", [42, 52]], [",", ",", "PUNCT", [52, 53]], ["co\u017e", "co\u017e", "PRON", [54, 57]], ["byla", "b\u00fdt", "AUX", [58, 62]], ["velmi", "velmi", "ADV", [63, 68]], ["vysok\u00e1", "vysok\u00fd", "ADJ", [69, 75]], ["funkce", "funkce", "NOUN", [76, 82]], [",", ",", "PUNCT", [82, 83]], ["asi", "asi", "PART", [84, 87]], ["jako", "jako", "SCONJ", [88, 92]], ["dne\u0161n\u00ed", "dne\u0161n\u00ed", "ADJ", [93, 99]], ["mana\u017e\u00e9r", "mana\u017e\u00e9r", "NOUN", [100, 107]], [".", ".", "PUNCT", [107, 108]]]], ["calgarske-listy_2003_unor_ocr.txt", "Jejich banka m\u011bla od rakousk\u00e9 c\u00edsa\u0159sk\u00e9 vl\u00e1dy z V\u00eddn\u011b koupen\u00fd monopol na dovoz zelen\u00e9 k\u00e1vy pro cel\u00e9 rakousk\u00e9 mocn\u00e1\u0159stv\u00ed.", [["Jejich", "jeho", "DET", [0, 6]], ["banka", "banka", "NOUN", [7, 12]], ["m\u011bla", "m\u00edt", "VERB", [13, 17]], ["od", "od", "ADP", [18, 20]], ["rakousk\u00e9", "rakousk\u00fd", "ADJ", [21, 29]], ["c\u00edsa\u0159sk\u00e9", "c\u00edsa\u0159sk\u00fd", "ADJ", [30, 38]], ["vl\u00e1dy", "vl\u00e1da", "NOUN", [39, 44]], ["z", "z", "ADP", [45, 46]], ["V\u00eddn\u011b", "V\u00edde\u0148", "PROPN", [47, 52]], ["koupen\u00fd", "koupen\u00fd", "ADJ", [53, 60]], ["monopol", "monopol", "NOUN", [61, 68]], ["na", "na", "ADP", [69, 71]], ["dovoz", "dovoz", "NOUN", [72, 77]], ["zelen\u00e9", "zelen\u00fd", "ADJ", [78, 84]], ["k\u00e1vy", "k\u00e1va", "NOUN", [85, 89]], ["pro", "pro", "ADP", [90, 93]], ["cel\u00e9", "cel\u00fd", "ADJ", [94, 98]], ["rakousk\u00e9", "rakousk\u00fd", "ADJ", [99, 107]], ["mocn\u00e1\u0159stv\u00ed", "mocn\u00e1\u0159stv\u00ed", "NOUN", [108, 118]], [".", ".", "PUNCT", [118, 119]]]], ["calgarske-listy_2003_unor_ocr.txt", "D\u011bda um\u011bl portugalsky, a tak m\u011bl na starosti jejich nejv\u00fdnosn\u011bj\u0161\u00ed obchod s brazilskou k\u00e1vou.", [["D\u011bda", "d\u011bda", "NOUN", [0, 4]], ["um\u011bl", "um\u011bt", "VERB", [5, 9]], ["portugalsky", "portugalsky", "ADV", [10, 21]], [",", ",", "PUNCT", [21, 22]], ["a", "a", "CCONJ", [23, 24]], ["tak", "tak", "ADV", [25, 28]], ["m\u011bl", "m\u00edt", "VERB", [29, 32]], ["na", "na", "ADP", [33, 35]], ["starosti", "starost", "NOUN", [36, 44]], ["jejich", "jeho", "DET", [45, 51]], ["nejv\u00fdnosn\u011bj\u0161\u00ed", "v\u00fdnosn\u00fd", "ADJ", [52, 65]], ["obchod", "obchod", "NOUN", [66, 72]], ["s", "s", "ADP", [73, 74]], ["brazilskou", "brazilsk\u00fd", "ADJ", [75, 85]], ["k\u00e1vou", "k\u00e1va", "NOUN", [86, 91]], [".", ".", "PUNCT", [91, 92]]]], ["calgarske-listy_2003_unor_ocr.txt", "D\u00e1le um\u011bl n\u011bmecky a italsky, a v\u00edm, \u017ee psal a \u010detl dob\u0159e \u010desky.", [["D\u00e1le", "d\u00e1le", "ADV", [0, 4]], ["um\u011bl", "um\u011bt", "VERB", [5, 9]], ["n\u011bmecky", "n\u011bmecky", "ADV", [10, 17]], ["a", "a", "CCONJ", [18, 19]], ["italsky", "italsky", "ADV", [20, 27]], [",", ",", "PUNCT", [27, 28]], ["a", "a", "CCONJ", [29, 30]], ["v\u00edm", "v\u011bd\u011bt", "VERB", [31, 34]], [",", ",", "PUNCT", [34, 35]], ["\u017ee", "\u017ee", "SCONJ", [36, 38]], ["psal", "ps\u00e1t", "VERB", [39, 43]], ["a", "a", "CCONJ", [44, 45]], ["\u010detl", "\u010d\u00edst", "VERB", [46, 50]], ["dob\u0159e", "dob\u0159e", "ADV", [51, 56]], ["\u010desky", "\u010desky", "ADV", [57, 62]], [".", ".", "PUNCT", [62, 63]]]], ["calgarske-listy_2003_unor_ocr.txt", "B\u011bhem prvn\u00ed sv\u011btov\u00e9 v\u00e1lky byl na front\u011b a jako plukovn\u00edk rakousk\u00e9 arm\u00e1dy byl tak\u00e9 velitelem vojensk\u00e9ho okrsku Boka Kotorsk\u00e1.", [["B\u011bhem", "b\u011bhem", "ADP", [0, 5]], ["prvn\u00ed", "prvn\u00ed", "ADJ", [6, 11]], ["sv\u011btov\u00e9", "sv\u011btov\u00fd", "ADJ", [12, 19]], ["v\u00e1lky", "v\u00e1lka", "NOUN", [20, 25]], ["byl", "b\u00fdt", "AUX", [26, 29]], ["na", "na", "ADP", [30, 32]], ["front\u011b", "fronta", "NOUN", [33, 39]], ["a", "a", "CCONJ", [40, 41]], ["jako", "jako", "SCONJ", [42, 46]], ["plukovn\u00edk", "plukovn\u00edk", "NOUN", [47, 56]], ["rakousk\u00e9", "rakousk\u00fd", "ADJ", [57, 65]], ["arm\u00e1dy", "arm\u00e1da", "NOUN", [66, 72]], ["byl", "b\u00fdt", "AUX", [73, 76]], ["tak\u00e9", "tak\u00e9", "ADV", [77, 81]], ["velitelem", "velitel", "NOUN", [82, 91]], ["vojensk\u00e9ho", "vojensk\u00fd", "ADJ", [92, 102]], ["okrsku", "okrsek", "NOUN", [103, 109]], ["Boka", "Boka", "PROPN", [110, 114]], ["Kotorsk\u00e1", "Kotorsk\u00e1", "PROPN", [115, 123]], [".", ".", "PUNCT", [123, 124]]]], ["calgarske-listy_2003_unor_ocr.txt", "V tomto n\u00e1dhern\u00e9m mo\u0159sk\u00e9m fjordu na dalmatsk\u00e9m pob\u0159e\u017e\u00ed se pr\u00fd schov\u00e1vala rakousk\u00e1 n\u00e1mo\u0159n\u00ed flotila.", [["V", "v", "ADP", [0, 1]], ["tomto", "tento", "DET", [2, 7]], ["n\u00e1dhern\u00e9m", "n\u00e1dhern\u00fd", "ADJ", [8, 17]], ["mo\u0159sk\u00e9m", "mo\u0159sk\u00fd", "ADJ", [18, 25]], ["fjordu", "fjord", "NOUN", [26, 32]], ["na", "na", "ADP", [33, 35]], ["dalmatsk\u00e9m", "dalmatsk\u00fd", "ADJ", [36, 46]], ["pob\u0159e\u017e\u00ed", "pob\u0159e\u017e\u00ed", "NOUN", [47, 54]], ["se", "se", "PRON", [55, 57]], ["pr\u00fd", "pr\u00fd", "PART", [58, 61]], ["schov\u00e1vala", "schov\u00e1vat", "VERB", [62, 72]], ["rakousk\u00e1", "rakousk\u00fd", "ADJ", [73, 81]], ["n\u00e1mo\u0159n\u00ed", "n\u00e1mo\u0159n\u00ed", "ADJ", [82, 89]], ["flotila", "flotila", "NOUN", [90, 97]], [".", ".", "PUNCT", [97, 98]]]], ["calgarske-listy_2003_unor_ocr.txt", "D\u011bda asi byl dost horliv\u00fdm plukovn\u00edkem a n\u011bkde se motal moc bl\u00edzko frontov\u00e9 linie, kde ho zas\u00e1hl d\u011blost\u0159eleck\u00fd \u0161rapnel do b\u0159icha.", [["D\u011bda", "d\u011bda", "NOUN", [0, 4]], ["asi", "asi", "PART", [5, 8]], ["byl", "b\u00fdt", "AUX", [9, 12]], ["dost", "dost", "ADV", [13, 17]], ["horliv\u00fdm", "horliv\u00fd", "ADJ", [18, 26]], ["plukovn\u00edkem", "plukovn\u00edk", "NOUN", [27, 38]], ["a", "a", "CCONJ", [39, 40]], ["n\u011bkde", "n\u011bkde", "ADV", [41, 46]], ["se", "se", "PRON", [47, 49]], ["motal", "motat", "VERB", [50, 55]], ["moc", "moc", "ADV", [56, 59]], ["bl\u00edzko", "bl\u00edzko", "ADV", [60, 66]], ["frontov\u00e9", "frontov\u00fd", "ADJ", [67, 75]], ["linie", "linie", "NOUN", [76, 81]], [",", ",", "PUNCT", [81, 82]], ["kde", "kde", "ADV", [83, 86]], ["ho", "on", "PRON", [87, 89]], ["zas\u00e1hl", "zas\u00e1hnout", "VERB", [90, 96]], ["d\u011blost\u0159eleck\u00fd", "d\u011blost\u0159eleck\u00fd", "ADJ", [97, 110]], ["\u0161rapnel", "\u0161rapnel", "NOUN", [111, 118]], ["do", "do", "ADP", [119, 121]], ["b\u0159icha", "b\u0159icho", "NOUN", [122, 128]], [".", ".", "PUNCT", [128, 129]]]], ["calgarske-listy_2003_unor_ocr.txt", "V d\u016fsledku toho zran\u011bn\u00ed m\u011bl velmi bolestiv\u00e9 pot\u00ed\u017ee.", [["V", "v", "ADP", [0, 1]], ["d\u016fsledku", "d\u016fsledek", "NOUN", [2, 10]], ["toho", "ten", "DET", [11, 15]], ["zran\u011bn\u00ed", "zran\u011bn\u00ed", "NOUN", [16, 23]], ["m\u011bl", "m\u00edt", "VERB", [24, 27]], ["velmi", "velmi", "ADV", [28, 33]], ["bolestiv\u00e9", "bolestiv\u00fd", "ADJ", [34, 43]], ["pot\u00ed\u017ee", "pot\u00ed\u017e", "NOUN", [44, 50]], [".", ".", "PUNCT", [50, 51]]]], ["calgarske-listy_2003_unor_ocr.txt", "Pr\u00fd mu ti poln\u00ed fel\u010da\u0159i p\u0159i operaci \u0161patn\u011b slo\u017eili st\u0159eva do b\u0159icha a to ho moc zlobilo.", [["Pr\u00fd", "pr\u00fd", "PART", [0, 3]], ["mu", "on", "PRON", [4, 6]], ["ti", "ten", "DET", [7, 9]], ["poln\u00ed", "poln\u00ed", "ADJ", [10, 15]], ["fel\u010da\u0159i", "fel\u010da\u0159", "NOUN", [16, 23]], ["p\u0159i", "p\u0159i", "ADP", [24, 27]], ["operaci", "operace", "NOUN", [28, 35]], ["\u0161patn\u011b", "\u0161patn\u011b", "ADV", [36, 42]], ["slo\u017eili", "slo\u017eit", "VERB", [43, 50]], ["st\u0159eva", "st\u0159evo", "NOUN", [51, 57]], ["do", "do", "ADP", [58, 60]], ["b\u0159icha", "b\u0159icho", "NOUN", [61, 67]], ["a", "a", "CCONJ", [68, 69]], ["to", "ten", "DET", [70, 72]], ["ho", "on", "PRON", [73, 75]], ["moc", "moc", "ADV", [76, 79]], ["zlobilo", "zlobit", "VERB", [80, 87]], [".", ".", "PUNCT", [87, 88]]]], ["calgarske-listy_2003_unor_ocr.txt", "M\u011bl velk\u00e9 mno\u017estv\u00ed odborn\u00fdch knih o ovocn\u00e1\u0159stv\u00ed, do kter\u00e9ho asi bl\u00e1hov\u00e9 nacpal velmi hodn\u011b pen\u011bz.", [["M\u011bl", "m\u00edt", "VERB", [0, 3]], ["velk\u00e9", "velk\u00fd", "ADJ", [4, 9]], ["mno\u017estv\u00ed", "mno\u017estv\u00ed", "NOUN", [10, 18]], ["odborn\u00fdch", "odborn\u00fd", "ADJ", [19, 28]], ["knih", "kniha", "NOUN", [29, 33]], ["o", "o", "ADP", [34, 35]], ["ovocn\u00e1\u0159stv\u00ed", "ovocn\u00e1\u0159stv\u00ed", "NOUN", [36, 47]], [",", ",", "PUNCT", [47, 48]], ["do", "do", "ADP", [49, 51]], ["kter\u00e9ho", "kter\u00fd", "DET", [52, 59]], ["asi", "asi", "PART", [60, 63]], ["bl\u00e1hov\u00e9", "bl\u00e1hov\u00fd", "ADJ", [64, 71]], ["nacpal", "nacpat", "VERB", [72, 78]], ["velmi", "velmi", "ADV", [79, 84]], ["hodn\u011b", "hodn\u011b", "NOUN", [85, 90]], ["pen\u011bz", "pen\u00edze", "NOUN", [91, 96]], [".", ".", "PUNCT", [96, 97]]]], ["calgarske-listy_2003_unor_ocr.txt", "Na v\u0161ech pol\u00edch, co m\u011bl k disposici nechal nas\u00e1zet spousty 15  jablon\u00ed, hru\u0161ek a velk\u00fd \u0161vestkov\u00fd sad.", [["Na", "na", "ADP", [0, 2]], ["v\u0161ech", "v\u0161echen", "DET", [3, 8]], ["pol\u00edch", "pole", "NOUN", [9, 15]], [",", ",", "PUNCT", [15, 16]], ["co", "co", "PRON", [17, 19]], ["m\u011bl", "m\u00edt", "VERB", [20, 23]], ["k", "k", "ADP", [24, 25]], ["disposici", "disposice", "NOUN", [26, 35]], ["nechal", "nechat", "VERB", [36, 42]], ["nas\u00e1zet", "nas\u00e1zet", "VERB", [43, 50]], ["spousty", "spousta", "NOUN", [51, 58]], ["15", "15", "NUM", [59, 61]], ["jablon\u00ed", "jablo\u0148", "NOUN", [63, 70]], [",", ",", "PUNCT", [70, 71]], ["hru\u0161ek", "hru\u0161ka", "NOUN", [72, 78]], ["a", "a", "CCONJ", [79, 80]], ["velk\u00fd", "velk\u00fd", "ADJ", [81, 86]], ["\u0161vestkov\u00fd", "\u0161vestkov\u00fd", "ADJ", [87, 96]], ["sad", "sad", "NOUN", [97, 100]], [".", ".", "PUNCT", [100, 101]]]], ["calgarske-listy_2003_unor_ocr.txt", "Ov\u0161em ten kraj na p\u0159edh\u016f\u0159\u00ed \u010ceskomoravsk\u00e9 vyso\u010diny byl absolutn\u011b nevhodn\u00fd pro ovocn\u00e1\u0159sv\u00ed.", [["Ov\u0161em", "ov\u0161em", "PART", [0, 5]], ["ten", "ten", "DET", [6, 9]], ["kraj", "kraj", "NOUN", [10, 14]], ["na", "na", "ADP", [15, 17]], ["p\u0159edh\u016f\u0159\u00ed", "p\u0159edh\u016f\u0159\u00ed", "NOUN", [18, 26]], ["\u010ceskomoravsk\u00e9", "\u010deskomoravsk\u00fd", "ADJ", [27, 40]], ["vyso\u010diny", "vyso\u010dina", "NOUN", [41, 49]], ["byl", "b\u00fdt", "AUX", [50, 53]], ["absolutn\u011b", "absolutn\u011b", "ADV", [54, 63]], ["nevhodn\u00fd", "vhodn\u00fd", "ADJ", [64, 72]], ["pro", "pro", "ADP", [73, 76]], ["ovocn\u00e1\u0159sv\u00ed", "ovocn\u00e1\u0159sv\u00ed", "NOUN", [77, 87]], [".", ".", "PUNCT", [87, 88]]]], ["calgarske-listy_2003_unor_ocr.txt", "V roce 1929 p\u0159i\u0161ly velk\u00e9 mrazy a v\u011bt\u0161ina drah\u00fdch odr\u016fd to odnesla.", [["V", "v", "ADP", [0, 1]], ["roce", "rok", "NOUN", [2, 6]], ["1929", "1929", "NUM", [7, 11]], ["p\u0159i\u0161ly", "p\u0159ij\u00edt", "VERB", [12, 18]], ["velk\u00e9", "velk\u00fd", "ADJ", [19, 24]], ["mrazy", "mr\u00e1z", "NOUN", [25, 30]], ["a", "a", "CCONJ", [31, 32]], ["v\u011bt\u0161ina", "v\u011bt\u0161ina", "NOUN", [33, 40]], ["drah\u00fdch", "drah\u00fd", "ADJ", [41, 48]], ["odr\u016fd", "odr\u016fd", "NOUN", [49, 54]], ["to", "ten", "DET", [55, 57]], ["odnesla", "odn\u00e9st", "VERB", [58, 65]], [".", ".", "PUNCT", [65, 66]]]], ["calgarske-listy_2003_unor_ocr.txt", "Dokonce nechal postavit klenutou su\u0161\u00e1rnu na su\u0161en\u00ed k\u0159\u00ed\u017eal a \u0161vestek.", [["Dokonce", "dokonce", "ADV", [0, 7]], ["nechal", "nechat", "VERB", [8, 14]], ["postavit", "postavit", "VERB", [15, 23]], ["klenutou", "klenut\u00fd", "ADJ", [24, 32]], ["su\u0161\u00e1rnu", "su\u0161\u00e1rna", "NOUN", [33, 40]], ["na", "na", "ADP", [41, 43]], ["su\u0161en\u00ed", "su\u0161en\u00ed", "NOUN", [44, 50]], ["k\u0159\u00ed\u017eal", "k\u0159\u00ed\u017eal", "NOUN", [51, 57]], ["a", "a", "CCONJ", [58, 59]], ["\u0161vestek", "\u0161vestek", "NOUN", [60, 67]], [".", ".", "PUNCT", [67, 68]]]], ["calgarske-listy_2003_unor_ocr.txt", "\u0160vestkov\u00fd sad byl na moc such\u00e9 str\u00e1ni, a tak to v\u011bt\u0161inou spadalo a jablon\u011b byly na p\u0159\u00edli\u0161 otev\u0159en\u00e9 str\u00e1ni pro severn\u00ed v\u011btry.", [["\u0160vestkov\u00fd", "\u0161vestkov\u00fd", "ADJ", [0, 9]], ["sad", "sad", "NOUN", [10, 13]], ["byl", "b\u00fdt", "AUX", [14, 17]], ["na", "na", "ADP", [18, 20]], ["moc", "moc", "NOUN", [21, 24]], ["such\u00e9", "such\u00fd", "ADJ", [25, 30]], ["str\u00e1ni", "str\u00e1na", "NOUN", [31, 37]], [",", ",", "PUNCT", [37, 38]], ["a", "a", "CCONJ", [39, 40]], ["tak", "tak", "ADV", [41, 44]], ["to", "ten", "DET", [45, 47]], ["v\u011bt\u0161inou", "v\u011bt\u0161inou", "ADV", [48, 56]], ["spadalo", "spadat", "VERB", [57, 64]], ["a", "a", "CCONJ", [65, 66]], ["jablon\u011b", "jablo\u0148", "NOUN", [67, 74]], ["byly", "b\u00fdt", "AUX", [75, 79]], ["na", "na", "ADP", [80, 82]], ["p\u0159\u00edli\u0161", "p\u0159\u00edli\u0161", "ADV", [83, 89]], ["otev\u0159en\u00e9", "otev\u0159en\u00fd", "ADJ", [90, 98]], ["str\u00e1ni", "str\u00e1na", "NOUN", [99, 105]], ["pro", "pro", "ADP", [106, 109]], ["severn\u00ed", "severn\u00ed", "ADJ", [110, 117]], ["v\u011btry", "v\u00edtra", "NOUN", [118, 123]], [".", ".", "PUNCT", [123, 124]]]], ["calgarske-listy_2003_unor_ocr.txt", "Nadmo\u0159sk\u00e1 v\u00fd\u0161ka krajiny je asi 360 - 380 m nad mo\u0159em.", [["Nadmo\u0159sk\u00e1", "nadmo\u0159sk\u00fd", "ADJ", [0, 9]], ["v\u00fd\u0161ka", "v\u00fd\u0161ka", "NOUN", [10, 15]], ["krajiny", "krajina", "NOUN", [16, 23]], ["je", "b\u00fdt", "AUX", [24, 26]], ["asi", "asi", "PART", [27, 30]], ["360", "360", "NUM", [31, 34]], ["-", "-", "PUNCT", [35, 36]], ["380", "380", "NUM", [37, 40]], ["m", "metr", "NOUN", [41, 42]], ["nad", "nad", "ADP", [43, 46]], ["mo\u0159em", "mo\u0159e", "NOUN", [47, 52]], [".", ".", "PUNCT", [52, 53]]]], ["calgarske-listy_2003_unor_ocr.txt", "Ta je dobr\u00e1 na sb\u00edr\u00e1n\u00ed hub, a p\u011bstov\u00e1n\u00ed sena \u010di jetel\u016f.", [["Ta", "ten", "DET", [0, 2]], ["je", "b\u00fdt", "AUX", [3, 5]], ["dobr\u00e1", "dobr\u00fd", "ADJ", [6, 11]], ["na", "na", "ADP", [12, 14]], ["sb\u00edr\u00e1n\u00ed", "sb\u00edr\u00e1n\u00ed", "NOUN", [15, 22]], ["hub", "houba", "NOUN", [23, 26]], [",", ",", "PUNCT", [26, 27]], ["a", "a", "CCONJ", [28, 29]], ["p\u011bstov\u00e1n\u00ed", "p\u011bstov\u00e1n\u00ed", "NOUN", [30, 39]], ["sena", "seno", "NOUN", [40, 44]], ["\u010di", "\u010di", "CCONJ", [45, 47]], ["jetel\u016f", "jetel", "NOUN", [48, 54]], [".", ".", "PUNCT", [54, 55]]]], ["calgarske-listy_2003_unor_ocr.txt", "S d\u011bdou jsem tam v roce 1935 s\u00e1zel dlouhou \u0159adu asi 50-ti mod\u0159\u00edn\u016f.", [["S", "s", "ADP", [0, 1]], ["d\u011bdou", "d\u00edda", "NOUN", [2, 7]], ["jsem", "b\u00fdt", "AUX", [8, 12]], ["tam", "tam", "ADV", [13, 16]], ["v", "v", "ADP", [17, 18]], ["roce", "rok", "NOUN", [19, 23]], ["1935", "1935", "NUM", [24, 28]], ["s\u00e1zel", "s\u00e1zet", "VERB", [29, 34]], ["dlouhou", "dlouh\u00fd", "ADJ", [35, 42]], ["\u0159adu", "\u0159ada", "NOUN", [43, 47]], ["asi", "asi", "PART", [48, 51]], ["50", "50", "NUM", [52, 54]], ["-", "-", "PUNCT", [54, 55]], ["ti", "ten", "DET", [55, 57]], ["mod\u0159\u00edn\u016f", "mod\u0159\u00edn", "NOUN", [58, 65]], [".", ".", "PUNCT", [65, 66]]]], ["calgarske-listy_2003_unor_ocr.txt", "Tam\u011bj\u0161\u00ed \u010desk\u00fd mod\u0159\u00edn je v\u00fdborn\u00e9 t\u011b\u017ek\u00e9 n\u00e1bytk\u00e1\u0159sk\u00e9 d\u0159evo, zejm\u00e9na pro dekorativn\u00ed \u00fa\u010dely.", [["Tam\u011bj\u0161\u00ed", "tam\u011bj\u0161\u00ed", "ADJ", [0, 7]], ["\u010desk\u00fd", "\u010desk\u00fd", "ADJ", [8, 13]], ["mod\u0159\u00edn", "mod\u0159\u00edn", "NOUN", [14, 20]], ["je", "b\u00fdt", "AUX", [21, 23]], ["v\u00fdborn\u00e9", "v\u00fdborn\u00fd", "ADJ", [24, 31]], ["t\u011b\u017ek\u00e9", "t\u011b\u017ek\u00fd", "ADJ", [32, 37]], ["n\u00e1bytk\u00e1\u0159sk\u00e9", "n\u00e1bytk\u00e1\u0159sk\u00fd", "ADJ", [38, 49]], ["d\u0159evo", "d\u0159evo", "NOUN", [50, 55]], [",", ",", "PUNCT", [55, 56]], ["zejm\u00e9na", "zejm\u00e9na", "PART", [57, 64]], ["pro", "pro", "ADP", [65, 68]], ["dekorativn\u00ed", "dekorativn\u00ed", "ADJ", [69, 80]], ["\u00fa\u010dely", "\u00fa\u010del", "NOUN", [81, 86]], [".", ".", "PUNCT", [86, 87]]]], ["calgarske-listy_2003_unor_ocr.txt", "Mod\u0159\u00edny vyrostly n\u00e1dhern\u00e9, ni\u010d\u00edm nest\u00edn\u011bn\u00e9.", [["Mod\u0159\u00edny", "mod\u0159\u00edn", "NOUN", [0, 7]], ["vyrostly", "vyr\u016fst", "VERB", [8, 16]], ["n\u00e1dhern\u00e9", "n\u00e1dhern\u00fd", "ADJ", [17, 25]], [",", ",", "PUNCT", [25, 26]], ["ni\u010d\u00edm", "nic", "PRON", [27, 32]], ["nest\u00edn\u011bn\u00e9", "st\u00edn\u011bn\u00fd", "ADJ", [33, 42]], [".", ".", "PUNCT", [42, 43]]]], ["calgarske-listy_2003_unor_ocr.txt", "Je jich tam je\u0161t\u011b po 68 mi letech, z t\u011bch 50 ti p\u016fvodn\u00edch v \u0159ad\u011b u\u017e jen 7.", [["Je", "b\u00fdt", "AUX", [0, 2]], ["jich", "on", "PRON", [3, 7]], ["tam", "tam", "ADV", [8, 11]], ["je\u0161t\u011b", "je\u0161t\u011b", "ADV", [12, 17]], ["po", "po", "ADP", [18, 20]], ["68", "68", "NUM", [21, 23]], ["mi", "j\u00e1", "PRON", [24, 26]], ["letech", "l\u00e9ta", "NOUN", [27, 33]], [",", ",", "PUNCT", [33, 34]], ["z", "z", "ADP", [35, 36]], ["t\u011bch", "ten", "DET", [37, 41]], ["50", "50", "NUM", [42, 44]], ["ti", "ten", "DET", [45, 47]], ["p\u016fvodn\u00edch", "p\u016fvodn\u00ed", "ADJ", [48, 57]], ["v", "v", "ADP", [58, 59]], ["\u0159ad\u011b", "\u0159ada", "NOUN", [60, 64]], ["u\u017e", "u\u017e", "ADV", [65, 67]], ["jen", "jen", "ADV", [68, 71]], ["7", "7", "NUM", [72, 73]], [".", ".", "PUNCT", [73, 74]]]], ["calgarske-listy_2003_unor_ocr.txt", "Nov\u00ed majitel\u00e9 t\u011bch pozemk\u016f jich v\u011bt\u0161inu pok\u00e1celi a n\u011bco vzala v\u00fdstavba nov\u00e9 asfaltov\u00e9 silnice, kter\u00e1 p\u0159etnula ty na\u0161e b\u00fdval\u00e9 pozemky diagon\u00e1ln\u011b.", [["Nov\u00ed", "nov\u00fd", "ADJ", [0, 4]], ["majitel\u00e9", "majitel", "NOUN", [5, 13]], ["t\u011bch", "ten", "DET", [14, 18]], ["pozemk\u016f", "pozemek", "NOUN", [19, 26]], ["jich", "on", "PRON", [27, 31]], ["v\u011bt\u0161inu", "v\u011bt\u0161ina", "NOUN", [32, 39]], ["pok\u00e1celi", "pok\u00e1cet", "VERB", [40, 48]], ["a", "a", "CCONJ", [49, 50]], ["n\u011bco", "n\u011bco", "PRON", [51, 55]], ["vzala", "vz\u00edt", "VERB", [56, 61]], ["v\u00fdstavba", "v\u00fdstavba", "NOUN", [62, 70]], ["nov\u00e9", "nov\u00fd", "ADJ", [71, 75]], ["asfaltov\u00e9", "asfaltov\u00fd", "ADJ", [76, 85]], ["silnice", "silnice", "NOUN", [86, 93]], [",", ",", "PUNCT", [93, 94]], ["kter\u00e1", "kter\u00fd", "DET", [95, 100]], ["p\u0159etnula", "p\u0159etnout", "VERB", [101, 109]], ["ty", "ten", "DET", [110, 112]], ["na\u0161e", "n\u00e1\u0161", "DET", [113, 117]], ["b\u00fdval\u00e9", "b\u00fdval\u00fd", "ADJ", [118, 124]], ["pozemky", "pozemek", "NOUN", [125, 132]], ["diagon\u00e1ln\u011b", "diagon\u00e1ln\u011b", "ADV", [133, 143]], [".", ".", "PUNCT", [143, 144]]]], ["calgarske-listy_2003_unor_ocr.txt", "Moje obl\u00edben\u00e9 m\u00edsto b\u011bhem tepl\u00fdch dn\u016f bylo v zahradn\u00edm alt\u00e1nu.", [["Moje", "m\u016fj", "DET", [0, 4]], ["obl\u00edben\u00e9", "obl\u00edben\u00fd", "ADJ", [5, 13]], ["m\u00edsto", "m\u00edsto", "NOUN", [14, 19]], ["b\u011bhem", "b\u011bhem", "ADP", [20, 25]], ["tepl\u00fdch", "tepl\u00fd", "ADJ", [26, 33]], ["dn\u016f", "den", "NOUN", [34, 37]], ["bylo", "b\u00fdt", "AUX", [38, 42]], ["v", "v", "ADP", [43, 44]], ["zahradn\u00edm", "zahradn\u00ed", "ADJ", [45, 54]], ["alt\u00e1nu", "alt\u00e1n", "NOUN", [55, 61]], [".", ".", "PUNCT", [61, 62]]]], ["calgarske-listy_2003_unor_ocr.txt", "D\u011bda zde m\u011bl slo\u017eeny knihy o ovocn\u00e1\u0159stv\u00ed a spousty obr\u00e1zkov\u00fdch \u010dasopis\u016f.", [["D\u011bda", "d\u011bda", "NOUN", [0, 4]], ["zde", "zde", "ADV", [5, 8]], ["m\u011bl", "m\u00edt", "VERB", [9, 12]], ["slo\u017eeny", "slo\u017een\u00fd", "ADJ", [13, 20]], ["knihy", "kniha", "NOUN", [21, 26]], ["o", "o", "ADP", [27, 28]], ["ovocn\u00e1\u0159stv\u00ed", "ovocn\u00e1\u0159stv\u00ed", "NOUN", [29, 40]], ["a", "a", "CCONJ", [41, 42]], ["spousty", "spousta", "NOUN", [43, 50]], ["obr\u00e1zkov\u00fdch", "obr\u00e1zkov\u00fd", "ADJ", [51, 62]], ["\u010dasopis\u016f", "\u010dasopis", "NOUN", [63, 71]], [".", ".", "PUNCT", [71, 72]]]], ["calgarske-listy_2003_unor_ocr.txt", "V obr\u00e1zkov\u00e9m \u010dasopise \"Ilustrovan\u00fd A-Z.\" m\u011b jednou velmi zaujaly fotografie le\u017e\u00edc\u00edch lid\u00ed s velice nafoukl\u00fdmi b\u0159ichy okolo velmi n\u00edzk\u00fdch staveb a byly tam i koleje.", [["V", "v", "ADP", [0, 1]], ["obr\u00e1zkov\u00e9m", "obr\u00e1zkov\u00fd", "ADJ", [2, 12]], ["\u010dasopise", "\u010dasopis", "NOUN", [13, 21]], ["\"", "\"", "PUNCT", [22, 23]], ["Ilustrovan\u00fd", "ilustrovan\u00fd", "ADJ", [23, 34]], ["A", "A", "NOUN", [35, 36]], ["-", "-", "PUNCT", [36, 37]], ["Z", "Z", "NOUN", [37, 38]], [".", ".", "PUNCT", [38, 39]], ["\"", "\"", "PUNCT", [39, 40]], ["m\u011b", "j\u00e1", "PRON", [41, 43]], ["jednou", "jednou", "ADV", [44, 50]], ["velmi", "velmi", "ADV", [51, 56]], ["zaujaly", "zaujmout", "VERB", [57, 64]], ["fotografie", "fotografie", "NOUN", [65, 75]], ["le\u017e\u00edc\u00edch", "le\u017e\u00edc\u00ed", "ADJ", [76, 84]], ["lid\u00ed", "lid\u00e9", "NOUN", [85, 89]], ["s", "s", "ADP", [90, 91]], ["velice", "velice", "ADV", [92, 98]], ["nafoukl\u00fdmi", "nafoukl\u00fd", "ADJ", [99, 109]], ["b\u0159ichy", "b\u0159ich", "NOUN", [110, 116]], ["okolo", "okolo", "ADP", [117, 122]], ["velmi", "velmi", "ADV", [123, 128]], ["n\u00edzk\u00fdch", "n\u00edzk\u00fd", "ADJ", [129, 136]], ["staveb", "stavba", "NOUN", [137, 143]], ["a", "a", "CCONJ", [144, 145]], ["byly", "b\u00fdt", "AUX", [146, 150]], ["tam", "tam", "ADV", [151, 154]], ["i", "i", "CCONJ", [155, 156]], ["koleje", "kolej", "NOUN", [157, 163]], [".", ".", "PUNCT", [163, 164]]]], ["calgarske-listy_2003_unor_ocr.txt", "Na moji zv\u011bdavou ot\u00e1zku, pro\u010d maj\u00ed takov\u00e1 velik\u00e1 b\u0159icha, mi d\u011bda pov\u00eddal.", [["Na", "na", "ADP", [0, 2]], ["moji", "m\u016fj", "DET", [3, 7]], ["zv\u011bdavou", "zv\u011bdav\u00fd", "ADJ", [8, 16]], ["ot\u00e1zku", "ot\u00e1zka", "NOUN", [17, 23]], [",", ",", "PUNCT", [23, 24]], ["pro\u010d", "pro\u010d", "ADV", [25, 29]], ["maj\u00ed", "m\u00edt", "VERB", [30, 34]], ["takov\u00e1", "takov\u00fd", "DET", [35, 41]], ["velik\u00e1", "velik\u00fd", "ADJ", [42, 48]], ["b\u0159icha", "b\u0159icho", "NOUN", [49, 55]], [",", ",", "PUNCT", [55, 56]], ["mi", "j\u00e1", "PRON", [57, 59]], ["d\u011bda", "d\u011bda", "NOUN", [60, 64]], ["pov\u00eddal", "pov\u00eddat", "VERB", [65, 72]], [".", ".", "PUNCT", [72, 73]]]], ["calgarske-listy_2003_unor_ocr.txt", "Ty lidi tam m\u011bli velk\u00fd hlad, p\u0159i\u0161li k n\u00e1dra\u017e\u00ed a \u010dekali tam na n\u011bjak\u00e9 j\u00eddlo a pak zem\u0159eli.", [["Ty", "ten", "DET", [0, 2]], ["lidi", "lid\u00e9", "NOUN", [3, 7]], ["tam", "tam", "ADV", [8, 11]], ["m\u011bli", "m\u00edt", "VERB", [12, 16]], ["velk\u00fd", "velk\u00fd", "ADJ", [17, 22]], ["hlad", "hlad", "NOUN", [23, 27]], [",", ",", "PUNCT", [27, 28]], ["p\u0159i\u0161li", "p\u0159ij\u00edt", "VERB", [29, 35]], ["k", "k", "ADP", [36, 37]], ["n\u00e1dra\u017e\u00ed", "n\u00e1dra\u017e\u00ed", "NOUN", [38, 45]], ["a", "a", "CCONJ", [46, 47]], ["\u010dekali", "\u010dekat", "VERB", [48, 54]], ["tam", "tam", "ADV", [55, 58]], ["na", "na", "ADP", [59, 61]], ["n\u011bjak\u00e9", "n\u011bjak\u00fd", "DET", [62, 68]], ["j\u00eddlo", "j\u00eddlo", "NOUN", [69, 74]], ["a", "a", "CCONJ", [75, 76]], ["pak", "pak", "ADV", [77, 80]], ["zem\u0159eli", "zem\u0159\u00edt", "VERB", [81, 88]], [".", ".", "PUNCT", [88, 89]]]], ["calgarske-listy_2003_unor_ocr.txt", "Je\u0161t\u011b jsem se zeptal pro\u010d m\u011bli hlad, kdy\u017e m\u011bli takov\u00e1 velk\u00e1 b\u0159icha.", [["Je\u0161t\u011b", "je\u0161t\u011b", "ADV", [0, 5]], ["jsem", "b\u00fdt", "AUX", [6, 10]], ["se", "se", "PRON", [11, 13]], ["zeptal", "zeptat", "VERB", [14, 20]], ["pro\u010d", "pro\u010d", "ADV", [21, 25]], ["m\u011bli", "m\u00edt", "VERB", [26, 30]], ["hlad", "hlad", "NOUN", [31, 35]], [",", ",", "PUNCT", [35, 36]], ["kdy\u017e", "kdy\u017e", "SCONJ", [37, 41]], ["m\u011bli", "m\u00edt", "VERB", [42, 46]], ["takov\u00e1", "takov\u00fd", "DET", [47, 53]], ["velk\u00e1", "velk\u00fd", "ADJ", [54, 59]], ["b\u0159icha", "b\u0159icho", "NOUN", [60, 66]], [".", ".", "PUNCT", [66, 67]]]], ["calgarske-listy_2003_unor_ocr.txt", "Na to jsi je\u0161t\u011b moc mal\u00fd hoch, zahr\u00e1l d\u011bda debatu do autu.", [["Na", "na", "ADP", [0, 2]], ["to", "ten", "DET", [3, 5]], ["jsi", "b\u00fdt", "AUX", [6, 9]], ["je\u0161t\u011b", "je\u0161t\u011b", "ADV", [10, 15]], ["moc", "moc", "ADV", [16, 19]], ["mal\u00fd", "mal\u00fd", "ADJ", [20, 24]], ["hoch", "hocha", "NOUN", [25, 29]], [",", ",", "PUNCT", [29, 30]], ["zahr\u00e1l", "zahr\u00e1t", "VERB", [31, 37]], ["d\u011bda", "d\u011bda", "NOUN", [38, 42]], ["debatu", "debata", "NOUN", [43, 49]], ["do", "do", "ADP", [50, 52]], ["autu", "auto", "NOUN", [53, 57]], [".", ".", "PUNCT", [57, 58]]]], ["calgarske-listy_2003_unor_ocr.txt", "Moc m\u011b to tehd\u00e1 utkv\u011blo v pam\u011bti, ale a\u017e po 18 ti letech jsem se dozv\u011bd\u011bl o co \u0161lo.", [["Moc", "moc", "ADV", [0, 3]], ["m\u011b", "j\u00e1", "PRON", [4, 6]], ["to", "ten", "DET", [7, 9]], ["tehd\u00e1", "tehd\u00e1", "ADV", [10, 15]], ["utkv\u011blo", "utkv\u011bt", "VERB", [16, 23]], ["v", "v", "ADP", [24, 25]], ["pam\u011bti", "pam\u011b\u0165", "NOUN", [26, 32]], [",", ",", "PUNCT", [32, 33]], ["ale", "ale", "CCONJ", [34, 37]], ["a\u017e", "a\u017e", "PART", [38, 40]], ["po", "po", "ADP", [41, 43]], ["18", "18", "NUM", [44, 46]], ["ti", "ten", "DET", [47, 49]], ["letech", "l\u00e9ta", "NOUN", [50, 56]], ["jsem", "b\u00fdt", "AUX", [57, 61]], ["se", "se", "PRON", [62, 64]], ["dozv\u011bd\u011bl", "dozv\u011bd\u011bt", "VERB", [65, 73]], ["o", "o", "ADP", [74, 75]], ["co", "co", "PRON", [76, 78]], ["\u0161lo", "j\u00edt", "VERB", [79, 82]], [".", ".", "PUNCT", [82, 83]]]], ["calgarske-listy_2003_unor_ocr.txt", "To jsem byl jako politicky nespolehliv\u00fd na vojn\u011b u PTP na ostravsk\u00e9 \u0161acht\u011b a n\u00e1\u0161 politruk n\u00e1m p\u0159edn\u00e1\u0161el p\u0159i politick\u00e9m \u0161kolen\u00ed d\u011bjiny VKSb a mluvilo se o kolektivizaci rusk\u00e9ho zem\u011bd\u011blstv\u00ed.", [["To", "ten", "DET", [0, 2]], ["jsem", "b\u00fdt", "AUX", [3, 7]], ["byl", "b\u00fdt", "AUX", [8, 11]], ["jako", "jako", "SCONJ", [12, 16]], ["politicky", "politicky", "ADV", [17, 26]], ["nespolehliv\u00fd", "spolehliv\u00fd", "ADJ", [27, 39]], ["na", "na", "ADP", [40, 42]], ["vojn\u011b", "vojna", "NOUN", [43, 48]], ["u", "u", "ADP", [49, 50]], ["PTP", "PTP", "NOUN", [51, 54]], ["na", "na", "ADP", [55, 57]], ["ostravsk\u00e9", "ostravsk\u00fd", "ADJ", [58, 67]], ["\u0161acht\u011b", "\u0161achta", "NOUN", [68, 74]], ["a", "a", "CCONJ", [75, 76]], ["n\u00e1\u0161", "n\u00e1\u0161", "DET", [77, 80]], ["politruk", "politruk", "NOUN", [81, 89]], ["n\u00e1m", "my", "PRON", [90, 93]], ["p\u0159edn\u00e1\u0161el", "p\u0159edn\u00e1\u0161et", "VERB", [94, 103]], ["p\u0159i", "p\u0159i", "ADP", [104, 107]], ["politick\u00e9m", "politick\u00fd", "ADJ", [108, 118]], ["\u0161kolen\u00ed", "\u0161kolen\u00ed", "NOUN", [119, 126]], ["d\u011bjiny", "d\u011bjiny", "NOUN", [127, 133]], ["VKSb", "VKSb", "NOUN", [134, 138]], ["a", "a", "CCONJ", [139, 140]], ["mluvilo", "mluvit", "VERB", [141, 148]], ["se", "se", "PRON", [149, 151]], ["o", "o", "ADP", [152, 153]], ["kolektivizaci", "kolektivizace", "NOUN", [154, 167]], ["rusk\u00e9ho", "rusk\u00fd", "ADJ", [168, 175]], ["zem\u011bd\u011blstv\u00ed", "zem\u011bd\u011blstv\u00ed", "NOUN", [176, 187]], [".", ".", "PUNCT", [187, 188]]]], ["calgarske-listy_2003_unor_ocr.txt", "Stalin pr\u00fd se rozhodl v roce 1935 pro urychlenou kolektivizaci venkova.", [["Stalin", "Stalin", "PROPN", [0, 6]], ["pr\u00fd", "pr\u00fd", "PART", [7, 10]], ["se", "se", "PRON", [11, 13]], ["rozhodl", "rozhodnout", "VERB", [14, 21]], ["v", "v", "ADP", [22, 23]], ["roce", "rok", "NOUN", [24, 28]], ["1935", "1935", "NUM", [29, 33]], ["pro", "pro", "ADP", [34, 37]], ["urychlenou", "urychlen\u00fd", "ADJ", [38, 48]], ["kolektivizaci", "kolektivizace", "NOUN", [49, 62]], ["venkova", "venkov", "NOUN", [63, 70]], [".", ".", "PUNCT", [70, 71]]]], ["calgarske-listy_2003_unor_ocr.txt", "Rusk\u00fd venkov tomu moc nev\u011b\u0159il, ot\u00e1lel.", [["Rusk\u00fd", "rusk\u00fd", "ADJ", [0, 5]], ["venkov", "venkov", "NOUN", [6, 12]], ["tomu", "ten", "DET", [13, 17]], ["moc", "moc", "ADV", [18, 21]], ["nev\u011b\u0159il", "v\u011b\u0159it", "VERB", [22, 29]], [",", ",", "PUNCT", [29, 30]], ["ot\u00e1lel", "ot\u00e1lit", "VERB", [31, 37]], [".", ".", "PUNCT", [37, 38]]]], ["calgarske-listy_2003_unor_ocr.txt", "Stalin tedy poslal do Saratovsk\u00e9ho okresu vojsko, kter\u00e9 tam m\u011blo sebrat v\u0161echno zrn\u00ed se slibem, \u017ee jim na novou sadbu p\u0159ivezou lep\u0161\u00ed osivo.", [["Stalin", "Stalin", "PROPN", [0, 6]], ["tedy", "tedy", "CCONJ", [7, 11]], ["poslal", "poslat", "VERB", [12, 18]], ["do", "do", "ADP", [19, 21]], ["Saratovsk\u00e9ho", "saratovsk\u00fd", "ADJ", [22, 34]], ["okresu", "okres", "NOUN", [35, 41]], ["vojsko", "vojsko", "NOUN", [42, 48]], [",", ",", "PUNCT", [48, 49]], ["kter\u00e9", "kter\u00fd", "DET", [50, 55]], ["tam", "tam", "ADV", [56, 59]], ["m\u011blo", "m\u00edt", "VERB", [60, 64]], ["sebrat", "sebrat", "VERB", [65, 71]], ["v\u0161echno", "v\u0161echen", "DET", [72, 79]], ["zrn\u00ed", "zrn\u00ed", "ADJ", [80, 84]], ["se", "s", "ADP", [85, 87]], ["slibem", "slib", "NOUN", [88, 94]], [",", ",", "PUNCT", [94, 95]], ["\u017ee", "\u017ee", "SCONJ", [96, 98]], ["jim", "on", "PRON", [99, 102]], ["na", "na", "ADP", [103, 105]], ["novou", "nov\u00fd", "ADJ", [106, 111]], ["sadbu", "sadba", "NOUN", [112, 117]], ["p\u0159ivezou", "p\u0159iv\u00e9zt", "VERB", [118, 126]], ["lep\u0161\u00ed", "lep\u0161\u00ed", "ADJ", [127, 132]], ["osivo", "osivo", "NOUN", [133, 138]], [".", ".", "PUNCT", [138, 139]]]], ["calgarske-listy_2003_unor_ocr.txt", "Sebrali, nic nep\u0159ivezli, kolektivizace v\u00e1zla d\u00e1le.", [["Sebrali", "sebrat", "VERB", [0, 7]], [",", ",", "PUNCT", [7, 8]], ["nic", "nic", "PRON", [9, 12]], ["nep\u0159ivezli", "p\u0159iv\u00e9zt", "VERB", [13, 23]], [",", ",", "PUNCT", [23, 24]], ["kolektivizace", "kolektivizace", "NOUN", [25, 38]], ["v\u00e1zla", "v\u00e1znout", "VERB", [39, 44]], ["d\u00e1le", "d\u00e1le", "ADV", [45, 49]], [".", ".", "PUNCT", [49, 50]]]], ["calgarske-listy_2003_unor_ocr.txt", "Stalin zarazil dovoz potravin do Saratovsk\u00e9ho okresu a hladov\u011bj\u00edc\u00ed mu\u017eici se shrom\u00e1\u017edili kolem n\u00e1dra\u017e\u00ed, kde \u010dekali pomoc, \u010di cht\u011bli n\u011bkam odjet.", [["Stalin", "Stalin", "PROPN", [0, 6]], ["zarazil", "zarazit", "VERB", [7, 14]], ["dovoz", "dovoz", "NOUN", [15, 20]], ["potravin", "potravina", "NOUN", [21, 29]], ["do", "do", "ADP", [30, 32]], ["Saratovsk\u00e9ho", "saratovsk\u00fd", "ADJ", [33, 45]], ["okresu", "okres", "NOUN", [46, 52]], ["a", "a", "CCONJ", [53, 54]], ["hladov\u011bj\u00edc\u00ed", "hladov\u011bj\u00edc\u00ed", "ADJ", [55, 66]], ["mu\u017eici", "mu\u017eice", "NOUN", [67, 73]], ["se", "se", "PRON", [74, 76]], ["shrom\u00e1\u017edili", "shrom\u00e1\u017edit", "VERB", [77, 88]], ["kolem", "kolem", "ADP", [89, 94]], ["n\u00e1dra\u017e\u00ed", "n\u00e1dra\u017e\u00ed", "NOUN", [95, 102]], [",", ",", "PUNCT", [102, 103]], ["kde", "kde", "ADV", [104, 107]], ["\u010dekali", "\u010dekat", "VERB", [108, 114]], ["pomoc", "pomoc", "NOUN", [115, 120]], [",", ",", "PUNCT", [120, 121]], ["\u010di", "\u010di", "CCONJ", [122, 124]], ["cht\u011bli", "cht\u00edt", "VERB", [125, 131]], ["n\u011bkam", "n\u011bkam", "ADV", [132, 137]], ["odjet", "odjet", "VERB", [138, 143]], [".", ".", "PUNCT", [143, 144]]]], ["calgarske-listy_2003_unor_ocr.txt", "Vlaky nep\u0159ijely a lidi tam kolem n\u00e1dra\u017e\u00ed pom\u0159eli hlady.", [["Vlaky", "vlak", "NOUN", [0, 5]], ["nep\u0159ijely", "p\u0159ijet", "VERB", [6, 15]], ["a", "a", "CCONJ", [16, 17]], ["lidi", "lid\u00e9", "NOUN", [18, 22]], ["tam", "tam", "ADV", [23, 26]], ["kolem", "kolem", "ADP", [27, 32]], ["n\u00e1dra\u017e\u00ed", "n\u00e1dra\u017e\u00ed", "NOUN", [33, 40]], ["pom\u0159eli", "pom\u0159\u00edt", "VERB", [41, 48]], ["hlady", "hlad", "NOUN", [49, 54]], [".", ".", "PUNCT", [54, 55]]]], ["calgarske-listy_2003_unor_ocr.txt", "Mrtvoly se po n\u011bkolika dnech na slunci nafoukly a v tom okam\u017eiku tam n\u011bjak proj\u00ed\u017ed\u011bli \u010de\u0161t\u00ed fotoreport\u00e9\u0159i a ty fotografick\u00e9 z\u00e1b\u011bry z Ruska propa\u0161ovaly.", [["Mrtvoly", "mrtvola", "NOUN", [0, 7]], ["se", "se", "PRON", [8, 10]], ["po", "po", "ADP", [11, 13]], ["n\u011bkolika", "n\u011bkolik", "DET", [14, 22]], ["dnech", "den", "NOUN", [23, 28]], ["na", "na", "ADP", [29, 31]], ["slunci", "slunce", "NOUN", [32, 38]], ["nafoukly", "nafouknout", "VERB", [39, 47]], ["a", "a", "CCONJ", [48, 49]], ["v", "v", "ADP", [50, 51]], ["tom", "ten", "DET", [52, 55]], ["okam\u017eiku", "okam\u017eik", "NOUN", [56, 64]], ["tam", "tam", "ADV", [65, 68]], ["n\u011bjak", "n\u011bjak", "ADV", [69, 74]], ["proj\u00ed\u017ed\u011bli", "proj\u00ed\u017ed\u011bt", "VERB", [75, 85]], ["\u010de\u0161t\u00ed", "\u010desk\u00fd", "ADJ", [86, 91]], ["fotoreport\u00e9\u0159i", "fotoreport\u00e9r", "NOUN", [92, 105]], ["a", "a", "CCONJ", [106, 107]], ["ty", "ten", "DET", [108, 110]], ["fotografick\u00e9", "fotografick\u00fd", "ADJ", [111, 123]], ["z\u00e1b\u011bry", "z\u00e1b\u011br", "NOUN", [124, 130]], ["z", "z", "ADP", [131, 132]], ["Ruska", "Rusko", "PROPN", [133, 138]], ["propa\u0161ovaly", "propa\u0161ovat", "VERB", [139, 150]], [".", ".", "PUNCT", [150, 151]]]], ["calgarske-listy_2003_unor_ocr.txt", "Af\u00e9ra se jmenovala saratovsk\u00fd hladomor a Stalin na ot\u00e1zky ciz\u00edch n\u00e1v\u0161t\u011bvn\u00edk\u016f odpov\u00eddal pokr\u010den\u00edm ramen.", [["Af\u00e9ra", "af\u00e9ra", "NOUN", [0, 5]], ["se", "se", "PRON", [6, 8]], ["jmenovala", "jmenovat", "VERB", [9, 18]], ["saratovsk\u00fd", "saratovsk\u00fd", "ADJ", [19, 29]], ["hladomor", "hladomor", "NOUN", [30, 38]], ["a", "a", "CCONJ", [39, 40]], ["Stalin", "Stalin", "PROPN", [41, 47]], ["na", "na", "ADP", [48, 50]], ["ot\u00e1zky", "ot\u00e1zka", "NOUN", [51, 57]], ["ciz\u00edch", "ciz\u00ed", "ADJ", [58, 64]], ["n\u00e1v\u0161t\u011bvn\u00edk\u016f", "n\u00e1v\u0161t\u011bvn\u00edk", "NOUN", [65, 76]], ["odpov\u00eddal", "odpov\u00eddat", "VERB", [77, 86]], ["pokr\u010den\u00edm", "pokr\u010den\u00ed", "NOUN", [87, 96]], ["ramen", "rameno", "NOUN", [97, 102]], [".", ".", "PUNCT", [102, 103]]]], ["calgarske-listy_2003_unor_ocr.txt", "Ten n\u00e1\u0161 politruk tehd\u00e1 u PTP na mne koukal s otev\u0159enou pusou o \u010dem to mluv\u00edm.", [["Ten", "ten", "DET", [0, 3]], ["n\u00e1\u0161", "n\u00e1\u0161", "DET", [4, 7]], ["politruk", "politruk", "NOUN", [8, 16]], ["tehd\u00e1", "tehd\u00e1", "ADV", [17, 22]], ["u", "u", "ADP", [23, 24]], ["PTP", "PTP", "NOUN", [25, 28]], ["na", "na", "ADP", [29, 31]], ["mne", "j\u00e1", "PRON", [32, 35]], ["koukal", "koukat", "VERB", [36, 42]], ["s", "s", "ADP", [43, 44]], ["otev\u0159enou", "otev\u0159en\u00fd", "ADJ", [45, 54]], ["pusou", "pusa", "NOUN", [55, 60]], ["o", "o", "ADP", [61, 62]], ["\u010dem", "co", "PRON", [63, 66]], ["to", "ten", "DET", [67, 69]], ["mluv\u00edm", "mluvit", "VERB", [70, 76]], [".", ".", "PUNCT", [76, 77]]]], ["calgarske-listy_2003_unor_ocr.txt", "Proto\u017ee jsem asi nebyl dostate\u010dn\u011b usm\u011brn\u011bn\u00fd, tak si m\u011b po dvou letech vojny p\u0159idr\u017eeli kopat uhl\u00ed na neur\u010dito.", [["Proto\u017ee", "proto\u017ee", "SCONJ", [0, 7]], ["jsem", "b\u00fdt", "AUX", [8, 12]], ["asi", "asi", "PART", [13, 16]], ["nebyl", "b\u00fdt", "AUX", [17, 22]], ["dostate\u010dn\u011b", "dostate\u010dn\u011b", "ADV", [23, 33]], ["usm\u011brn\u011bn\u00fd", "usm\u011brn\u011bn\u00fd", "ADJ", [34, 43]], [",", ",", "PUNCT", [43, 44]], ["tak", "tak", "ADV", [45, 48]], ["si", "se", "PRON", [49, 51]], ["m\u011b", "j\u00e1", "PRON", [52, 54]], ["po", "po", "ADP", [55, 57]], ["dvou", "dva", "NUM", [58, 62]], ["letech", "l\u00e9ta", "NOUN", [63, 69]], ["vojny", "vojna", "NOUN", [70, 75]], ["p\u0159idr\u017eeli", "p\u0159idr\u017eet", "VERB", [76, 85]], ["kopat", "kopat", "VERB", [86, 91]], ["uhl\u00ed", "uhl\u00ed", "NOUN", [92, 96]], ["na", "na", "ADP", [97, 99]], ["neur\u010dito", "neur\u010dito", "NOUN", [100, 108]], [".", ".", "PUNCT", [108, 109]]]], ["calgarske-listy_2003_unor_ocr.txt", "Tehd\u00e1 jsem byl naivn\u00ed venkovsk\u00fd synek.", [["Tehd\u00e1", "tehd\u00e1", "ADV", [0, 5]], ["jsem", "b\u00fdt", "AUX", [6, 10]], ["byl", "b\u00fdt", "AUX", [11, 14]], ["naivn\u00ed", "naivn\u00ed", "ADJ", [15, 21]], ["venkovsk\u00fd", "venkovsk\u00fd", "ADJ", [22, 31]], ["synek", "synek", "NOUN", [32, 37]], [".", ".", "PUNCT", [37, 38]]]], ["calgarske-listy_2003_unor_ocr.txt", "Pozd\u011bji jsem tu indoktrinaci t\u011bm koman\u010d\u016fm ale velmi elegantn\u011b vr\u00e1til.", [["Pozd\u011bji", "pozd\u011b", "ADV", [0, 7]], ["jsem", "b\u00fdt", "AUX", [8, 12]], ["tu", "tu", "ADV", [13, 15]], ["indoktrinaci", "indoktrinace", "NOUN", [16, 28]], ["t\u011bm", "ten", "DET", [29, 32]], ["koman\u010d\u016fm", "koman\u010d", "NOUN", [33, 41]], ["ale", "ale", "CCONJ", [42, 45]], ["velmi", "velmi", "ADV", [46, 51]], ["elegantn\u011b", "elegantn\u011b", "ADV", [52, 61]], ["vr\u00e1til", "vr\u00e1tit", "VERB", [62, 68]], [".", ".", "PUNCT", [68, 69]]]], ["calgarske-listy_2003_unor_ocr.txt", "(Pokra\u010dov\u00e1n\u00ed p\u0159\u00ed\u0161t\u011b).", [["(", "(", "PUNCT", [0, 1]], ["Pokra\u010dov\u00e1n\u00ed", "pokra\u010dov\u00e1n\u00ed", "NOUN", [1, 12]], ["p\u0159\u00ed\u0161t\u011b", "p\u0159\u00ed\u0161t\u011b", "ADV", [13, 19]], [")", ")", "PUNCT", [19, 20]], [".", ".", "PUNCT", [20, 21]]]], ["calgarske-listy_2003_unor_ocr.txt", "V.M. Bez titulu .....", [["V", "V", "NOUN", [0, 1]], [".", ".", "PUNCT", [1, 2]], ["M", "M", "NOUN", [2, 3]], [".", ".", "PUNCT", [3, 4]], ["Bez", "bez", "ADP", [5, 8]], ["titulu", "titul", "NOUN", [9, 15]], [".", ".", "PUNCT", [16, 17]], [".", ".", "PUNCT", [17, 18]], [".", ".", "PUNCT", [18, 19]], [".", ".", "PUNCT", [19, 20]], [".", ".", "PUNCT", [20, 21]]]], ["calgarske-listy_2003_unor_ocr.txt", "Leto\u0161n\u00ed zima je sice m\u00edrn\u00e1 ale ne\u00fam\u011brn\u00fd je leto\u0161n\u00ed \u00fa\u010det za ot\u00e1p\u011bn\u00ed na\u0161eho domu.", [["Leto\u0161n\u00ed", "leto\u0161n\u00ed", "ADJ", [0, 7]], ["zima", "zima", "NOUN", [8, 12]], ["je", "b\u00fdt", "AUX", [13, 15]], ["sice", "sice", "CCONJ", [16, 20]], ["m\u00edrn\u00e1", "m\u00edrn\u00fd", "ADJ", [21, 26]], ["ale", "ale", "CCONJ", [27, 30]], ["ne\u00fam\u011brn\u00fd", "\u00fam\u011brn\u00fd", "ADJ", [31, 39]], ["je", "b\u00fdt", "AUX", [40, 42]], ["leto\u0161n\u00ed", "leto\u0161n\u00ed", "ADJ", [43, 50]], ["\u00fa\u010det", "\u00fa\u010det", "NOUN", [51, 55]], ["za", "za", "ADP", [56, 58]], ["ot\u00e1p\u011bn\u00ed", "ot\u00e1p\u011bn\u00ed", "NOUN", [59, 66]], ["na\u0161eho", "n\u00e1\u0161", "DET", [67, 73]], ["domu", "d\u016fm", "NOUN", [74, 78]], [".", ".", "PUNCT", [78, 79]]]], ["calgarske-listy_2003_unor_ocr.txt", "Byl jsem ve Vancouveru u dcery si vyzkou\u0161et jejich zimu a tak ten d\u00e9\u0161\u0165 je tam z\u00e1dum\u010div\u00fd.", [["Byl", "b\u00fdt", "AUX", [0, 3]], ["jsem", "b\u00fdt", "AUX", [4, 8]], ["ve", "v", "ADP", [9, 11]], ["Vancouveru", "Vancouver", "PROPN", [12, 22]], ["u", "u", "ADP", [23, 24]], ["dcery", "dcera", "NOUN", [25, 30]], ["si", "se", "PRON", [31, 33]], ["vyzkou\u0161et", "vyzkou\u0161et", "VERB", [34, 43]], ["jejich", "jeho", "DET", [44, 50]], ["zimu", "zima", "NOUN", [51, 55]], ["a", "a", "CCONJ", [56, 57]], ["tak", "tak", "ADV", [58, 61]], ["ten", "ten", "DET", [62, 65]], ["d\u00e9\u0161\u0165", "d\u00e9\u0161\u0165", "NOUN", [66, 70]], ["je", "b\u00fdt", "AUX", [71, 73]], ["tam", "tam", "ADV", [74, 77]], ["z\u00e1dum\u010div\u00fd", "z\u00e1dum\u010div\u00fd", "ADJ", [78, 87]], [".", ".", "PUNCT", [87, 88]]]], ["calgarske-listy_2003_unor_ocr.txt", "Z Prahy p\u0159i\u0161lo ozn\u00e1men\u00ed o smrti pana Horn\u00ed\u010dka.", [["Z", "z", "ADP", [0, 1]], ["Prahy", "Praha", "PROPN", [2, 7]], ["p\u0159i\u0161lo", "p\u0159ij\u00edt", "VERB", [8, 14]], ["ozn\u00e1men\u00ed", "ozn\u00e1men\u00ed", "NOUN", [15, 23]], ["o", "o", "ADP", [24, 25]], ["smrti", "smrt", "NOUN", [26, 31]], ["pana", "pan", "NOUN", [32, 36]], ["Horn\u00ed\u010dka", "Horn\u00ed\u010dek", "PROPN", [37, 45]], [".", ".", "PUNCT", [45, 46]]]], ["calgarske-listy_2003_unor_ocr.txt", "Spolu s Janem Werichem to byla velmi zaj\u00edmav\u00e1 dvojice.", [["Spolu", "spolu", "ADV", [0, 5]], ["s", "s", "ADP", [6, 7]], ["Janem", "Jan", "PROPN", [8, 13]], ["Werichem", "Werich", "PROPN", [14, 22]], ["to", "ten", "DET", [23, 25]], ["byla", "b\u00fdt", "AUX", [26, 30]], ["velmi", "velmi", "ADV", [31, 36]], ["zaj\u00edmav\u00e1", "zaj\u00edmav\u00fd", "ADJ", [37, 45]], ["dvojice", "dvojice", "NOUN", [46, 53]], [".", ".", "PUNCT", [53, 54]]]], ["calgarske-listy_2003_unor_ocr.txt", "Miroslav Horn\u00ed\u010dek n\u00e1s nav\u0161t\u00edvil i zde v Calgary.", [["Miroslav", "Miroslav", "PROPN", [0, 8]], ["Horn\u00ed\u010dek", "Horn\u00ed\u010dek", "PROPN", [9, 17]], ["n\u00e1s", "my", "PRON", [18, 21]], ["nav\u0161t\u00edvil", "nav\u0161t\u00edvit", "VERB", [22, 31]], ["i", "i", "CCONJ", [32, 33]], ["zde", "zde", "ADV", [34, 37]], ["v", "v", "ADP", [38, 39]], ["Calgary", "Calgary", "PROPN", [40, 47]], [".", ".", "PUNCT", [47, 48]]]], ["calgarske-listy_2003_unor_ocr.txt", "Na hawajsk\u00e9m ostrov\u011b Kauai, p\u0159ed koncem minul\u00e9ho roku se se\u0161lo celkem 16 \u00fa\u010dastn\u00edk\u016f ku spole\u010dn\u00e9mu kempov\u00e1n\u00ed..", [["Na", "na", "ADP", [0, 2]], ["hawajsk\u00e9m", "hawajsk\u00fd", "ADJ", [3, 12]], ["ostrov\u011b", "ostrov", "NOUN", [13, 20]], ["Kauai", "Kauai", "PROPN", [21, 26]], [",", ",", "PUNCT", [26, 27]], ["p\u0159ed", "p\u0159ed", "ADP", [28, 32]], ["koncem", "konec", "NOUN", [33, 39]], ["minul\u00e9ho", "minul\u00fd", "ADJ", [40, 48]], ["roku", "rok", "NOUN", [49, 53]], ["se", "se", "PRON", [54, 56]], ["se\u0161lo", "sej\u00edt", "VERB", [57, 62]], ["celkem", "celkem", "ADV", [63, 69]], ["16", "16", "NUM", [70, 72]], ["\u00fa\u010dastn\u00edk\u016f", "\u00fa\u010dastn\u00edk", "NOUN", [73, 82]], ["ku", "k", "ADP", [83, 85]], ["spole\u010dn\u00e9mu", "spole\u010dn\u00fd", "ADJ", [86, 96]], ["kempov\u00e1n\u00ed", "kempov\u00e1n\u00ed", "NOUN", [97, 106]], [".", ".", "PUNCT", [106, 107]], [".", ".", "PUNCT", [107, 108]]]], ["calgarske-listy_2003_unor_ocr.txt", "Pochvalovali si p\u0159\u00edjemn\u00e9 po\u010das\u00ed, v\u00fdborn\u00e9 \u010derstv\u00e9 ovoce na lok\u00e1ln\u00edch trz\u00edch a teplota vody v oce\u00e1nu byla 26,5 C.", [["Pochvalovali", "pochvalovat", "VERB", [0, 12]], ["si", "se", "PRON", [13, 15]], ["p\u0159\u00edjemn\u00e9", "p\u0159\u00edjemn\u00fd", "ADJ", [16, 24]], ["po\u010das\u00ed", "po\u010das\u00ed", "NOUN", [25, 31]], [",", ",", "PUNCT", [31, 32]], ["v\u00fdborn\u00e9", "v\u00fdborn\u00fd", "ADJ", [33, 40]], ["\u010derstv\u00e9", "\u010derstv\u00fd", "ADJ", [41, 48]], ["ovoce", "ovoce", "NOUN", [49, 54]], ["na", "na", "ADP", [55, 57]], ["lok\u00e1ln\u00edch", "lok\u00e1ln\u00ed", "ADJ", [58, 67]], ["trz\u00edch", "trh", "NOUN", [68, 74]], ["a", "a", "CCONJ", [75, 76]], ["teplota", "teplota", "NOUN", [77, 84]], ["vody", "voda", "NOUN", [85, 89]], ["v", "v", "ADP", [90, 91]], ["oce\u00e1nu", "oce\u00e1n", "NOUN", [92, 98]], ["byla", "b\u00fdt", "AUX", [99, 103]], ["26", "26", "NUM", [104, 106]], [",", ",", "PUNCT", [106, 107]], ["5", "5", "NUM", [107, 108]], ["C", "Celsius", "PROPN", [109, 110]], [".", ".", "PUNCT", [110, 111]]]], ["calgarske-listy_2003_unor_ocr.txt", "Samotn\u00e9 V\u00e1noce pak pro\u017eil n\u00e1\u0161 nejmlad\u0161\u00ed \u010dlen v\u00fdboru pobo\u010dky Tom\u00e1\u0161 Nevesel\u00fd na sv\u00e9 v\u00fdprav\u011b na nejvy\u0161\u0161\u00ed horu obou americk\u00fdch kontinent\u016f.", [["Samotn\u00e9", "samotn\u00fd", "ADJ", [0, 7]], ["V\u00e1noce", "V\u00e1noce", "NOUN", [8, 14]], ["pak", "pak", "ADV", [15, 18]], ["pro\u017eil", "pro\u017e\u00edt", "VERB", [19, 25]], ["n\u00e1\u0161", "n\u00e1\u0161", "DET", [26, 29]], ["nejmlad\u0161\u00ed", "mlad\u00fd", "ADJ", [30, 39]], ["\u010dlen", "\u010dlen", "NOUN", [40, 44]], ["v\u00fdboru", "v\u00fdbor", "NOUN", [45, 51]], ["pobo\u010dky", "pobo\u010dka", "NOUN", [52, 59]], ["Tom\u00e1\u0161", "Tom\u00e1\u0161", "PROPN", [60, 65]], ["Nevesel\u00fd", "Nevesel\u00fd", "PROPN", [66, 74]], ["na", "na", "ADP", [75, 77]], ["sv\u00e9", "sv\u016fj", "DET", [78, 81]], ["v\u00fdprav\u011b", "v\u00fdprava", "NOUN", [82, 89]], ["na", "na", "ADP", [90, 92]], ["nejvy\u0161\u0161\u00ed", "vysok\u00fd", "ADJ", [93, 101]], ["horu", "hora", "NOUN", [102, 106]], ["obou", "oba", "NUM", [107, 111]], ["americk\u00fdch", "americk\u00fd", "ADJ", [112, 122]], ["kontinent\u016f", "kontinent", "NOUN", [123, 133]], [".", ".", "PUNCT", [133, 134]]]], ["calgarske-listy_2003_unor_ocr.txt", "Jedn\u00e1 se o sopku Acongaqua na \u00fazem\u00ed Argentiny, kter\u00e1 dosahuje 6,700 metr\u016f.", [["Jedn\u00e1", "jednat", "VERB", [0, 5]], ["se", "se", "PRON", [6, 8]], ["o", "o", "ADP", [9, 10]], ["sopku", "sopka", "NOUN", [11, 16]], ["Acongaqua", "Acongaqua", "PROPN", [17, 26]], ["na", "na", "ADP", [27, 29]], ["\u00fazem\u00ed", "\u00fazem\u00ed", "NOUN", [30, 35]], ["Argentiny", "Argentina", "PROPN", [36, 45]], [",", ",", "PUNCT", [45, 46]], ["kter\u00e1", "kter\u00fd", "DET", [47, 52]], ["dosahuje", "dosahovat", "VERB", [53, 61]], ["6", "6", "NUM", [62, 63]], [",", ",", "PUNCT", [63, 64]], ["700", "700", "NUM", [64, 67]], ["metr\u016f", "metr", "NOUN", [68, 73]], [".", ".", "PUNCT", [73, 74]]]], ["calgarske-listy_2003_unor_ocr.txt", "Dal\u0161\u00ed \u010dlen na\u0161\u00ed komunity, Milan Netuka z Goldenu si vyjel do d\u00e1ln\u00e9ho Ruska a poslal pohled z chladn\u00e9ho m\u011bsta Irkutsku.", [["Dal\u0161\u00ed", "dal\u0161\u00ed", "ADJ", [0, 5]], ["\u010dlen", "\u010dlen", "NOUN", [6, 10]], ["na\u0161\u00ed", "n\u00e1\u0161", "DET", [11, 15]], ["komunity", "komunita", "NOUN", [16, 24]], [",", ",", "PUNCT", [24, 25]], ["Milan", "Milan", "PROPN", [26, 31]], ["Netuka", "Netuk", "PROPN", [32, 38]], ["z", "z", "ADP", [39, 40]], ["Goldenu", "Golden", "PROPN", [41, 48]], ["si", "se", "PRON", [49, 51]], ["vyjel", "vyjet", "VERB", [52, 57]], ["do", "do", "ADP", [58, 60]], ["d\u00e1ln\u00e9ho", "d\u00e1ln\u00fd", "ADJ", [61, 68]], ["Ruska", "Rusko", "PROPN", [69, 74]], ["a", "a", "CCONJ", [75, 76]], ["poslal", "poslat", "VERB", [77, 83]], ["pohled", "pohled", "NOUN", [84, 90]], ["z", "z", "ADP", [91, 92]], ["chladn\u00e9ho", "chladn\u00fd", "ADJ", [93, 102]], ["m\u011bsta", "m\u011bsto", "NOUN", [103, 108]], ["Irkutsku", "Irkutsk", "PROPN", [109, 117]], [".", ".", "PUNCT", [117, 118]]]], ["calgarske-listy_2003_unor_ocr.txt", "Milan um\u00ed v\u00fdborn\u011b zazp\u00edvat p\u0159i kyta\u0159e na na\u0161ich piknic\u00edch v Radium, zn\u00e1mou p\u00edse\u0148 \"Rosa na kolej\u00edch\".", [["Milan", "Milan", "PROPN", [0, 5]], ["um\u00ed", "um\u011bt", "VERB", [6, 9]], ["v\u00fdborn\u011b", "v\u00fdborn\u011b", "ADV", [10, 17]], ["zazp\u00edvat", "zazp\u00edvat", "VERB", [18, 26]], ["p\u0159i", "p\u0159i", "ADP", [27, 30]], ["kyta\u0159e", "kytara", "NOUN", [31, 37]], ["na", "na", "ADP", [38, 40]], ["na\u0161ich", "n\u00e1\u0161", "DET", [41, 47]], ["piknic\u00edch", "piknik", "NOUN", [48, 57]], ["v", "v", "ADP", [58, 59]], ["Radium", "Radium", "PROPN", [60, 66]], [",", ",", "PUNCT", [66, 67]], ["zn\u00e1mou", "zn\u00e1m\u00fd", "ADJ", [68, 74]], ["p\u00edse\u0148", "p\u00edse\u0148", "NOUN", [75, 80]], ["\"", "\"", "PUNCT", [81, 82]], ["Rosa", "rosa", "PROPN", [82, 86]], ["na", "na", "ADP", [87, 89]], ["kolej\u00edch", "kolej", "NOUN", [90, 98]], ["\"", "\"", "PUNCT", [98, 99]], [".", ".", "PUNCT", [99, 100]]]], ["calgarske-listy_2003_unor_ocr.txt", "Pokus\u00edme se ho p\u0159esv\u011bd\u010dit o naps\u00e1n\u00ed report\u00e1\u017ee z jeho zimn\u00ed anabaze po d\u00e1ln\u00e9 Rusi o tom, jak tam na magistr\u00e1le mrzne rosa na kolej\u00edch.", [["Pokus\u00edme", "pokusit", "VERB", [0, 8]], ["se", "se", "PRON", [9, 11]], ["ho", "on", "PRON", [12, 14]], ["p\u0159esv\u011bd\u010dit", "p\u0159esv\u011bd\u010dit", "VERB", [15, 25]], ["o", "o", "ADP", [26, 27]], ["naps\u00e1n\u00ed", "naps\u00e1n\u00ed", "NOUN", [28, 35]], ["report\u00e1\u017ee", "report\u00e1\u017e", "NOUN", [36, 45]], ["z", "z", "ADP", [46, 47]], ["jeho", "jeho", "DET", [48, 52]], ["zimn\u00ed", "zimn\u00ed", "ADJ", [53, 58]], ["anabaze", "anabaze", "NOUN", [59, 66]], ["po", "po", "ADP", [67, 69]], ["d\u00e1ln\u00e9", "d\u00e1ln\u00fd", "ADJ", [70, 75]], ["Rusi", "Rus", "PROPN", [76, 80]], ["o", "o", "ADP", [81, 82]], ["tom", "ten", "DET", [83, 86]], [",", ",", "PUNCT", [86, 87]], ["jak", "jak", "ADV", [88, 91]], ["tam", "tam", "ADV", [92, 95]], ["na", "na", "ADP", [96, 98]], ["magistr\u00e1le", "magistr\u00e1la", "NOUN", [99, 109]], ["mrzne", "mrznout", "VERB", [110, 115]], ["rosa", "rosa", "NOUN", [116, 120]], ["na", "na", "ADP", [121, 123]], ["kolej\u00edch", "kolej", "NOUN", [124, 132]], [".", ".", "PUNCT", [132, 133]]]], ["calgarske-listy_2003_unor_ocr.txt", "Mnoho mlad\u00fdch kana\u010fan\u016f \u010desk\u00e9ho p\u016fvodu, kte\u0159\u00ed se ji\u017e narodili v Kanad\u011b si \u017e\u00e1d\u00e1 o p\u0159id\u011blen\u00ed \u010desk\u00e9ho ob\u010danstv\u00ed a vystaven\u00ed \u010desk\u00e9ho pasu.", [["Mnoho", "mnoho", "DET", [0, 5]], ["mlad\u00fdch", "mlad\u00fd", "ADJ", [6, 13]], ["kana\u010fan\u016f", "kana\u010fan", "NOUN", [14, 22]], ["\u010desk\u00e9ho", "\u010desk\u00fd", "ADJ", [23, 30]], ["p\u016fvodu", "p\u016fvod", "NOUN", [31, 37]], [",", ",", "PUNCT", [37, 38]], ["kte\u0159\u00ed", "kter\u00fd", "DET", [39, 44]], ["se", "se", "PRON", [45, 47]], ["ji\u017e", "ji\u017e", "ADV", [48, 51]], ["narodili", "narodit", "VERB", [52, 60]], ["v", "v", "ADP", [61, 62]], ["Kanad\u011b", "Kanada", "PROPN", [63, 69]], ["si", "se", "PRON", [70, 72]], ["\u017e\u00e1d\u00e1", "\u017e\u00e1dat", "VERB", [73, 77]], ["o", "o", "ADP", [78, 79]], ["p\u0159id\u011blen\u00ed", "p\u0159id\u011blen\u00ed", "NOUN", [80, 89]], ["\u010desk\u00e9ho", "\u010desk\u00fd", "ADJ", [90, 97]], ["ob\u010danstv\u00ed", "ob\u010danstv\u00ed", "NOUN", [98, 107]], ["a", "a", "CCONJ", [108, 109]], ["vystaven\u00ed", "vystaven\u00ed", "NOUN", [110, 119]], ["\u010desk\u00e9ho", "\u010desk\u00fd", "ADJ", [120, 127]], ["pasu", "pas", "NOUN", [128, 132]], [".", ".", "PUNCT", [132, 133]]]], ["calgarske-listy_2003_unor_ocr.txt", "Jejich v\u00fdhoda bude snadn\u00e9 cestov\u00e1n\u00ed a i podnik\u00e1n\u00ed v budouc\u00ed sjednocen\u00e9 Evrop\u011b.", [["Jejich", "jeho", "DET", [0, 6]], ["v\u00fdhoda", "v\u00fdhoda", "NOUN", [7, 13]], ["bude", "b\u00fdt", "AUX", [14, 18]], ["snadn\u00e9", "snadn\u00fd", "ADJ", [19, 25]], ["cestov\u00e1n\u00ed", "cestov\u00e1n\u00ed", "NOUN", [26, 35]], ["a", "a", "CCONJ", [36, 37]], ["i", "i", "CCONJ", [38, 39]], ["podnik\u00e1n\u00ed", "podnik\u00e1n\u00ed", "NOUN", [40, 49]], ["v", "v", "ADP", [50, 51]], ["budouc\u00ed", "budouc\u00ed", "ADJ", [52, 59]], ["sjednocen\u00e9", "sjednocen\u00fd", "ADJ", [60, 70]], ["Evrop\u011b", "Evropa", "PROPN", [71, 77]], [".", ".", "PUNCT", [77, 78]]]], ["calgarske-listy_2003_unor_ocr.txt", "Nyn\u00ed se zase pod\u00edv\u00e1me do seznam\u016f co n\u00e1m p\u0159edala na\u0161e pan\u00ed pokladn\u00ed s p\u0159ehledem p\u0159edplatn\u00e9ho na \u010dlenstv\u00ed, pos\u00edl\u00e1n\u00ed \u010dasopisu a sponzorsk\u00e9 dary na vyd\u00e1v\u00e1n\u00ed na\u0161ich Calgarsk\u00fdch List\u016f.", [["Nyn\u00ed", "nyn\u00ed", "ADV", [0, 4]], ["se", "se", "PRON", [5, 7]], ["zase", "zase", "ADV", [8, 12]], ["pod\u00edv\u00e1me", "pod\u00edvat", "VERB", [13, 21]], ["do", "do", "ADP", [22, 24]], ["seznam\u016f", "seznam", "NOUN", [25, 32]], ["co", "co", "PRON", [33, 35]], ["n\u00e1m", "my", "PRON", [36, 39]], ["p\u0159edala", "p\u0159edat", "VERB", [40, 47]], ["na\u0161e", "n\u00e1\u0161", "DET", [48, 52]], ["pan\u00ed", "pan\u00ed", "NOUN", [53, 57]], ["pokladn\u00ed", "pokladn\u00ed", "ADJ", [58, 66]], ["s", "s", "ADP", [67, 68]], ["p\u0159ehledem", "p\u0159ehled", "NOUN", [69, 78]], ["p\u0159edplatn\u00e9ho", "p\u0159edplatn\u00fd", "ADJ", [79, 91]], ["na", "na", "ADP", [92, 94]], ["\u010dlenstv\u00ed", "\u010dlenstv\u00ed", "NOUN", [95, 103]], [",", ",", "PUNCT", [103, 104]], ["pos\u00edl\u00e1n\u00ed", "pos\u00edl\u00e1n\u00ed", "NOUN", [105, 113]], ["\u010dasopisu", "\u010dasopis", "NOUN", [114, 122]], ["a", "a", "CCONJ", [123, 124]], ["sponzorsk\u00e9", "sponzorsk\u00fd", "ADJ", [125, 135]], ["dary", "dar", "NOUN", [136, 140]], ["na", "na", "ADP", [141, 143]], ["vyd\u00e1v\u00e1n\u00ed", "vyd\u00e1v\u00e1n\u00ed", "NOUN", [144, 152]], ["na\u0161ich", "n\u00e1\u0161", "DET", [153, 159]], ["Calgarsk\u00fdch", "calgarsk\u00fd", "ADJ", [160, 171]], ["List\u016f", "list", "NOUN", [172, 177]], [".", ".", "PUNCT", [177, 178]]]], ["calgarske-listy_2003_unor_ocr.txt", "\u0160ek na 60 dolar\u016f n\u00e1m poslala rodina pana Vlasty Chr\u00e1pav\u00e9ho, \u0161ek na 50 dolar\u016f zaslala pan\u00ed Marie Kersov\u00e1 z Bragg Creek.", [["\u0160ek", "\u0161ek", "NOUN", [0, 3]], ["na", "na", "ADP", [4, 6]], ["60", "60", "NUM", [7, 9]], ["dolar\u016f", "dolar", "NOUN", [10, 16]], ["n\u00e1m", "my", "PRON", [17, 20]], ["poslala", "poslat", "VERB", [21, 28]], ["rodina", "rodina", "NOUN", [29, 35]], ["pana", "pan", "NOUN", [36, 40]], ["Vlasty", "Vlasta", "PROPN", [41, 47]], ["Chr\u00e1pav\u00e9ho", "Chr\u00e1pav\u00fd", "PROPN", [48, 58]], [",", ",", "PUNCT", [58, 59]], ["\u0161ek", "\u0161ek", "NOUN", [60, 63]], ["na", "na", "ADP", [64, 66]], ["50", "50", "NUM", [67, 69]], ["dolar\u016f", "dolar", "NOUN", [70, 76]], ["zaslala", "zaslat", "VERB", [77, 84]], ["pan\u00ed", "pan\u00ed", "NOUN", [85, 89]], ["Marie", "Marie", "PROPN", [90, 95]], ["Kersov\u00e1", "Kersov\u00e1", "PROPN", [96, 103]], ["z", "z", "ADP", [104, 105]], ["Bragg", "Bragg", "X", [106, 111]], ["Creek", "Creek", "X", [112, 117]], [".", ".", "PUNCT", [117, 118]]]], ["calgarske-listy_2003_unor_ocr.txt", "D\u00e1le n\u00e1sleduje sponzorsk\u00fd dar od pana Zde\u0148ka Net\u00edka 45 dolar\u016f.", [["D\u00e1le", "d\u00e1le", "ADV", [0, 4]], ["n\u00e1sleduje", "n\u00e1sledovat", "VERB", [5, 14]], ["sponzorsk\u00fd", "sponzorsk\u00fd", "ADJ", [15, 25]], ["dar", "dar", "NOUN", [26, 29]], ["od", "od", "ADP", [30, 32]], ["pana", "pan", "NOUN", [33, 37]], ["Zde\u0148ka", "Zden\u011bk", "PROPN", [38, 44]], ["Net\u00edka", "Net\u00edk", "PROPN", [45, 51]], ["45", "45", "NUM", [52, 54]], ["dolar\u016f", "dolar", "NOUN", [55, 61]], [".", ".", "PUNCT", [61, 62]]]], ["calgarske-listy_2003_unor_ocr.txt", "Pan Josef M\u017eik poslal 30ti dolarov\u00fd \u0161ek a hezk\u00fd dopis pro redakci.", [["Pan", "pan", "NOUN", [0, 3]], ["Josef", "Josef", "PROPN", [4, 9]], ["M\u017eik", "M\u017eik", "PROPN", [10, 14]], ["poslal", "poslat", "VERB", [15, 21]], ["30", "30", "NUM", [22, 24]], ["ti", "ten", "DET", [24, 26]], ["dolarov\u00fd", "dolarov\u00fd", "ADJ", [27, 35]], ["\u0161ek", "\u0161ek", "NOUN", [36, 39]], ["a", "a", "CCONJ", [40, 41]], ["hezk\u00fd", "hezk\u00fd", "ADJ", [42, 47]], ["dopis", "dopis", "NOUN", [48, 53]], ["pro", "pro", "ADP", [54, 57]], ["redakci", "redakce", "NOUN", [58, 65]], [".", ".", "PUNCT", [65, 66]]]], ["calgarske-listy_2003_unor_ocr.txt", "Tak\u00e9 pan\u00ed Zdenka Machutov\u00e1 poslala 30 dolar\u016f.", [["Tak\u00e9", "tak\u00e9", "ADV", [0, 4]], ["pan\u00ed", "pan\u00ed", "NOUN", [5, 9]], ["Zdenka", "Zdenek", "PROPN", [10, 16]], ["Machutov\u00e1", "Machutov\u00e1", "PROPN", [17, 26]], ["poslala", "poslat", "VERB", [27, 34]], ["30", "30", "NUM", [35, 37]], ["dolar\u016f", "dolar", "NOUN", [38, 44]], [".", ".", "PUNCT", [44, 45]]]], ["calgarske-listy_2003_unor_ocr.txt", "N\u00e1sleduje \u0159ada \u0161ek\u016f po 20 ti dolarech od pan\u00ed A.Cabrnochov\u00e9, pana Josefa H\u00e1jka z Roudnice nad Labem, Karla Hofmana, od pan\u00ed Z. Rybanov\u00e9, pana Ale\u0161e Sedl\u00e1ka, od pan\u00ed Marie Spev\u00e1k, pana Jindry Streibla, pan\u00ed M\u00edly Vesel\u00e9 a pana Petra Ziezlera.", [["N\u00e1sleduje", "n\u00e1sledovat", "VERB", [0, 9]], ["\u0159ada", "\u0159ada", "NOUN", [10, 14]], ["\u0161ek\u016f", "\u0161ek", "NOUN", [15, 19]], ["po", "po", "ADP", [20, 22]], ["20", "20", "NUM", [23, 25]], ["ti", "ten", "DET", [26, 28]], ["dolarech", "dolar", "NOUN", [29, 37]], ["od", "od", "ADP", [38, 40]], ["pan\u00ed", "pan\u00ed", "NOUN", [41, 45]], ["A", "A", "NOUN", [46, 47]], [".", ".", "PUNCT", [47, 48]], ["Cabrnochov\u00e9", "Cabrnoch", "PROPN", [48, 59]], [",", ",", "PUNCT", [59, 60]], ["pana", "pan", "NOUN", [61, 65]], ["Josefa", "Josef", "PROPN", [66, 72]], ["H\u00e1jka", "H\u00e1jka", "PROPN", [73, 78]], ["z", "z", "ADP", [79, 80]], ["Roudnice", "Roudnice", "PROPN", [81, 89]], ["nad", "nad", "ADP", [90, 93]], ["Labem", "Labe", "PROPN", [94, 99]], [",", ",", "PUNCT", [99, 100]], ["Karla", "Karel", "PROPN", [101, 106]], ["Hofmana", "Hofman", "PROPN", [107, 114]], [",", ",", "PUNCT", [114, 115]], ["od", "od", "ADP", [116, 118]], ["pan\u00ed", "pan\u00ed", "NOUN", [119, 123]], ["Z", "Z", "NOUN", [124, 125]], [".", ".", "PUNCT", [125, 126]], ["Rybanov\u00e9", "Rybanov\u00e1", "PROPN", [127, 135]], [",", ",", "PUNCT", [135, 136]], ["pana", "pan", "NOUN", [137, 141]], ["Ale\u0161e", "Ale\u0161", "PROPN", [142, 147]], ["Sedl\u00e1ka", "Sedl\u00e1k", "PROPN", [148, 155]], [",", ",", "PUNCT", [155, 156]], ["od", "od", "ADP", [157, 159]], ["pan\u00ed", "pan\u00ed", "NOUN", [160, 164]], ["Marie", "Marie", "PROPN", [165, 170]], ["Spev\u00e1k", "Spev\u00e1k", "PROPN", [171, 177]], [",", ",", "PUNCT", [177, 178]], ["pana", "pan", "NOUN", [179, 183]], ["Jindry", "Jindry", "PROPN", [184, 190]], ["Streibla", "Streibl", "PROPN", [191, 199]], [",", ",", "PUNCT", [199, 200]], ["pan\u00ed", "pan\u00ed", "NOUN", [201, 205]], ["M\u00edly", "M\u00edla", "PROPN", [206, 210]], ["Vesel\u00e9", "Vesel\u00e1", "PROPN", [211, 217]], ["a", "a", "CCONJ", [218, 219]], ["pana", "pan", "NOUN", [220, 224]], ["Petra", "Petr", "PROPN", [225, 230]], ["Ziezlera", "Ziezler", "PROPN", [231, 239]], [".", ".", "PUNCT", [239, 240]]]], ["calgarske-listy_2003_unor_ocr.txt", "Pan\u00ed Stanislava Stastny poslala celkem 17 dolar\u016f.", [["Pan\u00ed", "pan\u00ed", "NOUN", [0, 4]], ["Stanislava", "Stanislav", "PROPN", [5, 15]], ["Stastny", "Stastna", "PROPN", [16, 23]], ["poslala", "poslat", "VERB", [24, 31]], ["celkem", "celkem", "ADV", [32, 38]], ["17", "17", "NUM", [39, 41]], ["dolar\u016f", "dolar", "NOUN", [42, 48]], [".", ".", "PUNCT", [48, 49]]]], ["calgarske-listy_2003_unor_ocr.txt", "D\u00e1le tu m\u00e1me 15 ti dolarov\u00fd \u0161ek od pana Ernsta Keornera, pana Milo\u0161e Nov\u00e1ka a pana Karla Pavl\u00edka z Lethbridge.", [["D\u00e1le", "d\u00e1le", "ADV", [0, 4]], ["tu", "tu", "ADV", [5, 7]], ["m\u00e1me", "m\u00edt", "VERB", [8, 12]], ["15", "15", "NUM", [13, 15]], ["ti", "ten", "DET", [16, 18]], ["dolarov\u00fd", "dolarov\u00fd", "ADJ", [19, 27]], ["\u0161ek", "\u0161ek", "NOUN", [28, 31]], ["od", "od", "ADP", [32, 34]], ["pana", "pan", "NOUN", [35, 39]], ["Ernsta", "Ernst", "PROPN", [40, 46]], ["Keornera", "Keorner", "PROPN", [47, 55]], [",", ",", "PUNCT", [55, 56]], ["pana", "pan", "NOUN", [57, 61]], ["Milo\u0161e", "Milo\u0161", "PROPN", [62, 68]], ["Nov\u00e1ka", "Nov\u00e1k", "PROPN", [69, 75]], ["a", "a", "CCONJ", [76, 77]], ["pana", "pan", "NOUN", [78, 82]], ["Karla", "Karel", "PROPN", [83, 88]], ["Pavl\u00edka", "Pavl\u00edk", "PROPN", [89, 96]], ["z", "z", "ADP", [97, 98]], ["Lethbridge", "Lethbridge", "PROPN", [99, 109]], [".", ".", "PUNCT", [109, 110]]]], ["calgarske-listy_2003_unor_ocr.txt", "Po 10 ti dolarech p\u0159edplatn\u00e9ho poslali pan Vl\u00e1d.", [["Po", "po", "ADP", [0, 2]], ["10", "10", "NUM", [3, 5]], ["ti", "ten", "DET", [6, 8]], ["dolarech", "dolar", "NOUN", [9, 17]], ["p\u0159edplatn\u00e9ho", "p\u0159edplatn\u00fd", "ADJ", [18, 30]], ["poslali", "poslat", "VERB", [31, 38]], ["pan", "pan", "NOUN", [39, 42]], ["Vl\u00e1d", "vl\u00e1d", "NOUN", [43, 47]], [".", ".", "PUNCT", [47, 48]]]], ["calgarske-listy_2003_unor_ocr.txt", "Felix, pan Ivan H\u00fdsek, pan Kinzl, pan Frank Pa\u0161ek, pan\u00ed Pellar- Hobbs, pan E. Retzer a pan\u00ed Jana Volf.", [["Felix", "Felix", "PROPN", [0, 5]], [",", ",", "PUNCT", [5, 6]], ["pan", "pan", "NOUN", [7, 10]], ["Ivan", "Ivan", "PROPN", [11, 15]], ["H\u00fdsek", "H\u00fdsek", "PROPN", [16, 21]], [",", ",", "PUNCT", [21, 22]], ["pan", "pan", "NOUN", [23, 26]], ["Kinzl", "Kinzl", "PROPN", [27, 32]], [",", ",", "PUNCT", [32, 33]], ["pan", "pan", "NOUN", [34, 37]], ["Frank", "Frank", "PROPN", [38, 43]], ["Pa\u0161ek", "Pa\u0161ek", "PROPN", [44, 49]], [",", ",", "PUNCT", [49, 50]], ["pan\u00ed", "pan\u00ed", "NOUN", [51, 55]], ["Pellar", "Pellar", "PROPN", [56, 62]], ["-", "-", "PUNCT", [62, 63]], ["Hobbs", "Hobbs", "PROPN", [64, 69]], [",", ",", "PUNCT", [69, 70]], ["pan", "pan", "NOUN", [71, 74]], ["E", "E", "NOUN", [75, 76]], [".", ".", "PUNCT", [76, 77]], ["Retzer", "Retzer", "PROPN", [78, 84]], ["a", "a", "CCONJ", [85, 86]], ["pan\u00ed", "pan\u00ed", "NOUN", [87, 91]], ["Jana", "Jan", "PROPN", [92, 96]], ["Volf", "Volf", "PROPN", [97, 101]], [".", ".", "PUNCT", [101, 102]]]], ["calgarske-listy_2003_unor_ocr.txt", "V\u0161em zde uveden\u00fdm d\u00e1rc\u016fm a p\u0159edplatitel\u016fm velmi up\u0159\u00edmn\u011b d\u011bkujeme za jejich st\u00e1lou podporu na\u0161\u00ed dobrovoln\u00e9 pr\u00e1ce pro krajanskou komunitu.", [["V\u0161em", "v\u0161echen", "DET", [0, 4]], ["zde", "zde", "ADV", [5, 8]], ["uveden\u00fdm", "uveden\u00fd", "ADJ", [9, 17]], ["d\u00e1rc\u016fm", "d\u00e1rce", "NOUN", [18, 24]], ["a", "a", "CCONJ", [25, 26]], ["p\u0159edplatitel\u016fm", "p\u0159edplatitel", "NOUN", [27, 41]], ["velmi", "velmi", "ADV", [42, 47]], ["up\u0159\u00edmn\u011b", "up\u0159\u00edmn\u011b", "ADV", [48, 55]], ["d\u011bkujeme", "d\u011bkovat", "VERB", [56, 64]], ["za", "za", "ADP", [65, 67]], ["jejich", "jeho", "DET", [68, 74]], ["st\u00e1lou", "st\u00e1l\u00fd", "ADJ", [75, 81]], ["podporu", "podpora", "NOUN", [82, 89]], ["na\u0161\u00ed", "n\u00e1\u0161", "DET", [90, 94]], ["dobrovoln\u00e9", "dobrovoln\u00fd", "ADJ", [95, 105]], ["pr\u00e1ce", "pr\u00e1ce", "NOUN", [106, 111]], ["pro", "pro", "ADP", [112, 115]], ["krajanskou", "krajansk\u00fd", "ADJ", [116, 126]], ["komunitu", "komunita", "NOUN", [127, 135]], [".", ".", "PUNCT", [135, 136]]]], ["calgarske-listy_2003_unor_ocr.txt", "P\u0159\u00edpadn\u00e9 nedostatky zavolejte na telefon 289 - 7244, penzista Vladim\u00edr Ma\u0161ata m\u00e1 hodiny od 9.30 do 18.00 a email adresu masata@telusplanet.net 16  STAROREZNA PROST\u011aJOV", [["P\u0159\u00edpadn\u00e9", "p\u0159\u00edpadn\u00fd", "ADJ", [0, 8]], ["nedostatky", "nedostatek", "NOUN", [9, 19]], ["zavolejte", "zavolat", "VERB", [20, 29]], ["na", "na", "ADP", [30, 32]], ["telefon", "telefon", "NOUN", [33, 40]], ["289", "289", "NUM", [41, 44]], ["-", "-", "PUNCT", [45, 46]], ["7244", "7244", "NUM", [47, 51]], [",", ",", "PUNCT", [51, 52]], ["penzista", "penzista", "NOUN", [53, 61]], ["Vladim\u00edr", "Vladim\u00edr", "PROPN", [62, 70]], ["Ma\u0161ata", "Ma\u0161ata", "PROPN", [71, 77]], ["m\u00e1", "m\u00edt", "VERB", [78, 80]], ["hodiny", "hodina", "NOUN", [81, 87]], ["od", "od", "ADP", [88, 90]], ["9.30", "9.30", "NUM", [91, 95]], ["do", "do", "ADP", [96, 98]], ["18.00", "18.00", "NUM", [99, 104]], ["a", "a", "CCONJ", [105, 106]], ["email", "email", "NOUN", [107, 112]], ["adresu", "adresa", "NOUN", [113, 119]], ["masata@telusplanet.net", "masata@telusplanet.net", "NOUN", [120, 142]], ["16", "16", "NUM", [143, 145]], ["STAROREZNA", "Starorezn", "PROPN", [147, 157]], ["PROST\u011aJOV", "Prost\u011bjov", "PROPN", [158, 167]]]], ["calgarske-listy_2003_unor_ocr.txt", "Ji\u017e od kv\u011btna 1998 n\u00e1\u0161 z\u00e1vod nab\u00edz\u00ed zde v Calgary 15 r\u016fzn\u00fdch v\u00fdrobk\u016f v mnoha prodejn\u00e1ch: PEACH VODKA - GRIOTKA BANANA CREAM LIK\u00c9R MERU\u0147KA CHOCOLADE LIK\u00c9R HAN\u00c1CK\u00c1 VODKA NUG\u00c1T LIK\u00c9R SLIVOVICE - GRIOTKA TUZEMSK\u00dd RUM HAN\u00c1CK\u00c1 VODKA- 1.8L CASSIS - \u010cERN\u00dd RYB\u00cdZ AMARETTO - SPECI\u00c1LN\u00cd L\u00c1HEV NOV\u00c9 V\u00ddROBKY NA CEST\u011a SPECI\u00c1LN\u011a PRO LETO\u0160N\u00cd V\u00c1NOCE NAB\u00cdZ\u00cdME:........", [["Ji\u017e", "ji\u017e", "ADV", [0, 3]], ["od", "od", "ADP", [4, 6]], ["kv\u011btna", "kv\u011bten", "NOUN", [7, 13]], ["1998", "1998", "NUM", [14, 18]], ["n\u00e1\u0161", "n\u00e1\u0161", "DET", [19, 22]], ["z\u00e1vod", "z\u00e1vod", "NOUN", [23, 28]], ["nab\u00edz\u00ed", "nab\u00edzet", "VERB", [29, 35]], ["zde", "zde", "ADV", [36, 39]], ["v", "v", "ADP", [40, 41]], ["Calgary", "Calgary", "PROPN", [42, 49]], ["15", "15", "NUM", [50, 52]], ["r\u016fzn\u00fdch", "r\u016fzn\u00fd", "ADJ", [53, 60]], ["v\u00fdrobk\u016f", "v\u00fdrobek", "NOUN", [61, 68]], ["v", "v", "ADP", [69, 70]], ["mnoha", "mnoho", "DET", [71, 76]], ["prodejn\u00e1ch", "prodejna", "NOUN", [77, 87]], [":", ":", "PUNCT", [87, 88]], ["PEACH", "Peach", "X", [89, 94]], ["VODKA", "vodka", "NOUN", [95, 100]], ["-", "-", "PUNCT", [101, 102]], ["GRIOTKA", "Griotka", "X", [103, 110]], ["BANANA", "Banana", "X", [111, 117]], ["CREAM", "Cream", "X", [118, 123]], ["LIK\u00c9R", "Lik\u00e1r", "X", [124, 129]], ["MERU\u0147KA", "Meru\u0148ka", "X", [130, 137]], ["CHOCOLADE", "Chocolade", "X", [138, 147]], ["LIK\u00c9R", "Lik\u00e1r", "X", [148, 153]], ["HAN\u00c1CK\u00c1", "han\u00e1ck\u00fd", "ADJ", [154, 161]], ["VODKA", "vodka", "NOUN", [162, 167]], ["NUG\u00c1T", "NUG\u00c1T", "PROPN", [168, 173]], ["LIK\u00c9R", "lik\u00e9r", "NOUN", [174, 179]], ["SLIVOVICE", "slivovice", "NOUN", [180, 189]], ["-", "-", "PUNCT", [190, 191]], ["GRIOTKA", "Griotka", "PROPN", [192, 199]], ["TUZEMSK\u00dd", "tuzemsk\u00fd", "ADJ", [200, 208]], ["RUM", "RUM", "NOUN", [209, 212]], ["HAN\u00c1CK\u00c1", "han\u00e1ck\u00fd", "ADJ", [213, 220]], ["VODKA", "vodka", "NOUN", [221, 226]], ["-", "-", "PUNCT", [226, 227]], ["1.8L", "1.8L", "NUM", [228, 232]], ["CASSIS", "Cassis", "PROPN", [233, 239]], ["-", "-", "PUNCT", [240, 241]], ["\u010cERN\u00dd", "\u010dern\u00fd", "ADJ", [242, 247]], ["RYB\u00cdZ", "ryb\u011bz", "NOUN", [248, 253]], ["AMARETTO", "Amaretto", "PROPN", [254, 262]], ["-", "-", "PUNCT", [263, 264]], ["SPECI\u00c1LN\u00cd", "speci\u00e1ln\u00ed", "ADJ", [265, 274]], ["L\u00c1HEV", "l\u00e1hev", "NOUN", [275, 280]], ["NOV\u00c9", "nov\u00fd", "ADJ", [281, 285]], ["V\u00ddROBKY", "v\u00fdrobek", "NOUN", [286, 293]], ["NA", "na", "ADP", [294, 296]], ["CEST\u011a", "cesta", "NOUN", [297, 302]], ["SPECI\u00c1LN\u011a", "speci\u00e1ln\u011b", "ADV", [303, 312]], ["PRO", "pro", "ADP", [313, 316]], ["LETO\u0160N\u00cd", "leto\u0161n\u00ed", "ADJ", [317, 324]], ["V\u00c1NOCE", "v\u00e1noce", "NOUN", [325, 331]], ["NAB\u00cdZ\u00cdME", "nab\u00edzet", "VERB", [332, 340]], [":", ":", "PUNCT", [340, 341]], [".", ".", "PUNCT", [341, 342]], [".", ".", "PUNCT", [342, 343]], [".", ".", "PUNCT", [343, 344]], [".", ".", "PUNCT", [344, 345]], [".", ".", "PUNCT", [345, 346]], [".", ".", "PUNCT", [346, 347]], [".", ".", "PUNCT", [347, 348]], [".", ".", "PUNCT", [348, 349]]]], ["calgarske-listy_2003_unor_ocr.txt", "BOHEMIA SECT CHAMPAGNE", [["BOHEMIA", "Bohemia", "PROPN", [0, 7]], ["SECT", "Sect", "X", [8, 12]], ["CHAMPAGNE", "Champagne", "X", [13, 22]]]], ["calgarske-listy_2003_unor_ocr.txt", "V\u0161ech 15 druh\u016f je mo\u017eno koupit za p\u0159ijateln\u00e9 ceny v t\u011bchto dvou calgarsk\u00fdch prodejn\u00e1ch lihovin : 1) 2) Fourth Street Liq. Store & Wine Cellar, 1809 - 4 th Str. SW. Willow Park Liq.", [["V\u0161ech", "v\u0161echen", "DET", [0, 5]], ["15", "15", "NUM", [6, 8]], ["druh\u016f", "druh", "NOUN", [9, 14]], ["je", "b\u00fdt", "AUX", [15, 17]], ["mo\u017eno", "mo\u017en\u00fd", "ADJ", [18, 23]], ["koupit", "koupit", "VERB", [24, 30]], ["za", "za", "ADP", [31, 33]], ["p\u0159ijateln\u00e9", "p\u0159ijateln\u00fd", "ADJ", [34, 44]], ["ceny", "cena", "NOUN", [45, 49]], ["v", "v", "ADP", [50, 51]], ["t\u011bchto", "tento", "DET", [52, 58]], ["dvou", "dva", "NUM", [59, 63]], ["calgarsk\u00fdch", "calgarsk\u00fd", "ADJ", [64, 75]], ["prodejn\u00e1ch", "prodejna", "NOUN", [76, 86]], ["lihovin", "lihovina", "NOUN", [87, 94]], [":", ":", "PUNCT", [95, 96]], ["1", "1", "NUM", [97, 98]], [")", ")", "PUNCT", [98, 99]], ["2", "2", "NUM", [100, 101]], [")", ")", "PUNCT", [101, 102]], ["Fourth", "Fourth", "X", [103, 109]], ["Street", "Street", "X", [110, 116]], ["Liq", "Liq", "X", [117, 120]], [".", ".", "PUNCT", [120, 121]], ["Store", "Store", "X", [122, 127]], ["&", "&", "PUNCT", [128, 129]], ["Wine", "Wine", "X", [130, 134]], ["Cellar", "Cellar", "X", [135, 141]], [",", ",", "PUNCT", [141, 142]], ["1809", "1809", "NUM", [143, 147]], ["-", "-", "PUNCT", [148, 149]], ["4", "4", "NUM", [150, 151]], ["th", "th", "PUNCT", [152, 154]], ["Str", "strana", "NOUN", [155, 158]], [".", ".", "PUNCT", [158, 159]], ["SW", "SW", "NOUN", [160, 162]], [".", ".", "PUNCT", [162, 163]], ["Willow", "Willow", "X", [164, 170]], ["Park", "Park", "X", [171, 175]], ["Liq", "Liq", "X", [176, 179]], [".", ".", "PUNCT", [179, 180]]]], ["calgarske-listy_2003_unor_ocr.txt", "Store, 10801 - Bonaventure Dr. SE.", [["Store", "Store", "PROPN", [0, 5]], [",", ",", "PUNCT", [5, 6]], ["10801", "10801", "NUM", [7, 12]], ["-", "-", "PUNCT", [13, 14]], ["Bonaventure", "Bonaventure", "PROPN", [15, 26]], ["Dr", "Dr", "NOUN", [27, 29]], [".", ".", "PUNCT", [29, 30]], ["SE", "se", "PRON", [31, 33]], [".", ".", "PUNCT", [33, 34]]]], ["calgarske-listy_2003_unor_ocr.txt", "Brought to Canada by : TRU - DOR DISTRIBUTORS, Ltd. of CALGARY - Phone (403) 517- 8800 Specializes in electrolysis, facials, manicures, pedicures, cellulite, body treatments, waxing, make-up, eye brow & lash tinting.", [["Brought", "Brought", "X", [0, 7]], ["to", "ten", "DET", [8, 10]], ["Canada", "Canada", "X", [11, 17]], ["by", "b\u00fdt", "AUX", [18, 20]], [":", ":", "PUNCT", [21, 22]], ["TRU", "TRU", "NOUN", [23, 26]], ["-", "-", "PUNCT", [27, 28]], ["DOR", "Dor", "X", [29, 32]], ["DISTRIBUTORS", "Distributors", "X", [33, 45]], [",", ",", "PUNCT", [45, 46]], ["Ltd", "Ltd", "X", [47, 50]], [".", ".", "PUNCT", [50, 51]], ["of", "of", "X", [52, 54]], ["CALGARY", "Calgara", "PROPN", [55, 62]], ["-", "-", "PUNCT", [63, 64]], ["Phone", "Phone", "X", [65, 70]], ["(", "(", "PUNCT", [71, 72]], ["403", "403", "NUM", [72, 75]], [")", ")", "PUNCT", [75, 76]], ["517", "517", "NUM", [77, 80]], ["-", "-", "PUNCT", [80, 81]], ["8800", "8800", "NUM", [82, 86]], ["Specializes", "Specializes", "X", [87, 98]], ["in", "in", "X", [99, 101]], ["electrolysis", "electrolysis", "X", [102, 114]], [",", ",", "PUNCT", [114, 115]], ["facials", "facials", "X", [116, 123]], [",", ",", "PUNCT", [123, 124]], ["manicures", "manicures", "NOUN", [125, 134]], [",", ",", "PUNCT", [134, 135]], ["pedicures", "pedicures", "NOUN", [136, 145]], [",", ",", "PUNCT", [145, 146]], ["cellulite", "cellulita", "NOUN", [147, 156]], [",", ",", "PUNCT", [156, 157]], ["body", "bod", "NOUN", [158, 162]], ["treatments", "treatments", "X", [163, 173]], [",", ",", "PUNCT", [173, 174]], ["waxing", "waxing", "NOUN", [175, 181]], [",", ",", "PUNCT", [181, 182]], ["make", "make", "ADJ", [183, 187]], ["-", "-", "PUNCT", [187, 188]], ["up", "up", "X", [188, 190]], [",", ",", "PUNCT", [190, 191]], ["eye", "eye", "X", [192, 195]], ["brow", "brow", "X", [196, 200]], ["&", "&", "PUNCT", [201, 202]], ["lash", "lash", "X", [203, 207]], ["tinting", "tinting", "X", [208, 215]], [".", ".", "PUNCT", [215, 216]]]], ["calgarske-listy_2003_unor_ocr.txt", "Certified Esthetician & Electrologist Cail Hana Tel: (403) 293-4639 Fax: (403) 293-7853 eVL\u2019VfOi) 3W747\u0160 W HANA GEBA Travel Consultant TRAVEL SPECIALISTS mluv\u00edm \u010desky a specializuji se na st\u0159edn\u00ed Evropu.", [["Certified", "Certified", "X", [0, 9]], ["Esthetician", "Esthetician", "X", [10, 21]], ["&", "&", "PUNCT", [22, 23]], ["Electrologist", "Electrologist", "PROPN", [24, 37]], ["Cail", "Cail", "X", [38, 42]], ["Hana", "Hana", "PROPN", [43, 47]], ["Tel", "telefon", "NOUN", [48, 51]], [":", ":", "PUNCT", [51, 52]], ["(", "(", "PUNCT", [53, 54]], ["403", "403", "NUM", [54, 57]], [")", ")", "PUNCT", [57, 58]], ["293", "293", "NUM", [59, 62]], ["-", "-", "PUNCT", [62, 63]], ["4639", "4639", "NUM", [63, 67]], ["Fax", "fax", "NOUN", [68, 71]], [":", ":", "PUNCT", [71, 72]], ["(", "(", "PUNCT", [73, 74]], ["403", "403", "NUM", [74, 77]], [")", ")", "PUNCT", [77, 78]], ["293", "293", "NUM", [79, 82]], ["-", "-", "PUNCT", [82, 83]], ["7853", "7853", "NUM", [83, 87]], ["eVL", "eVL", "NOUN", [88, 91]], ["\u2019", "'", "PUNCT", [91, 92]], ["VfOi", "VfOi", "NOUN", [92, 96]], [")", ")", "PUNCT", [96, 97]], ["3W747", "3W747", "NUM", [98, 103]], ["\u0160", "\u0160", "NOUN", [103, 104]], ["W", "W", "NOUN", [105, 106]], ["HANA", "Han", "PROPN", [107, 111]], ["GEBA", "Geba", "X", [112, 116]], ["Travel", "Travel", "X", [117, 123]], ["Consultant", "Consultant", "X", [124, 134]], ["TRAVEL", "Travel", "X", [135, 141]], ["SPECIALISTS", "Specialists", "X", [142, 153]], ["mluv\u00edm", "mluvit", "VERB", [154, 160]], ["\u010desky", "\u010desky", "ADV", [161, 166]], ["a", "a", "CCONJ", [167, 168]], ["specializuji", "specializovat", "VERB", [169, 181]], ["se", "se", "PRON", [182, 184]], ["na", "na", "ADP", [185, 187]], ["st\u0159edn\u00ed", "st\u0159edn\u00ed", "ADJ", [188, 195]], ["Evropu", "Evropa", "PROPN", [196, 202]], [".", ".", "PUNCT", [202, 203]]]], ["calgarske-listy_2003_unor_ocr.txt", "901 - 6th Avenue S.W. \u2014\u2014\u2014 Calgary, Alberta T2P 0V7 Bus: (403) 269-9322 Toll Free: 1-888-777-6617 Fax: (403) 269-9342 E-MAIL: agent@travelspc.com FAMILY DENTISTRY Tel. (403) 286-2222 Ve\u010dern\u00ed a sobotn\u00ed ordinace dle ujedn\u00e1n\u00ed Dr. Alojz \u0160koln\u00edk D.D.S. #208 Crowchild Square 5403 Crowchild Trail N.W. Calgary, AB, T3B4Z1 Freedom 55 Financial Richard Novak, B.Comm. Financial Security Advisor Suite 800, 322 - 11 Avenue South West Calgary, Alberta T2R 0C5 Office: 403-261-4690, ext. 255 Fax: 403-265-5984 Toll Free: 1-877-566-5433 richard.novak@freedom55finandal.com Client Service Centre: 1-877-566-5433 A division of London Life Insurance Company 17  W\u00e9 make the Steps To Home Ownership Easy Z Mortgage Services Z Home Services v' Legal Services Z Insurance Services INFORMACE PRO INZERCI", [["901", "901", "NUM", [0, 3]], ["-", "-", "PUNCT", [4, 5]], ["6", "6", "NUM", [6, 7]], ["t", "t", "NOUN", [7, 8]], ["h", "hodina", "NOUN", [8, 9]], ["Avenue", "Avenue", "X", [10, 16]], ["S", "S", "NOUN", [17, 18]], [".", ".", "PUNCT", [18, 19]], ["W", "W", "NOUN", [19, 20]], [".", ".", "PUNCT", [20, 21]], ["\u2014", "\u2014", "PUNCT", [22, 23]], ["\u2014", "\u2014", "PUNCT", [23, 24]], ["\u2014", "\u2014", "PUNCT", [24, 25]], ["Calgary", "Calgary", "PROPN", [26, 33]], [",", ",", "PUNCT", [33, 34]], ["Alberta", "Albert", "PROPN", [35, 42]], ["T", "T", "NOUN", [43, 44]], ["2P", "2P", "NOUN", [44, 46]], ["0V", "0V", "NUM", [47, 49]], ["7", "7", "NUM", [49, 50]], ["Bus", "bus", "NOUN", [51, 54]], [":", ":", "PUNCT", [54, 55]], ["(", "(", "PUNCT", [56, 57]], ["403", "403", "NUM", [57, 60]], [")", ")", "PUNCT", [60, 61]], ["269", "269", "NUM", [62, 65]], ["-", "-", "PUNCT", [65, 66]], ["9322", "9322", "NUM", [66, 70]], ["Toll", "Toll", "X", [71, 75]], ["Free", "Free", "X", [76, 80]], [":", ":", "PUNCT", [80, 81]], ["1", "1", "NUM", [82, 83]], ["-", "-", "PUNCT", [83, 84]], ["888", "888", "NUM", [84, 87]], ["-", "-", "PUNCT", [87, 88]], ["777", "777", "NUM", [88, 91]], ["-", "-", "PUNCT", [91, 92]], ["6617", "6617", "NUM", [92, 96]], ["Fax", "fax", "NOUN", [97, 100]], [":", ":", "PUNCT", [100, 101]], ["(", "(", "PUNCT", [102, 103]], ["403", "403", "NUM", [103, 106]], [")", ")", "PUNCT", [106, 107]], ["269", "269", "NUM", [108, 111]], ["-", "-", "PUNCT", [111, 112]], ["9342", "9342", "NUM", [112, 116]], ["E", "E", "NOUN", [117, 118]], ["-", "-", "PUNCT", [118, 119]], ["MAIL", "MAIL", "NOUN", [119, 123]], [":", ":", "PUNCT", [123, 124]], ["agent@travelspc.com", "agent@travelspc.com", "X", [125, 144]], ["FAMILY", "Family", "X", [145, 151]], ["DENTISTRY", "Dentistry", "X", [152, 161]], ["Tel", "telefon", "NOUN", [162, 165]], [".", ".", "PUNCT", [165, 166]], ["(", "(", "PUNCT", [167, 168]], ["403", "403", "NUM", [168, 171]], [")", ")", "PUNCT", [171, 172]], ["286", "286", "NUM", [173, 176]], ["-", "-", "PUNCT", [176, 177]], ["2222", "2222", "NUM", [177, 181]], ["Ve\u010dern\u00ed", "ve\u010dern\u00ed", "ADJ", [182, 189]], ["a", "a", "CCONJ", [190, 191]], ["sobotn\u00ed", "sobotn\u00ed", "ADJ", [192, 199]], ["ordinace", "ordinace", "NOUN", [200, 208]], ["dle", "dle", "ADP", [209, 212]], ["ujedn\u00e1n\u00ed", "ujedn\u00e1n\u00ed", "NOUN", [213, 221]], ["Dr", "Dr", "NOUN", [222, 224]], [".", ".", "PUNCT", [224, 225]], ["Alojz", "Alojz", "PROPN", [226, 231]], ["\u0160koln\u00edk", "\u0160koln\u00edk", "PROPN", [232, 239]], ["D", "D", "NOUN", [240, 241]], [".", ".", "PUNCT", [241, 242]], ["D", "D", "NOUN", [242, 243]], [".", ".", "PUNCT", [243, 244]], ["S", "S", "NOUN", [244, 245]], [".", ".", "PUNCT", [245, 246]], ["#208", "#208", "NUM", [247, 251]], ["Crowchild", "Crowchild", "X", [252, 261]], ["Square", "Square", "X", [262, 268]], ["5403", "5403", "NUM", [269, 273]], ["Crowchild", "Crowchild", "X", [274, 283]], ["Trail", "Trail", "X", [284, 289]], ["N", "N", "NOUN", [290, 291]], [".", ".", "PUNCT", [291, 292]], ["W", "W", "NOUN", [292, 293]], [".", ".", "PUNCT", [293, 294]], ["Calgary", "Calgary", "PROPN", [295, 302]], [",", ",", "PUNCT", [302, 303]], ["AB", "AB", "NOUN", [304, 306]], [",", ",", "PUNCT", [306, 307]], ["T", "T", "NOUN", [308, 309]], ["3", "3", "NUM", [309, 310]], ["B", "B", "NOUN", [310, 311]], ["4Z", "4Z", "NOUN", [311, 313]], ["1", "1", "NUM", [313, 314]], ["Freedom", "Freedom", "X", [315, 322]], ["55", "55", "NUM", [323, 325]], ["Financial", "Financial", "X", [326, 335]], ["Richard", "Richard", "PROPN", [336, 343]], ["Novak", "Novak", "PROPN", [344, 349]], [",", ",", "PUNCT", [349, 350]], ["B", "B", "NOUN", [351, 352]], [".", ".", "PUNCT", [352, 353]], ["Comm", "Comm", "PROPN", [353, 357]], [".", ".", "PUNCT", [357, 358]], ["Financial", "Financial", "X", [359, 368]], ["Security", "Security", "X", [369, 377]], ["Advisor", "Advisor", "X", [378, 385]], ["Suite", "Suite", "X", [386, 391]], ["800", "800", "NUM", [392, 395]], [",", ",", "PUNCT", [395, 396]], ["322", "322", "NUM", [397, 400]], ["-", "-", "PUNCT", [401, 402]], ["11", "11", "NUM", [403, 405]], ["Avenue", "Avenue", "X", [406, 412]], ["South", "South", "X", [413, 418]], ["West", "West", "X", [419, 423]], ["Calgary", "Calgary", "PROPN", [424, 431]], [",", ",", "PUNCT", [431, 432]], ["Alberta", "Albert", "PROPN", [433, 440]], ["T", "T", "NOUN", [441, 442]], ["2R", "2r", "PUNCT", [442, 444]], ["0C", "0C", "NUM", [445, 447]], ["5", "5", "NUM", [447, 448]], ["Office", "Office", "X", [449, 455]], [":", ":", "PUNCT", [455, 456]], ["403", "403", "NUM", [457, 460]], ["-", "-", "PUNCT", [460, 461]], ["261", "261", "NUM", [461, 464]], ["-", "-", "PUNCT", [464, 465]], ["4690", "4690", "NUM", [465, 469]], [",", ",", "PUNCT", [469, 470]], ["ext", "ext", "NOUN", [471, 474]], [".", ".", "PUNCT", [474, 475]], ["255", "255", "NUM", [476, 479]], ["Fax", "fax", "NOUN", [480, 483]], [":", ":", "PUNCT", [483, 484]], ["403", "403", "NUM", [485, 488]], ["-", "-", "PUNCT", [488, 489]], ["265", "265", "NUM", [489, 492]], ["-", "-", "PUNCT", [492, 493]], ["5984", "5984", "NUM", [493, 497]], ["Toll", "Toll", "X", [498, 502]], ["Free", "Free", "X", [503, 507]], [":", ":", "PUNCT", [507, 508]], ["1", "1", "NUM", [509, 510]], ["-", "-", "PUNCT", [510, 511]], ["877", "877", "NUM", [511, 514]], ["-", "-", "PUNCT", [514, 515]], ["566", "566", "NUM", [515, 518]], ["-", "-", "PUNCT", [518, 519]], ["5433", "5433", "NUM", [519, 523]], ["richard.novak@freedom55finandal.com", "richard.novak@freedom55finandal.com", "X", [524, 559]], ["Client", "Client", "X", [560, 566]], ["Service", "Service", "X", [567, 574]], ["Centre", "Centre", "X", [575, 581]], [":", ":", "PUNCT", [581, 582]], ["1", "1", "NUM", [583, 584]], ["-", "-", "PUNCT", [584, 585]], ["877", "877", "NUM", [585, 588]], ["-", "-", "PUNCT", [588, 589]], ["566", "566", "NUM", [589, 592]], ["-", "-", "PUNCT", [592, 593]], ["5433", "5433", "NUM", [593, 597]], ["A", "A", "X", [598, 599]], ["division", "division", "X", [600, 608]], ["of", "of", "X", [609, 611]], ["London", "London", "X", [612, 618]], ["Life", "Life", "X", [619, 623]], ["Insurance", "Insurance", "X", [624, 633]], ["Company", "Company", "X", [634, 641]], ["17", "17", "NUM", [642, 644]], ["W\u00e9", "W\u00e9", "X", [646, 648]], ["make", "make", "X", [649, 653]], ["the", "the", "X", [654, 657]], ["Steps", "Steps", "X", [658, 663]], ["To", "To", "X", [664, 666]], ["Home", "Home", "X", [667, 671]], ["Ownership", "Ownership", "X", [672, 681]], ["Easy", "Easy", "X", [682, 686]], ["Z", "z", "ADP", [687, 688]], ["Mortgage", "Mortgage", "X", [689, 697]], ["Services", "Services", "X", [698, 706]], ["Z", "z", "ADP", [707, 708]], ["Home", "Home", "X", [709, 713]], ["Services", "Services", "X", [714, 722]], ["v", "v", "ADP", [723, 724]], ["'", "'", "PUNCT", [724, 725]], ["Legal", "Legal", "X", [726, 731]], ["Services", "Services", "X", [732, 740]], ["Z", "z", "ADP", [741, 742]], ["Insurance", "Insurance", "X", [743, 752]], ["Services", "Services", "X", [753, 761]], ["INFORMACE", "informace", "NOUN", [762, 771]], ["PRO", "pro", "ADP", [772, 775]], ["INZERCI", "inzerec", "NOUN", [776, 783]]]], ["calgarske-listy_2003_unor_ocr.txt", "Z\u00e1kladni poplatek za otisknuti inzer\u00e1tu na dobu jednoho roku ve velikosti : business card .. $30 1/4 str\u00e1nky .. $60", [["Z\u00e1kladni", "Z\u00e1kladni", "PROPN", [0, 8]], ["poplatek", "poplatek", "NOUN", [9, 17]], ["za", "za", "ADP", [18, 20]], ["otisknuti", "otisknut\u00fd", "ADJ", [21, 30]], ["inzer\u00e1tu", "inzer\u00e1t", "NOUN", [31, 39]], ["na", "na", "ADP", [40, 42]], ["dobu", "doba", "NOUN", [43, 47]], ["jednoho", "jeden", "NUM", [48, 55]], ["roku", "rok", "NOUN", [56, 60]], ["ve", "v", "ADP", [61, 63]], ["velikosti", "velikost", "NOUN", [64, 73]], [":", ":", "PUNCT", [74, 75]], ["business", "business", "X", [76, 84]], ["card", "card", "X", [85, 89]], [".", ".", "PUNCT", [90, 91]], [".", ".", "PUNCT", [91, 92]], ["$", "$", "NOUN", [93, 94]], ["30", "30", "NUM", [94, 96]], ["1", "1", "NUM", [97, 98]], ["/", "/", "PUNCT", [98, 99]], ["4", "4", "NUM", [99, 100]], ["str\u00e1nky", "str\u00e1nka", "NOUN", [101, 108]], [".", ".", "PUNCT", [109, 110]], [".", ".", "PUNCT", [110, 111]], ["$", "$", "NOUN", [112, 113]], ["60", "60", "NUM", [113, 115]]]], ["calgarske-listy_2003_unor_ocr.txt", "P\u0159ipom\u00edn\u00e1me, \u017ee poplatek je t\u0159eba bez vyzv\u00e1ni do jednoho roku obnovit \u0161ekem na adresu: Czech and Slovak Assoc. of Canada, Calgary Branch P.O.Box 355, Calgary, T2P 2H9 WWW. MTRUST.", [["P\u0159ipom\u00edn\u00e1me", "p\u0159ipom\u00ednat", "VERB", [0, 11]], [",", ",", "PUNCT", [11, 12]], ["\u017ee", "\u017ee", "SCONJ", [13, 15]], ["poplatek", "poplatek", "NOUN", [16, 24]], ["je", "b\u00fdt", "AUX", [25, 27]], ["t\u0159eba", "t\u0159eba", "ADV", [28, 33]], ["bez", "bez", "ADP", [34, 37]], ["vyzv\u00e1ni", "vyzvan\u00fd", "ADJ", [38, 45]], ["do", "do", "ADP", [46, 48]], ["jednoho", "jeden", "NUM", [49, 56]], ["roku", "rok", "NOUN", [57, 61]], ["obnovit", "obnovit", "VERB", [62, 69]], ["\u0161ekem", "\u0161ek", "NOUN", [70, 75]], ["na", "na", "ADP", [76, 78]], ["adresu", "adresa", "NOUN", [79, 85]], [":", ":", "PUNCT", [85, 86]], ["Czech", "Czech", "X", [87, 92]], ["and", "and", "X", [93, 96]], ["Slovak", "Slovak", "X", [97, 103]], ["Assoc", "Assoc", "X", [104, 109]], [".", ".", "PUNCT", [109, 110]], ["of", "of", "X", [111, 113]], ["Canada", "Canada", "X", [114, 120]], [",", ",", "PUNCT", [120, 121]], ["Calgary", "Calgary", "PROPN", [122, 129]], ["Branch", "Branch", "X", [130, 136]], ["P", "P", "NOUN", [137, 138]], [".", ".", "PUNCT", [138, 139]], ["O", "O", "NOUN", [139, 140]], [".", ".", "PUNCT", [140, 141]], ["Box", "box", "NOUN", [141, 144]], ["355", "355", "NUM", [145, 148]], [",", ",", "PUNCT", [148, 149]], ["Calgary", "Calgary", "PROPN", [150, 157]], [",", ",", "PUNCT", [157, 158]], ["T", "T", "NOUN", [159, 160]], ["2P", "2P", "NOUN", [160, 162]], ["2H", "2egawaat", "NOUN", [163, 165]], ["9", "9", "NUM", [165, 166]], ["WWW", "WWW", "NOUN", [167, 170]], [".", ".", "PUNCT", [170, 171]], ["MTRUST", "Mtrust", "PROPN", [172, 178]], [".", ".", "PUNCT", [178, 179]]]], ["calgarske-listy_2003_unor_ocr.txt", "CA For more information contact David R. Kraus Service in English & Czech Ph. (403)703-8222 E-mail dkraus@mtrust.ca INGRID JINDRA RUMSTAY Anglicko-\u010desk\u00e9 p\u0159eklady pro Va\u0161i pot\u0159ebu p\u0159iprav\u00ed u\u010ditelka \u010de\u0161tiny a angli\u010dtiny Telefon : (403) 541 0654 *No cost for standard mortgage services /", [["CA", "Ca", "X", [0, 2]], ["For", "For", "X", [3, 6]], ["more", "more", "X", [7, 11]], ["information", "information", "X", [12, 23]], ["contact", "contact", "X", [24, 31]], ["David", "David", "PROPN", [32, 37]], ["R", "R", "NOUN", [38, 39]], [".", ".", "PUNCT", [39, 40]], ["Kraus", "Kraus", "PROPN", [41, 46]], ["Service", "Service", "X", [47, 54]], ["in", "in", "X", [55, 57]], ["English", "English", "X", [58, 65]], ["&", "&", "PUNCT", [66, 67]], ["Czech", "Czech", "X", [68, 73]], ["Ph", "Ph", "NOUN", [74, 76]], [".", ".", "PUNCT", [76, 77]], ["(", "(", "PUNCT", [78, 79]], ["403", "403", "NUM", [79, 82]], [")", ")", "PUNCT", [82, 83]], ["703", "703", "NUM", [83, 86]], ["-", "-", "PUNCT", [86, 87]], ["8222", "8222", "NUM", [87, 91]], ["E", "E", "NOUN", [92, 93]], ["-", "-", "PUNCT", [93, 94]], ["mail", "mail", "NOUN", [94, 98]], ["dkraus@mtrust.ca", "dkraus@mtrust.", "NOUN", [99, 115]], ["INGRID", "Ingrid", "PROPN", [116, 122]], ["JINDRA", "Jindra", "PROPN", [123, 129]], ["RUMSTAY", "Rumstay", "X", [130, 137]], ["Anglicko", "anglicko", "ADJ", [138, 146]], ["-", "-", "PUNCT", [146, 147]], ["\u010desk\u00e9", "\u010desk\u00fd", "ADJ", [147, 152]], ["p\u0159eklady", "p\u0159eklad", "NOUN", [153, 161]], ["pro", "pro", "ADP", [162, 165]], ["Va\u0161i", "v\u00e1\u0161", "DET", [166, 170]], ["pot\u0159ebu", "pot\u0159eba", "NOUN", [171, 178]], ["p\u0159iprav\u00ed", "p\u0159ipravit", "VERB", [179, 187]], ["u\u010ditelka", "u\u010ditelka", "NOUN", [188, 196]], ["\u010de\u0161tiny", "\u010de\u0161tina", "NOUN", [197, 204]], ["a", "a", "CCONJ", [205, 206]], ["angli\u010dtiny", "angli\u010dtina", "NOUN", [207, 217]], ["Telefon", "telefon", "NOUN", [218, 225]], [":", ":", "PUNCT", [226, 227]], ["(", "(", "PUNCT", [228, 229]], ["403", "403", "NUM", [229, 232]], [")", ")", "PUNCT", [232, 233]], ["541", "541", "NUM", [234, 237]], ["0654", "0654", "NUM", [238, 242]], ["*", "*", "PUNCT", [243, 244]], ["No", "No", "X", [244, 246]], ["cost", "cost", "X", [247, 251]], ["for", "for", "X", [252, 255]], ["standard", "standard", "X", [256, 264]], ["mortgage", "mortgage", "X", [265, 273]], ["services", "services", "X", [274, 282]], ["/", "/", "PUNCT", [283, 284]]]], ["calgarske-listy_2003_unor_ocr.txt", "Fees may be applicable to the mortgage agent and/or lender for hard to place mortgages.", [["Fees", "Fees", "X", [0, 4]], ["may", "may", "X", [5, 8]], ["be", "be", "X", [9, 11]], ["applicable", "applicable", "X", [12, 22]], ["to", "to", "X", [23, 25]], ["the", "the", "X", [26, 29]], ["mortgage", "mortgage", "X", [30, 38]], ["agent", "agent", "NOUN", [39, 44]], ["and", "and", "X", [45, 48]], ["/", "/", "PUNCT", [48, 49]], ["or", "or", "X", [49, 51]], ["lender", "lender", "X", [52, 58]], ["for", "for", "X", [59, 62]], ["hard", "hard", "X", [63, 67]], ["to", "to", "X", [68, 70]], ["place", "place", "X", [71, 76]], ["mortgages", "mortgages", "X", [77, 86]], [".", ".", "PUNCT", [86, 87]]]], ["calgarske-listy_2003_unor_ocr.txt", "JAN \u010cERM\u00c1K Transmission Repair All Work Guaranteed Low Hourly Rates Jan s Transmission pree Estimates Vo n d y Re n o v a t io n s Carpenter & General Contractor Kitchen cabinets \u2022 Custom renovations Bathrooms \u2022 Basement development MARCEL VONDRASEK Ph: (403) 256-0330 Cell: (403) 680-4066 3640 Burnsland Road S.E. Calgary, Alberta T2G 3Z2 Bus: (403) 243-8179 Res: 281-4762 P\u0158IHL\u00c1\u0160KA ZA \u010cLENA SDRU\u017dEN\u00cd - P\u0158EDPLATN\u00c9 CALGARSK\u00ddCHLIST\u016e \u25a1", [["JAN", "Jan", "PROPN", [0, 3]], ["\u010cERM\u00c1K", "\u010cerm\u00e1k", "PROPN", [4, 10]], ["Transmission", "Transmission", "X", [11, 23]], ["Repair", "Repair", "X", [24, 30]], ["All", "All", "X", [31, 34]], ["Work", "Work", "X", [35, 39]], ["Guaranteed", "Guaranteed", "X", [40, 50]], ["Low", "Low", "X", [51, 54]], ["Hourly", "Hourly", "X", [55, 61]], ["Rates", "Rates", "X", [62, 67]], ["Jan", "Jan", "PROPN", [68, 71]], ["s", "s", "X", [72, 73]], ["Transmission", "Transmission", "X", [74, 86]], ["pree", "pree", "X", [87, 91]], ["Estimates", "Estimates", "X", [92, 101]], ["Vo", "Vo", "X", [102, 104]], ["n", "n", "NOUN", [105, 106]], ["d", "d", "NOUN", [107, 108]], ["y", "y", "NOUN", [109, 110]], ["Re", "Re", "X", [111, 113]], ["n", "n", "NOUN", [114, 115]], ["o", "o", "ADP", [116, 117]], ["v", "v", "NOUN", [118, 119]], ["a", "a", "CCONJ", [120, 121]], ["t", "t", "NOUN", [122, 123]], ["io", "io", "X", [124, 126]], ["n", "n", "NOUN", [127, 128]], ["s", "s", "ADP", [129, 130]], ["Carpenter", "Carpenter", "X", [131, 140]], ["&", "&", "PUNCT", [141, 142]], ["General", "General", "X", [143, 150]], ["Contractor", "Contractor", "X", [151, 161]], ["Kitchen", "Kitchen", "X", [162, 169]], ["cabinets", "cabinets", "X", [170, 178]], ["\u2022", "\u2022", "PUNCT", [179, 180]], ["Custom", "Custom", "X", [181, 187]], ["renovations", "renovations", "X", [188, 199]], ["Bathrooms", "Bathrooms", "X", [200, 209]], ["\u2022", "\u2022", "PUNCT", [210, 211]], ["Basement", "Basement", "X", [212, 220]], ["development", "development", "X", [221, 232]], ["MARCEL", "Marcel", "X", [233, 239]], ["VONDRASEK", "Vondrasek", "PROPN", [240, 249]], ["Ph", "Ph", "PROPN", [250, 252]], [":", ":", "PUNCT", [252, 253]], ["(", "(", "PUNCT", [254, 255]], ["403", "403", "NUM", [255, 258]], [")", ")", "PUNCT", [258, 259]], ["256", "256", "NUM", [260, 263]], ["-", "-", "PUNCT", [263, 264]], ["0330", "0330", "NUM", [264, 268]], ["Cell", "Cell", "PROPN", [269, 273]], [":", ":", "PUNCT", [273, 274]], ["(", "(", "PUNCT", [275, 276]], ["403", "403", "NUM", [276, 279]], [")", ")", "PUNCT", [279, 280]], ["680", "680", "NUM", [281, 284]], ["-", "-", "PUNCT", [284, 285]], ["4066", "4066", "NUM", [285, 289]], ["3640", "3640", "NUM", [290, 294]], ["Burnsland", "Burnsland", "PROPN", [295, 304]], ["Road", "Road", "X", [305, 309]], ["S", "S", "NOUN", [310, 311]], [".", ".", "PUNCT", [311, 312]], ["E", "E", "NOUN", [312, 313]], [".", ".", "PUNCT", [313, 314]], ["Calgary", "Calgary", "PROPN", [315, 322]], [",", ",", "PUNCT", [322, 323]], ["Alberta", "Albert", "PROPN", [324, 331]], ["T", "T", "NOUN", [332, 333]], ["2G", "2G", "NOUN", [333, 335]], ["3Z", "3Z", "NOUN", [336, 338]], ["2", "2", "NUM", [338, 339]], ["Bus", "bus", "NOUN", [340, 343]], [":", ":", "PUNCT", [343, 344]], ["(", "(", "PUNCT", [345, 346]], ["403", "403", "NUM", [346, 349]], [")", ")", "PUNCT", [349, 350]], ["243", "243", "NUM", [351, 354]], ["-", "-", "PUNCT", [354, 355]], ["8179", "8179", "NUM", [355, 359]], ["Res", "res", "NOUN", [360, 363]], [":", ":", "PUNCT", [363, 364]], ["281", "281", "NUM", [365, 368]], ["-", "-", "PUNCT", [368, 369]], ["4762", "4762", "NUM", [369, 373]], ["P\u0158IHL\u00c1\u0160KA", "p\u0159ihl\u00e1\u0161ka", "NOUN", [374, 383]], ["ZA", "za", "ADP", [384, 386]], ["\u010cLENA", "\u010cLENA", "NOUN", [387, 392]], ["SDRU\u017dEN\u00cd", "sdru\u017een\u00ed", "NOUN", [393, 401]], ["-", "-", "PUNCT", [402, 403]], ["P\u0158EDPLATN\u00c9", "p\u0159edplatn\u00fd", "ADJ", [404, 414]], ["CALGARSK\u00ddCHLIST\u016e", "calaarsk\u00fdchista", "NOUN", [415, 431]], ["\u25a1", "\u25a1", "NOUN", [432, 433]]]], ["calgarske-listy_2003_unor_ocr.txt", "P\u0159ihla\u0161uji se za \u010dlena \u010ds. sdru\u017een\u00ed v Kanad\u011b, odbo\u010dka v Calgary, a chci p\u0159isp\u011bt ke kulturn\u00edmu a politick\u00e9mu d\u011bn\u00ed jak v Kanad\u011b, tak i v b\u00fdval\u00e9 vlasti.", [["P\u0159ihla\u0161uji", "p\u0159ihla\u0161ovat", "VERB", [0, 10]], ["se", "se", "PRON", [11, 13]], ["za", "za", "ADP", [14, 16]], ["\u010dlena", "\u010dlen", "NOUN", [17, 22]], ["\u010ds", "\u010deskoslovensk\u00fd", "ADJ", [23, 25]], [".", ".", "PUNCT", [25, 26]], ["sdru\u017een\u00ed", "sdru\u017een\u00ed", "NOUN", [27, 35]], ["v", "v", "ADP", [36, 37]], ["Kanad\u011b", "Kanada", "PROPN", [38, 44]], [",", ",", "PUNCT", [44, 45]], ["odbo\u010dka", "odbo\u010dka", "NOUN", [46, 53]], ["v", "v", "ADP", [54, 55]], ["Calgary", "Calgary", "PROPN", [56, 63]], [",", ",", "PUNCT", [63, 64]], ["a", "a", "CCONJ", [65, 66]], ["chci", "cht\u00edt", "VERB", [67, 71]], ["p\u0159isp\u011bt", "p\u0159isp\u011bt", "VERB", [72, 79]], ["ke", "k", "ADP", [80, 82]], ["kulturn\u00edmu", "kulturn\u00ed", "ADJ", [83, 93]], ["a", "a", "CCONJ", [94, 95]], ["politick\u00e9mu", "politick\u00fd", "ADJ", [96, 107]], ["d\u011bn\u00ed", "d\u011bn\u00ed", "NOUN", [108, 112]], ["jak", "jak", "ADV", [113, 116]], ["v", "v", "ADP", [117, 118]], ["Kanad\u011b", "Kanada", "PROPN", [119, 125]], [",", ",", "PUNCT", [125, 126]], ["tak", "tak", "ADV", [127, 130]], ["i", "i", "CCONJ", [131, 132]], ["v", "v", "ADP", [133, 134]], ["b\u00fdval\u00e9", "b\u00fdval\u00fd", "ADJ", [135, 141]], ["vlasti", "vlast", "NOUN", [142, 148]], [".", ".", "PUNCT", [148, 149]]]], ["calgarske-listy_2003_unor_ocr.txt", "P\u0159ikl\u00e1d\u00e1m \u0161ek na $20.00 za rodinu nebo $15.00 za jednotlivce.", [["P\u0159ikl\u00e1d\u00e1m", "p\u0159ikl\u00e1dat", "VERB", [0, 9]], ["\u0161ek", "\u0161ek", "NOUN", [10, 13]], ["na", "na", "ADP", [14, 16]], ["$20.00", "$20.00", "NUM", [17, 23]], ["za", "za", "ADP", [24, 26]], ["rodinu", "rodina", "NOUN", [27, 33]], ["nebo", "nebo", "CCONJ", [34, 38]], ["$15.00", "$15.00", "NUM", [39, 45]], ["za", "za", "ADP", [46, 48]], ["jednotlivce", "jednotlivec", "NOUN", [49, 60]], [".", ".", "PUNCT", [60, 61]]]], ["calgarske-listy_2003_unor_ocr.txt", "\u25a1 Chci b\u00fdt pouze informov\u00e1n o v\u0161ech akc\u00edch po\u0159\u00e1dan\u00fdch v Calgary i ve vlasti a p\u0159edpl\u00e1c\u00edm si Calgarsk\u00e9 Listy za upravenou cenu $ 10.00.", [["\u25a1", "\u25a1", "NOUN", [0, 1]], ["Chci", "cht\u00edt", "VERB", [2, 6]], ["b\u00fdt", "b\u00fdt", "AUX", [7, 10]], ["pouze", "pouze", "ADV", [11, 16]], ["informov\u00e1n", "informovan\u00fd", "ADJ", [17, 27]], ["o", "o", "ADP", [28, 29]], ["v\u0161ech", "v\u0161echen", "DET", [30, 35]], ["akc\u00edch", "akce", "NOUN", [36, 42]], ["po\u0159\u00e1dan\u00fdch", "po\u0159\u00e1dan\u00fd", "ADJ", [43, 53]], ["v", "v", "ADP", [54, 55]], ["Calgary", "Calgary", "PROPN", [56, 63]], ["i", "i", "CCONJ", [64, 65]], ["ve", "v", "ADP", [66, 68]], ["vlasti", "vlast", "NOUN", [69, 75]], ["a", "a", "CCONJ", [76, 77]], ["p\u0159edpl\u00e1c\u00edm", "p\u0159edpl\u00e1c\u00ed", "ADJ", [78, 88]], ["si", "se", "PRON", [89, 91]], ["Calgarsk\u00e9", "calgarsk\u00fd", "ADJ", [92, 101]], ["Listy", "list", "NOUN", [102, 107]], ["za", "za", "ADP", [108, 110]], ["upravenou", "upraven\u00fd", "ADJ", [111, 120]], ["cenu", "cena", "NOUN", [121, 125]], ["$", "$", "NOUN", [126, 127]], ["10.00", "10.00", "NUM", [128, 133]], [".", ".", "PUNCT", [133, 134]]]], ["calgarske-listy_2003_unor_ocr.txt", "Seky za\u0161lete pros\u00edm na adresu: Czech and Slovak Assoc, of Calgary, P.O.Box 355, Calgary, T2P-2H9 CALGARSK\u00c9 LISTY vyd\u00e1v\u00e1 zhruba 4x do roka Czech and Slovak Association of Canada, Calgary Branch, P. O.Box 355, Calgary, T2P-2H9.", [["Seky", "sek", "NOUN", [0, 4]], ["za\u0161lete", "zaslat", "VERB", [5, 12]], ["pros\u00edm", "prosit", "VERB", [13, 19]], ["na", "na", "ADP", [20, 22]], ["adresu", "adresa", "NOUN", [23, 29]], [":", ":", "PUNCT", [29, 30]], ["Czech", "Czech", "X", [31, 36]], ["and", "and", "X", [37, 40]], ["Slovak", "Slovak", "X", [41, 47]], ["Assoc", "Assoc", "X", [48, 53]], [",", ",", "PUNCT", [53, 54]], ["of", "of", "X", [55, 57]], ["Calgary", "Calgary", "PROPN", [58, 65]], [",", ",", "PUNCT", [65, 66]], ["P", "P", "NOUN", [67, 68]], [".", ".", "PUNCT", [68, 69]], ["O", "O", "NOUN", [69, 70]], [".", ".", "PUNCT", [70, 71]], ["Box", "box", "NOUN", [71, 74]], ["355", "355", "NUM", [75, 78]], [",", ",", "PUNCT", [78, 79]], ["Calgary", "Calgary", "PROPN", [80, 87]], [",", ",", "PUNCT", [87, 88]], ["T", "T", "NOUN", [89, 90]], ["2P", "2P", "NOUN", [90, 92]], ["-", "-", "PUNCT", [92, 93]], ["2H", "2egawaat", "NOUN", [93, 95]], ["9", "9", "NUM", [95, 96]], ["CALGARSK\u00c9", "calgarsk\u00fd", "ADJ", [97, 106]], ["LISTY", "list", "NOUN", [107, 112]], ["vyd\u00e1v\u00e1", "vyd\u00e1vat", "VERB", [113, 119]], ["zhruba", "zhruba", "ADV", [120, 126]], ["4", "4", "NUM", [127, 128]], ["x", "x", "SYM", [128, 129]], ["do", "do", "ADP", [130, 132]], ["roka", "rok", "NOUN", [133, 137]], ["Czech", "Czech", "X", [138, 143]], ["and", "and", "X", [144, 147]], ["Slovak", "Slovak", "X", [148, 154]], ["Association", "Association", "X", [155, 166]], ["of", "of", "X", [167, 169]], ["Canada", "Canada", "X", [170, 176]], [",", ",", "PUNCT", [176, 177]], ["Calgary", "Calgary", "PROPN", [178, 185]], ["Branch", "Branch", "X", [186, 192]], [",", ",", "PUNCT", [192, 193]], ["P", "P", "NOUN", [194, 195]], [".", ".", "PUNCT", [195, 196]], ["O", "O", "NOUN", [197, 198]], [".", ".", "PUNCT", [198, 199]], ["Box", "box", "NOUN", [199, 202]], ["355", "355", "NUM", [203, 206]], [",", ",", "PUNCT", [206, 207]], ["Calgary", "Calgary", "PROPN", [208, 215]], [",", ",", "PUNCT", [215, 216]], ["T", "T", "NOUN", [217, 218]], ["2P", "2P", "NOUN", [218, 220]], ["-", "-", "PUNCT", [220, 221]], ["2H", "2egawaat", "NOUN", [221, 223]], ["9", "9", "NUM", [223, 224]], [".", ".", "PUNCT", [224, 225]]]], ["calgarske-listy_2003_unor_ocr.txt", "Redakce si vyhrazuje pr\u00e1vo na zkr\u00e1cen\u00ed a \u00fapravu p\u0159\u00edsp\u011bvk\u016f.", [["Redakce", "redakce", "NOUN", [0, 7]], ["si", "se", "PRON", [8, 10]], ["vyhrazuje", "vyhrazovat", "VERB", [11, 20]], ["pr\u00e1vo", "pr\u00e1vo", "NOUN", [21, 26]], ["na", "na", "ADP", [27, 29]], ["zkr\u00e1cen\u00ed", "zkr\u00e1cen\u00ed", "NOUN", [30, 38]], ["a", "a", "CCONJ", [39, 40]], ["\u00fapravu", "\u00faprava", "NOUN", [41, 47]], ["p\u0159\u00edsp\u011bvk\u016f", "p\u0159\u00edsp\u011bvek", "NOUN", [48, 57]], [".", ".", "PUNCT", [57, 58]]]], ["calgarske-listy_2003_unor_ocr.txt", "Podepsan\u00e9 \u010dl\u00e1nky nemus\u00ed vyjad\u0159ovat n\u00e1zory redakce a vydavatele.", [["Podepsan\u00e9", "podepsan\u00fd", "ADJ", [0, 9]], ["\u010dl\u00e1nky", "\u010dl\u00e1nek", "NOUN", [10, 16]], ["nemus\u00ed", "muset", "VERB", [17, 23]], ["vyjad\u0159ovat", "vyjad\u0159ovat", "VERB", [24, 34]], ["n\u00e1zory", "n\u00e1zor", "NOUN", [35, 41]], ["redakce", "redakce", "NOUN", [42, 49]], ["a", "a", "CCONJ", [50, 51]], ["vydavatele", "vydavatel", "NOUN", [52, 62]], [".", ".", "PUNCT", [62, 63]]]], ["calgarske-listy_2003_unor_ocr.txt", "18", [["18", "18", "NUM", [0, 2]]]]]