{ "corpus_hits": { "KLK_FI_1830": 87, "KLK_FI_1831": 78, "KLK_FI_1832": 21, "KLK_FI_1833": 105, "KLK_FI_1834": 60, "KLK_FI_1835": 84, "KLK_FI_1836": 230, "KLK_FI_1837": 116, "KLK_FI_1838": 13, "KLK_FI_1839": 42 }, "corpus_order": [ "KLK_FI_1839", "KLK_FI_1838", "KLK_FI_1837", "KLK_FI_1836", "KLK_FI_1835", "KLK_FI_1834", "KLK_FI_1833", "KLK_FI_1832", "KLK_FI_1831", "KLK_FI_1830" ], "hits": 836, "kwic": [ { "corpus": "KLK_FI_1839", "match": { "end": 7, "position": 11983, "start": 6 }, "structs": { "paragraph_id": "1", "sentence_id": "801", "sentence_local_id": "2", "sentence_parse_state": "parsed", "text_binding_id": "501266", "text_datefrom": "18390303", "text_dateto": "18390331", "text_elec_date": "2008-05-09", "text_img_url": "#DIRECTORY#fk01442_1839-03_3#SEPARATOR#00018.#EXTENSION#", "text_issue_date": "03.1839", "text_issue_no": "3", "text_issue_title": "MEHIL\u00c4INEN.", "text_label": "MEHIL\u00c4INEN. no. 3 03.1839", "text_language": "fi", "text_page_no": "18", "text_publ_id": "fk01442", "text_publ_title": "Mehil\u00e4inen", "text_publ_type": "aikakausi", "text_sentcount": "12", "text_tokencount": "105" }, "tokens": [ { "dephead": "2", "deprel": "num", "lemma": "ensimm\u00e4inen", "lemmacomp": "ensimm\u00e4inen", "lex": "|ensimm\u00e4inen..rg.1|", "msd": "SUBCAT_Ord|NUM_Sg|CASE_Nom|CASECHANGE_Up", "ocr": "0.93", "pos": "Num", "ref": "1", "structs": { "open": [ "sentence" ] }, "word": "Ensimm\u00e4inen" }, { "dephead": "3", "deprel": "dobj", "lemma": "kristinusko", "lemmacomp": "kristinusko", "lex": "|kristinusko..nn.1|", "msd": "NUM_Sg|CASE_Nom|CASECHANGE_Up", "ocr": "0.93", "pos": "N", "ref": "2", "word": "Kristinusko" }, { "dephead": "0", "deprel": "ROOT", "lemma": "lukea", "lemmacomp": "lukea", "lex": "|lukea..vb.1|", "msd": "PRS_Pe4|VOICE_Pass|TENSE_Prs|MOOD_Ind", "ocr": "0.96", "pos": "V", "ref": "3", "word": "luetaan" }, { "dephead": "3", "deprel": "partmod", "lemma": "tulla", "lemmacomp": "tulla", "lex": "|tulla..vb.1|", "msd": "NUM_Sg|CASE_Tra|VOICE_Act|PCP_PrfPrc|CMP_Pos", "ocr": "0.91", "pos": "V", "ref": "4", "word": "tulleeksi" }, { "dephead": "6", "deprel": "num", "lemma": "w.", "lemmacomp": "w.", "lex": "|w...rg.1|", "msd": "OTHER_UNK", "ocr": "0.96", "pos": "Num", "ref": "5", "word": "w." }, { "dephead": "12", "deprel": "name", "lemma": "11Z6", "lemmacomp": "11Z6", "lex": "|11Z6..xx.1|", "msd": "OTHER_UNK", "ocr": "0.86", "pos": "Symb", "ref": "6", "word": "11Z6" }, { "dephead": "4", "deprel": "nommod", "lemma": "Suomi", "lemmacomp": "Suomi", "lex": "|Suomi..nn.1|", "msd": "SUBCAT_Prop|NUM_Sg|CASE_Ill|CASECHANGE_Up", "ocr": "0.96", "pos": "N", "ref": "7", "word": "Suomeen" }, { "dephead": "4", "deprel": "cc", "lemma": "ja", "lemmacomp": "ja", "lex": "|ja..kn.1|", "msd": "SUBCAT_CC", "ocr": "0.91", "pos": "C", "ref": "8", "word": "ja" }, { "dephead": "20", "deprel": "advmod", "lemma": "nyt", "lemmacomp": "nyt", "lex": "|nyt..ab.1|", "msd": "_", "ocr": "0.91", "pos": "Adv", "ref": "9", "word": "nyt" }, { "dephead": "20", "deprel": "aux", "lemma": "olla", "lemmacomp": "olla", "lex": "|olla..vb.1|", "msd": "PRS_Sg3|VOICE_Act|TENSE_Prs|MOOD_Ind", "ocr": "0.94", "pos": "V", "ref": "10", "word": "on" }, { "dephead": "20", "deprel": "advmod", "lemma": "wuosi", "lemmacomp": "wuosi", "lex": "|wuosi..ab.1|", "msd": "OTHER_UNK", "ocr": "0.98", "pos": "Adv", "ref": "11", "word": "wuosi" }, { "dephead": "20", "deprel": "nommod", "lemma": "1839", "lemmacomp": "1839", "lex": "|1839..rg.1|", "msd": "_", "ocr": "0.95", "pos": "Num", "ref": "12", "word": "1839" }, { "dephead": "12", "deprel": "punct", "lemma": ";", "lemmacomp": ";", "lex": "|;..xx.1|", "msd": "_", "ocr": "0.95", "pos": "Punct", "ref": "13", "word": ";" }, { "dephead": "15", "deprel": "det", "lemma": "monta", "lemmacomp": "monta", "lex": "|monta..pn.1|", "msd": "NUM_Sg|CASE_Nom|CLIT_Qst", "ocr": "0.93", "pos": "Pron", "ref": "14", "word": "montako" }, { "dephead": "20", "deprel": "nsubj", "lemma": "wuotta", "lemmacomp": "wuotta", "lex": "|wuotta..nn.1|", "msd": "NUM_Sg|CASE_Par|OTHER_UNK", "ocr": "0.96", "pos": "N", "ref": "15", "word": "wuotta" }, { "dephead": "20", "deprel": "aux", "lemma": "olla", "lemmacomp": "olla", "lex": "|olla..vb.1|", "msd": "PRS_Sg3|VOICE_Act|TENSE_Prs|MOOD_Ind", "ocr": "0.98", "pos": "V", "ref": "16", "word": "on" }, { "dephead": "20", "deprel": "advmod", "lemma": "siis", "lemmacomp": "siis", "lex": "|siis..ab.1|", "msd": "_", "ocr": "0.93", "pos": "Adv", "ref": "17", "word": "siis" }, { "dephead": "19", "deprel": "det", "lemma": "se", "lemmacomp": "se", "lex": "|se..pn.1|", "msd": "SUBCAT_Dem|NUM_Sg|CASE_Ela", "ocr": "0.95", "pos": "Pron", "ref": "18", "word": "siit\u00e4" }, { "dephead": "20", "deprel": "nommod", "lemma": "aika", "lemmacomp": "aika", "lex": "|aika..nn.1|", "msd": "NUM_Sg|CASE_Ela", "ocr": "0.94", "pos": "N", "ref": "19", "word": "ajasta" }, { "dephead": "4", "deprel": "conj", "lemma": "kulua", "lemmacomp": "kulua", "lex": "|kulua..vb.1|", "msd": "NUM_Sg|CASE_Nom|VOICE_Act|PCP_PrfPrc|CMP_Pos", "ocr": "0.96", "pos": "V", "ref": "20", "word": "kulunut" }, { "dephead": "3", "deprel": "punct", "lemma": "?", "lemmacomp": "?", "lex": "|?..xx.1|", "msd": "_", "ocr": "0.96", "pos": "Punct", "ref": "21", "structs": { "close": [ "sentence" ] }, "word": "?" } ] }, { "corpus": "KLK_FI_1839", "match": { "end": 1, "position": 548, "start": 0 }, "structs": { "paragraph_id": "6", "sentence_id": "43", "sentence_local_id": "8", "sentence_parse_state": "parsed", "text_binding_id": "501536", "text_datefrom": "18390101", "text_dateto": "18390131", "text_elec_date": "2008-05-09", "text_img_url": "#DIRECTORY#fk01442_1839-01_1#SEPARATOR#00004.#EXTENSION#", "text_issue_date": "01.1839", "text_issue_no": "1", "text_issue_title": "MEHIL\u00c4INEN.", "text_label": "MEHIL\u00c4INEN. no. 1 01.1839", "text_language": "fi", "text_page_no": "4", "text_publ_id": "fk01442", "text_publ_title": "Mehil\u00e4inen", "text_publ_type": "aikakausi", "text_sentcount": "10", "text_tokencount": "142" }, "tokens": [ { "dephead": "2", "deprel": "poss", "lemma": "Suomi", "lemmacomp": "Suomi", "lex": "|Suomi..nn.1|", "msd": "SUBCAT_Prop|NUM_Sg|CASE_Gen|CASECHANGE_Up", "ocr": "0.99", "pos": "N", "ref": "1", "structs": { "open": [ "paragraph", "sentence" ] }, "word": "Suomen" }, { "dephead": "3", "deprel": "poss", "lemma": "suurihin", "lemmacomp": "suurihin", "lex": "|suurihin..nn.1|", "msd": "NUM_Sg|CASE_Gen|OTHER_UNK", "ocr": "0.98", "pos": "N", "ref": "2", "word": "suurihin" }, { "dephead": "0", "deprel": "ROOT", "lemma": "kylihin", "lemmacomp": "kylihin", "lex": "|kylihin..nn.1|", "msd": "NUM_Pl|CASE_Ill|OTHER_UNK", "ocr": "0.94", "pos": "N", "ref": "3", "word": "kylihin" }, { "dephead": "3", "deprel": "punct", "lemma": ".", "lemmacomp": ".", "lex": "|...xx.1|", "msd": "_", "ocr": "0.94", "pos": "Punct", "ref": "4", "structs": { "close": [ "sentence" ] }, "word": "." } ] }, { "corpus": "KLK_FI_1839", "match": { "end": 19, "position": 3072, "start": 18 }, "structs": { "paragraph_id": "5", "sentence_id": "222", "sentence_local_id": "17", "sentence_parse_state": "parsed", "text_binding_id": "501536", "text_datefrom": "18390101", "text_dateto": "18390131", "text_elec_date": "2008-05-09", "text_img_url": "#DIRECTORY#fk01442_1839-01_1#SEPARATOR#00014.#EXTENSION#", "text_issue_date": "01.1839", "text_issue_no": "1", "text_issue_title": "MEHIL\u00c4INEN.", "text_label": "MEHIL\u00c4INEN. no. 1 01.1839", "text_language": "fi", "text_page_no": "14", "text_publ_id": "fk01442", "text_publ_title": "Mehil\u00e4inen", "text_publ_type": "aikakausi", "text_sentcount": "18", "text_tokencount": "282" }, "tokens": [ { "dephead": "3", "deprel": "det", "lemma": "muutama", "lemmacomp": "muutama", "lex": "|muutama..pn.1|", "msd": "NUM_Pl|CASE_Nom|CASECHANGE_Up", "ocr": "0.94", "pos": "Pron", "ref": "1", "structs": { "open": [ "sentence" ] }, "word": "Muutamat" }, { "dephead": "3", "deprel": "advmod", "lemma": "sit\u00e4", "lemmacomp": "sit\u00e4", "lex": "|sit\u00e4..ab.1|", "msd": "_", "ocr": "0.90", "pos": "Adv", "ref": "2", "word": "sit\u00e4" }, { "dephead": "9", "deprel": "nsubj-cop", "lemma": "arwelewat", "lemmacomp": "arwelewat", "lex": "|arwelewat..nn.1|", "msd": "NUM_Pl|CASE_Nom|OTHER_UNK", "ocr": "0.95", "pos": "N", "ref": "3", "word": "arwelewat" }, { "dephead": "6", "deprel": "acomp", "lemma": "konsti", "lemmacomp": "konsti", "lex": "|konsti..jj.1|", "msd": "NUM_Sg|CASE_Tra|DRV_Der_llinen", "ocr": "0.93", "pos": "A", "ref": "4", "word": "konstilliseksi" }, { "dephead": "6", "deprel": "nsubj", "lemma": "myllyk-", "lemmacomp": "myllyk-", "lex": "|myllyk-..nn.1|", "msd": "NUM_Sg|CASE_Nom|OTHER_UNK", "ocr": "0.92", "pos": "N", "ref": "5", "word": "myllyk-" }, { "dephead": "9", "deprel": "advcl", "lemma": "si", "lemmacomp": "si", "lex": "|si..vb.1|", "msd": "PRS_Sg3|VOICE_Act|TENSE_Prt|MOOD_Ind|OTHER_UNK", "ocr": "0.85", "pos": "V", "ref": "6", "word": "si" }, { "dephead": "6", "deprel": "punct", "lemma": ",", "lemmacomp": ",", "lex": "|,..xx.1|", "msd": "_", "ocr": "0.85", "pos": "Punct", "ref": "7", "word": "," }, { "dephead": "9", "deprel": "poss", "lemma": "toiscc", "lemmacomp": "toiscc", "lex": "|toiscc..nn.1|", "msd": "SUBCAT_Acro|NUM_Sg|CASE_Nom|OTHER_UNK", "ocr": "0.91", "pos": "N", "ref": "8", "word": "toiscc" }, { "dephead": "0", "deprel": "ROOT", "lemma": "koko", "lemmacomp": "koko", "lex": "|koko..nn.1|", "msd": "NUM_Sg|CASE_Nom", "ocr": "0.91", "pos": "N", "ref": "9", "word": "koko" }, { "dephead": "9", "deprel": "nommod", "lemma": "maa", "lemmacomp": "maa", "lex": "|maa..nn.1|", "msd": "NUM_Sg|CASE_Par", "ocr": "0.97", "pos": "N", "ref": "10", "word": "maata" }, { "dephead": "14", "deprel": "mark", "lemma": "sill\u00e4", "lemmacomp": "sill\u00e4", "lex": "|sill\u00e4..kn.1|", "msd": "SUBCAT_CS", "ocr": "0.93", "pos": "C", "ref": "11", "word": "sill\u00e4" }, { "dephead": "13", "deprel": "nn", "lemma": "werrailluksi", "lemmacomp": "werrailluksi", "lex": "|werrailluksi..nn.1|", "msd": "NUM_Sg|CASE_Nom|OTHER_UNK", "ocr": "0.92", "pos": "N", "ref": "12", "word": "werrailluksi" }, { "dephead": "14", "deprel": "nommod", "lemma": "jne.", "lemmacomp": "jne.", "lex": "|jne...nn.1|", "msd": "SUBCAT_Abbr", "ocr": "0.88", "pos": "N", "ref": "13", "word": "jne." }, { "dephead": "9", "deprel": "advcl", "lemma": "olla", "lemmacomp": "olla", "lex": "|olla..vb.1|", "msd": "PRS_Sg3|VOICE_Act|TENSE_Prt|MOOD_Ind|CASECHANGE_Up", "ocr": "0.93", "pos": "V", "ref": "14", "word": "Oli" }, { "dephead": "16", "deprel": "nommod", "lemma": "se", "lemmacomp": "se", "lex": "|se..pn.1|", "msd": "SUBCAT_Dem|NUM_Sg|CASE_Ela", "ocr": "0.95", "pos": "Pron", "ref": "15", "word": "siit\u00e4" }, { "dephead": "14", "deprel": "conj", "lemma": "kyllaki", "lemmacomp": "kyllaki", "lex": "|kyllaki..vb.1|", "msd": "PRS_Sg3|VOICE_Act|TENSE_Prt|MOOD_Ind|OTHER_UNK", "ocr": "0.82", "pos": "V", "ref": "16", "word": "kyllaki" }, { "dephead": "16", "deprel": "advmod", "lemma": "silloin", "lemmacomp": "silloin", "lex": "|silloin..ab.1|", "msd": "_", "ocr": "0.90", "pos": "Adv", "ref": "17", "word": "silloin" }, { "dephead": "16", "deprel": "dobj", "lemma": "seikka", "lemmacomp": "seikka", "lex": "|seikka..nn.1|", "msd": "NUM_Pl|CASE_Par", "ocr": "0.88", "pos": "N", "ref": "18", "word": "seikkoja" }, { "dephead": "22", "deprel": "poss", "lemma": "Suomi", "lemmacomp": "Suomi", "lex": "|Suomi..nn.1|", "msd": "SUBCAT_Prop|NUM_Sg|CASE_Gen|CASECHANGE_Up", "ocr": "0.93", "pos": "N", "ref": "19", "word": "Suomen" }, { "dephead": "19", "deprel": "cc", "lemma": "ja", "lemmacomp": "ja", "lex": "|ja..kn.1|", "msd": "SUBCAT_CC", "ocr": "0.91", "pos": "C", "ref": "20", "word": "ja" }, { "dephead": "19", "deprel": "conj", "lemma": "Pohjola", "lemmacomp": "Pohjola", "lex": "|Pohjola..nn.1|", "msd": "SUBCAT_Prop|NUM_Sg|CASE_Gen|CASECHANGE_Up", "ocr": "0.92", "pos": "N", "ref": "21", "word": "Pohjolan" }, { "dephead": "16", "deprel": "nommod", "lemma": "w\u00e4lill\u00e4", "lemmacomp": "w\u00e4lill\u00e4", "lex": "|w\u00e4lill\u00e4..nn.1|", "msd": "NUM_Sg|CASE_Ade|OTHER_UNK", "ocr": "0.90", "pos": "N", "ref": "22", "word": "w\u00e4lill\u00e4" }, { "dephead": "9", "deprel": "punct", "lemma": ".", "lemmacomp": ".", "lex": "|...xx.1|", "msd": "_", "ocr": "0.90", "pos": "Punct", "ref": "23", "structs": { "close": [ "sentence", "paragraph" ] }, "word": "." } ] }, { "corpus": "KLK_FI_1839", "match": { "end": 1, "position": 3362, "start": 0 }, "structs": { "paragraph_id": "0", "sentence_id": "238", "sentence_local_id": "0", "sentence_parse_state": "parsed", "text_binding_id": "501536", "text_datefrom": "18390101", "text_dateto": "18390131", "text_elec_date": "2008-05-09", "text_img_url": "#DIRECTORY#fk01442_1839-01_1#SEPARATOR#00016.#EXTENSION#", "text_issue_date": "01.1839", "text_issue_no": "1", "text_issue_title": "MEHIL\u00c4INEN.", "text_label": "MEHIL\u00c4INEN. no. 1 01.1839", "text_language": "fi", "text_page_no": "16", "text_publ_id": "fk01442", "text_publ_title": "Mehil\u00e4inen", "text_publ_type": "aikakausi", "text_sentcount": "20", "text_tokencount": "237" }, "tokens": [ { "dephead": "2", "deprel": "poss", "lemma": "Suomi", "lemmacomp": "Suomi", "lex": "|Suomi..nn.1|", "msd": "SUBCAT_Prop|NUM_Sg|CASE_Gen|CASECHANGE_Up", "ocr": "0.90", "pos": "N", "ref": "1", "structs": { "open": [ "paragraph", "sentence" ] }, "word": "Suomen" }, { "dephead": "3", "deprel": "nsubj", "lemma": "muinas", "lemmacomp": "muinas", "lex": "|muinas..nn.1|", "msd": "NUM_Sg|CASE_Nom|OTHER_UNK", "ocr": "0.91", "pos": "N", "ref": "2", "word": "muinas" }, { "dephead": "0", "deprel": "ROOT", "lemma": "historioida", "lemmacomp": "historioida", "lex": "|historioida..vb.1|", "msd": "PRS_Sg2|VOICE_Act|TENSE_Prs|MOOD_Ind", "ocr": "0.94", "pos": "V", "ref": "3", "word": "historioit" }, { "dephead": "3", "deprel": "nommod", "lemma": "sika", "lemmacomp": "sika", "lex": "|sika..nn.1|", "msd": "NUM_Pl|CASE_All", "ocr": "0.96", "pos": "N", "ref": "4", "word": "sioille" }, { "dephead": "3", "deprel": "nommod", "lemma": "mietint\u00e4", "lemmacomp": "mietint\u00e4", "lex": "|mietint\u00e4..nn.1|", "msd": "NUM_Sg|CASE_Tra", "ocr": "0.93", "pos": "N", "ref": "5", "word": "mietinn\u00e4ksi" }, { "dephead": "3", "deprel": "punct", "lemma": ".", "lemmacomp": ".", "lex": "|...xx.1|", "msd": "_", "ocr": "0.93", "pos": "Punct", "ref": "6", "structs": { "close": [ "sentence", "paragraph" ] }, "word": "." } ] }, { "corpus": "KLK_FI_1839", "match": { "end": 5, "position": 3379, "start": 4 }, "structs": { "paragraph_id": "1", "sentence_id": "240", "sentence_local_id": "2", "sentence_parse_state": "parsed", "text_binding_id": "501536", "text_datefrom": "18390101", "text_dateto": "18390131", "text_elec_date": "2008-05-09", "text_img_url": "#DIRECTORY#fk01442_1839-01_1#SEPARATOR#00016.#EXTENSION#", "text_issue_date": "01.1839", "text_issue_no": "1", "text_issue_title": "MEHIL\u00c4INEN.", "text_label": "MEHIL\u00c4INEN. no. 1 01.1839", "text_language": "fi", "text_page_no": "16", "text_publ_id": "fk01442", "text_publ_title": "Mehil\u00e4inen", "text_publ_type": "aikakausi", "text_sentcount": "20", "text_tokencount": "237" }, "tokens": [ { "dephead": "2", "deprel": "amod", "lemma": "synkk\u00e4", "lemmacomp": "synkk\u00e4", "lex": "|synkk\u00e4..jj.1|", "msd": "NUM_Sg|CASE_Nom|CMP_Pos|CASECHANGE_Up", "ocr": "0.91", "pos": "A", "ref": "1", "structs": { "open": [ "sentence" ] }, "word": "Synkk\u00e4" }, { "dephead": "3", "deprel": "nn", "lemma": "pimi\u00e4", "lemmacomp": "pimi\u00e4", "lex": "|pimi\u00e4..nn.1|", "msd": "NUM_Sg|CASE_Nom|OTHER_UNK", "ocr": "0.93", "pos": "N", "ref": "2", "word": "pimi\u00e4" }, { "dephead": "0", "deprel": "ROOT", "lemma": "y\u00f6", "lemmacomp": "y\u00f6", "lex": "|y\u00f6..nn.1|", "msd": "NUM_Sg|CASE_Nom", "ocr": "0.93", "pos": "N", "ref": "3", "word": "y\u00f6" }, { "dephead": "3", "deprel": "infmod", "lemma": "peitt\u00e4\u00e4", "lemmacomp": "peitt\u00e4\u00e4", "lex": "|peitt\u00e4\u00e4..vb.1|", "msd": "NUM_Sg|CASE_Lat|VOICE_Act|INF_Inf1", "ocr": "0.95", "pos": "V", "ref": "4", "word": "peitt\u00e4\u00e4" }, { "dephead": "6", "deprel": "poss", "lemma": "Suomi", "lemmacomp": "Suomi", "lex": "|Suomi..nn.1|", "msd": "SUBCAT_Prop|NUM_Sg|CASE_Gen|CASECHANGE_Up", "ocr": "0.98", "pos": "N", "ref": "5", "word": "Suomen" }, { "dephead": "7", "deprel": "poss", "lemma": "muinasajan", "lemmacomp": "muinasajan", "lex": "|muinasajan..nn.1|", "msd": "NUM_Sg|CASE_Gen|OTHER_UNK", "ocr": "0.93", "pos": "N", "ref": "6", "word": "muinasajan" }, { "dephead": "4", "deprel": "dobj", "lemma": "tieto", "lemmacomp": "tieto", "lex": "|tieto..nn.1|", "msd": "NUM_Pl|CASE_Nom", "ocr": "0.94", "pos": "N", "ref": "7", "word": "tiedot" }, { "dephead": "3", "deprel": "punct", "lemma": ".", "lemmacomp": ".", "lex": "|...xx.1|", "msd": "_", "ocr": "0.94", "pos": "Punct", "ref": "8", "structs": { "close": [ "sentence" ] }, "word": "." } ] }, { "corpus": "KLK_FI_1839", "match": { "end": 13, "position": 3395, "start": 12 }, "structs": { "paragraph_id": "1", "sentence_id": "241", "sentence_local_id": "3", "sentence_parse_state": "parsed", "text_binding_id": "501536", "text_datefrom": "18390101", "text_dateto": "18390131", "text_elec_date": "2008-05-09", "text_img_url": "#DIRECTORY#fk01442_1839-01_1#SEPARATOR#00016.#EXTENSION#", "text_issue_date": "01.1839", "text_issue_no": "1", "text_issue_title": "MEHIL\u00c4INEN.", "text_label": "MEHIL\u00c4INEN. no. 1 01.1839", "text_language": "fi", "text_page_no": "16", "text_publ_id": "fk01442", "text_publ_title": "Mehil\u00e4inen", "text_publ_type": "aikakausi", "text_sentcount": "20", "text_tokencount": "237" }, "tokens": [ { "dephead": "2", "deprel": "nommod", "lemma": "Wasta", "lemmacomp": "Wasta", "lex": "|Wasta..nn.1|", "msd": "NUM_Sg|CASE_Par|CASECHANGE_Up|OTHER_UNK", "ocr": "0.97", "pos": "N", "ref": "1", "structs": { "open": [ "sentence" ] }, "word": "Wasta" }, { "dephead": "5", "deprel": "advmod", "lemma": "my\u00f6hemmin", "lemmacomp": "my\u00f6hemmin", "lex": "|my\u00f6hemmin..ab.1|", "msd": "_", "ocr": "0.95", "pos": "Adv", "ref": "2", "word": "my\u00f6hemmin" }, { "dephead": "2", "deprel": "cc", "lemma": "ja", "lemmacomp": "ja", "lex": "|ja..kn.1|", "msd": "SUBCAT_CC", "ocr": "1.00", "pos": "C", "ref": "3", "word": "ja" }, { "dephead": "2", "deprel": "conj", "lemma": "m\u00e4hitellen", "lemmacomp": "m\u00e4hitellen", "lex": "|m\u00e4hitellen..ab.1|", "msd": "OTHER_UNK", "ocr": "0.96", "pos": "Adv", "ref": "4", "word": "m\u00e4hitellen" }, { "dephead": "0", "deprel": "ROOT", "lemma": "alkaa", "lemmacomp": "alkaa", "lex": "|alkaa..vb.1|", "msd": "PRS_Sg3|VOICE_Act|TENSE_Prs|MOOD_Ind", "ocr": "0.98", "pos": "V", "ref": "5", "word": "alkaa" }, { "dephead": "7", "deprel": "advmod", "lemma": "p\u00e4iw\u00e4", "lemmacomp": "p\u00e4iw\u00e4", "lex": "|p\u00e4iw\u00e4..ab.1|", "msd": "OTHER_UNK", "ocr": "0.96", "pos": "Adv", "ref": "6", "word": "p\u00e4iw\u00e4" }, { "dephead": "5", "deprel": "xcomp", "lemma": "koittaa", "lemmacomp": "koittaa", "lex": "|koittaa..vb.1|", "msd": "PRS_Sg3|VOICE_Act|TENSE_Prs|MOOD_Ind", "ocr": "0.96", "pos": "V", "ref": "7", "word": "koittaa" }, { "dephead": "7", "deprel": "nommod", "lemma": "se", "lemmacomp": "se", "lex": "|se..pn.1|", "msd": "SUBCAT_Dem|NUM_Sg|CASE_Ela", "ocr": "0.95", "pos": "Pron", "ref": "8", "word": "siit\u00e4" }, { "dephead": "10", "deprel": "nommod", "lemma": "aika", "lemmacomp": "aika", "lex": "|aika..nn.1|", "msd": "NUM_Sg|CASE_Ela", "ocr": "0.93", "pos": "N", "ref": "9", "word": "ajasta" }, { "dephead": "8", "deprel": "advcl", "lemma": "ruweten", "lemmacomp": "ruweten", "lex": "|ruweten..vb.1|", "msd": "NUM_Sg|CASE_Ins|VOICE_Act|INF_Inf2|OTHER_UNK", "ocr": "0.94", "pos": "V", "ref": "10", "word": "ruweten" }, { "dephead": "15", "deprel": "punct", "lemma": ",", "lemmacomp": ",", "lex": "|,..xx.1|", "msd": "_", "ocr": "0.94", "pos": "Punct", "ref": "11", "word": "," }, { "dephead": "15", "deprel": "rel", "lemma": "joka", "lemmacomp": "joka", "lex": "|joka..pn.1|", "msd": "SUBCAT_Rel|NUM_Sg|CASE_Ess", "ocr": "0.87", "pos": "Pron", "ref": "12", "word": "jona" }, { "dephead": "14", "deprel": "poss", "lemma": "Suomi", "lemmacomp": "Suomi", "lex": "|Suomi..nn.1|", "msd": "SUBCAT_Prop|NUM_Sg|CASE_Gen|CASECHANGE_Up", "ocr": "0.80", "pos": "N", "ref": "13", "word": "Suomen" }, { "dephead": "15", "deprel": "dobj", "lemma": "maa", "lemmacomp": "maa", "lex": "|maa..nn.1|", "msd": "NUM_Sg|CASE_Nom", "ocr": "0.96", "pos": "N", "ref": "14", "word": "maa" }, { "dephead": "9", "deprel": "rcmod", "lemma": "mallata", "lemmacomp": "mallata", "lex": "|mallata..vb.1|", "msd": "PRS_Pe4|VOICE_Pass|TENSE_Prt|MOOD_Ind", "ocr": "0.93", "pos": "V", "ref": "15", "word": "mallattiin" }, { "dephead": "15", "deprel": "dobj", "lemma": "ruotsalainenilta", "lemmacomp": "ruotsalainen|ilta", "lex": "|ruotsalainenilta..nn.1|", "msd": "NUM_Sg|CASE_Nom|CASECHANGE_Up", "ocr": "0.92", "pos": "N", "ref": "16", "word": "Ruotsalaisilta" }, { "dephead": "15", "deprel": "punct", "lemma": ",", "lemmacomp": ",", "lex": "|,..xx.1|", "msd": "_", "ocr": "0.92", "pos": "Punct", "ref": "17", "word": "," }, { "dephead": "23", "deprel": "neg", "lemma": "ei", "lemmacomp": "ei", "lex": "|ei..vb.1|", "msd": "SUBCAT_Neg|PRS_Sg3|VOICE_Act", "ocr": "0.98", "pos": "V", "ref": "18", "word": "ei" }, { "dephead": "21", "deprel": "quantmod", "lemma": "t\u00e4ysi", "lemmacomp": "t\u00e4ysi", "lex": "|t\u00e4ysi..jj.1|", "msd": "NUM_Sg|CASE_Par|CMP_Pos", "ocr": "0.93", "pos": "A", "ref": "19", "word": "t\u00e4ytt\u00e4" }, { "dephead": "21", "deprel": "number", "lemma": "sietsem\u00e4n", "lemmacomp": "sietsem\u00e4n", "lex": "|sietsem\u00e4n..rg.1|", "msd": "SUBCAT_Card|NUM_Sg|CASE_Nom|OTHER_UNK", "ocr": "0.96", "pos": "Num", "ref": "20", "word": "sietsem\u00e4n" }, { "dephead": "22", "deprel": "num", "lemma": "sata", "lemmacomp": "sata", "lex": "|sata..rg.1|", "msd": "SUBCAT_Card|NUM_Sg|CASE_Par", "ocr": "0.90", "pos": "Num", "ref": "21", "word": "sataa" }, { "dephead": "23", "deprel": "nommod", "lemma": "wuotta", "lemmacomp": "wuotta", "lex": "|wuotta..nn.1|", "msd": "NUM_Sg|CASE_Par|OTHER_UNK", "ocr": "0.94", "pos": "N", "ref": "22", "word": "wuotta" }, { "dephead": "7", "deprel": "advmod", "lemma": "sitte", "lemmacomp": "sitte", "lex": "|sitte..ab.1|", "msd": "OTHER_UNK", "ocr": "0.95", "pos": "Adv", "ref": "23", "word": "sitte" }, { "dephead": "5", "deprel": "punct", "lemma": ".", "lemmacomp": ".", "lex": "|...xx.1|", "msd": "_", "ocr": "0.95", "pos": "Punct", "ref": "24", "structs": { "close": [ "sentence" ] }, "word": "." } ] }, { "corpus": "KLK_FI_1839", "match": { "end": 2, "position": 3475, "start": 1 }, "structs": { "paragraph_id": "1", "sentence_id": "245", "sentence_local_id": "7", "sentence_parse_state": "parsed", "text_binding_id": "501536", "text_datefrom": "18390101", "text_dateto": "18390131", "text_elec_date": "2008-05-09", "text_img_url": "#DIRECTORY#fk01442_1839-01_1#SEPARATOR#00016.#EXTENSION#", "text_issue_date": "01.1839", "text_issue_no": "1", "text_issue_title": "MEHIL\u00c4INEN.", "text_label": "MEHIL\u00c4INEN. no. 1 01.1839", "text_language": "fi", "text_page_no": "16", "text_publ_id": "fk01442", "text_publ_title": "Mehil\u00e4inen", "text_publ_type": "aikakausi", "text_sentcount": "20", "text_tokencount": "237" }, "tokens": [ { "dephead": "5", "deprel": "punct", "lemma": "\u2014", "lemmacomp": "\u2014", "lex": "|\u2014..xx.1|", "msd": "_", "ocr": "1.00", "pos": "Punct", "ref": "1", "structs": { "open": [ "sentence" ] }, "word": "\u2014" }, { "dephead": "4", "deprel": "poss", "lemma": "Suomi", "lemmacomp": "Suomi", "lex": "|Suomi..nn.1|", "msd": "SUBCAT_Prop|NUM_Sg|CASE_Gen|CASECHANGE_Up", "ocr": "0.95", "pos": "N", "ref": "2", "word": "Suomen" }, { "dephead": "4", "deprel": "amod", "lemma": "manhoissa", "lemmacomp": "manhoissa", "lex": "|manhoissa..jj.1|", "msd": "NUM_Pl|CASE_Ine|CMP_Pos|OTHER_UNK", "ocr": "0.95", "pos": "A", "ref": "3", "word": "manhoissa" }, { "dephead": "5", "deprel": "nommod", "lemma": "tarinaruno", "lemmacomp": "tarina|runo", "lex": "|tarinaruno..nn.1|", "msd": "NUM_Pl|CASE_Ine", "ocr": "0.97", "pos": "N", "ref": "4", "word": "tarinarunoissa" }, { "dephead": "0", "deprel": "ROOT", "lemma": "mainita", "lemmacomp": "mainita", "lex": "|mainita..vb.1|", "msd": "PRS_Pe4|VOICE_Pass|TENSE_Prs|MOOD_Ind", "ocr": "0.95", "pos": "V", "ref": "5", "word": "mainitaan" }, { "dephead": "7", "deprel": "advmod", "lemma": "my\u00f6s", "lemmacomp": "my\u00f6s", "lex": "|my\u00f6s..ab.1|", "msd": "_", "ocr": "0.89", "pos": "Adv", "ref": "6", "word": "my\u00f6s" }, { "dephead": "5", "deprel": "acomp", "lemma": "yht\u00e4l\u00e4inen", "lemmacomp": "yht\u00e4l\u00e4inen", "lex": "|yht\u00e4l\u00e4inen..jj.1|", "msd": "NUM_Sg|CASE_Ill|CMP_Pos", "ocr": "0.96", "pos": "A", "ref": "7", "word": "yht\u00e4l\u00e4iseen" }, { "dephead": "9", "deprel": "det", "lemma": "er\u00e4s", "lemmacomp": "er\u00e4s", "lex": "|er\u00e4s..pn.1|", "msd": "NUM_Sg|CASE_Ela", "ocr": "0.94", "pos": "Pron", "ref": "8", "word": "er\u00e4\u00e4st\u00e4" }, { "dephead": "7", "deprel": "nommod", "lemma": "kansa", "lemmacomp": "kansa", "lex": "|kansa..nn.1|", "msd": "NUM_Sg|CASE_Ela", "ocr": "0.93", "pos": "N", "ref": "9", "word": "kansasta" }, { "dephead": "11", "deprel": "punct", "lemma": "(", "lemmacomp": "(", "lex": "|(..xx.1|", "msd": "_", "ocr": "0.94", "pos": "Punct", "ref": "10", "word": "(" }, { "dephead": "9", "deprel": "appos", "lemma": "suomalainenjoukko", "lemmacomp": "suomalainen|joukko", "lex": "|suomalainenjoukko..nn.1|", "msd": "NUM_Sg|CASE_Ela|CASECHANGE_Up", "ocr": "0.94", "pos": "N", "ref": "11", "word": "Suomalaisjoukosta" }, { "dephead": "11", "deprel": "punct", "lemma": ")", "lemmacomp": ")", "lex": "|)..xx.1|", "msd": "_", "ocr": "0.94", "pos": "Punct", "ref": "12", "word": ")" }, { "dephead": "19", "deprel": "punct", "lemma": ",", "lemmacomp": ",", "lex": "|,..xx.1|", "msd": "_", "ocr": "0.94", "pos": "Punct", "ref": "13", "word": "," }, { "dephead": "19", "deprel": "rel", "lemma": "joka", "lemmacomp": "joka", "lex": "|joka..pn.1|", "msd": "SUBCAT_Rel|NUM_Sg|CASE_Nom", "ocr": "0.76", "pos": "Pron", "ref": "14", "word": "joka" }, { "dephead": "9", "deprel": "cc", "lemma": "sek\u00e4", "lemmacomp": "sek\u00e4", "lex": "|sek\u00e4..kn.1|", "msd": "SUBCAT_CC", "ocr": "0.98", "pos": "C", "ref": "15", "word": "sek\u00e4" }, { "dephead": "19", "deprel": "nommod", "lemma": "nimi", "lemmacomp": "nimi", "lex": "|nimi..nn.1|", "msd": "NUM_Sg|CASE_Gen|POSS_Px3", "ocr": "0.95", "pos": "N", "ref": "16", "word": "nimens\u00e4" }, { "dephead": "16", "deprel": "adpos", "lemma": "puolesta", "lemmacomp": "puolesta", "lex": "|puolesta..pp.1|", "msd": "SUBCAT_Po", "ocr": "0.94", "pos": "Adp", "ref": "17", "word": "puolesta" }, { "dephead": "19", "deprel": "cop", "lemma": "olla", "lemmacomp": "olla", "lex": "|olla..vb.1|", "msd": "PRS_Sg3|VOICE_Act|TENSE_Prt|MOOD_Ind", "ocr": "0.96", "pos": "V", "ref": "18", "word": "oli" }, { "dephead": "9", "deprel": "rcmod", "lemma": "kuulua", "lemmacomp": "kuulua", "lex": "|kuulua..vb.1|", "msd": "TENSE_Prs|MOOD_Ind|NEG_ConNeg", "ocr": "0.93", "pos": "V", "ref": "19", "word": "kuulu" }, { "dephead": "26", "deprel": "punct", "lemma": ",", "lemmacomp": ",", "lex": "|,..xx.1|", "msd": "_", "ocr": "0.93", "pos": "Punct", "ref": "20", "word": "," }, { "dephead": "26", "deprel": "complm", "lemma": "ett\u00e4", "lemmacomp": "ett\u00e4", "lex": "|ett\u00e4..kn.1|", "msd": "SUBCAT_CS", "ocr": "0.94", "pos": "C", "ref": "21", "word": "ett\u00e4" }, { "dephead": "23", "deprel": "poss", "lemma": "muuten'", "lemmacomp": "muuten'", "lex": "|muuten'..nn.1|", "msd": "NUM_Sg|CASE_Gen|OTHER_UNK", "ocr": "0.83", "pos": "N", "ref": "22", "word": "muuten'" }, { "dephead": "26", "deprel": "nsubj", "lemma": "tvoimakas", "lemmacomp": "tvoimakas", "lex": "|tvoimakas..nn.1|", "msd": "NUM_Sg|CASE_Nom|OTHER_UNK", "ocr": "0.91", "pos": "N", "ref": "23", "word": "tvoimakas" }, { "dephead": "23", "deprel": "cc", "lemma": "ja", "lemmacomp": "ja", "lex": "|ja..kn.1|", "msd": "SUBCAT_CC", "ocr": "0.74", "pos": "C", "ref": "24", "word": "ja" }, { "dephead": "23", "deprel": "conj", "lemma": "joka", "lemmacomp": "joka", "lex": "|joka..pn.1|", "msd": "SUBCAT_Rel|NUM_Sg|CASE_Nom", "ocr": "0.97", "pos": "Pron", "ref": "25", "word": "joka" }, { "dephead": "19", "deprel": "advcl", "lemma": "n\u00e4ytt\u00e4\u00e4", "lemmacomp": "n\u00e4ytt\u00e4\u00e4", "lex": "|n\u00e4ytt\u00e4\u00e4..vb.1|", "msd": "PRS_Sg3|VOICE_Act|TENSE_Prs|MOOD_Ind", "ocr": "0.94", "pos": "V", "ref": "26", "word": "n\u00e4ytt\u00e4\u00e4" }, { "dephead": "28", "deprel": "det", "lemma": "t\u00e4m\u00e4", "lemmacomp": "t\u00e4m\u00e4", "lex": "|t\u00e4m\u00e4..pn.1|", "msd": "SUBCAT_Dem|NUM_Pl|CASE_Ade", "ocr": "0.97", "pos": "Pron", "ref": "27", "word": "n\u00e4ill\u00e4" }, { "dephead": "29", "deprel": "nommod", "lemma": "seutu", "lemmacomp": "seutu", "lex": "|seutu..nn.1|", "msd": "NUM_Pl|CASE_Ins", "ocr": "0.94", "pos": "N", "ref": "28", "word": "seuduin" }, { "dephead": "26", "deprel": "xcomp", "lemma": "asua", "lemmacomp": "asua", "lex": "|asua..vb.1|", "msd": "NUM_Sg|CASE_Gen|VOICE_Act|PCP_PrfPrc|CMP_Pos", "ocr": "0.89", "pos": "V", "ref": "29", "word": "asuneen" }, { "dephead": "5", "deprel": "punct", "lemma": ".", "lemmacomp": ".", "lex": "|...xx.1|", "msd": "_", "ocr": "0.89", "pos": "Punct", "ref": "30", "structs": { "close": [ "sentence" ] }, "word": "." } ] }, { "corpus": "KLK_FI_1839", "match": { "end": 1, "position": 3606, "start": 0 }, "structs": { "paragraph_id": "3", "sentence_id": "261", "sentence_local_id": "3", "sentence_parse_state": "parsed", "text_binding_id": "502562", "text_datefrom": "18390202", "text_dateto": "18390228", "text_elec_date": "2008-05-09", "text_img_url": "#DIRECTORY#fk01442_1839-02_2#SEPARATOR#00001.#EXTENSION#", "text_issue_date": "02.1839", "text_issue_no": "2", "text_issue_title": "MEHIL\u00c4INEN.", "text_label": "MEHIL\u00c4INEN. no. 2 02.1839", "text_language": "fi", "text_page_no": "1", "text_publ_id": "fk01442", "text_publ_title": "Mehil\u00e4inen", "text_publ_type": "aikakausi", "text_sentcount": "14", "text_tokencount": "207" }, "tokens": [ { "dephead": "2", "deprel": "poss", "lemma": "Suomi", "lemmacomp": "Suomi", "lex": "|Suomi..nn.1|", "msd": "SUBCAT_Prop|NUM_Sg|CASE_Gen|CASECHANGE_Up", "ocr": "0.96", "pos": "N", "ref": "1", "structs": { "open": [ "paragraph", "sentence" ] }, "word": "Suomen" }, { "dephead": "3", "deprel": "nommod", "lemma": "muinashistorioitsioille", "lemmacomp": "muinashistorioitsioille", "lex": "|muinashistorioitsioille..nn.1|", "msd": "NUM_Pl|CASE_All|OTHER_UNK", "ocr": "0.96", "pos": "N", "ref": "2", "word": "muinashistorioitsioille" }, { "dephead": "0", "deprel": "ROOT", "lemma": "mietint\u00e4", "lemmacomp": "mietint\u00e4", "lex": "|mietint\u00e4..nn.1|", "msd": "NUM_Sg|CASE_Tra", "ocr": "0.95", "pos": "N", "ref": "3", "word": "mietinn\u00e4ksi" }, { "dephead": "3", "deprel": "punct", "lemma": ".", "lemmacomp": ".", "lex": "|...xx.1|", "msd": "_", "ocr": "0.95", "pos": "Punct", "ref": "4", "structs": { "close": [ "sentence", "paragraph" ] }, "word": "." } ] }, { "corpus": "KLK_FI_1839", "match": { "end": 8, "position": 4661, "start": 7 }, "structs": { "paragraph_id": "11", "sentence_id": "325", "sentence_local_id": "14", "sentence_parse_state": "parsed", "text_binding_id": "502562", "text_datefrom": "18390202", "text_dateto": "18390228", "text_elec_date": "2008-05-09", "text_img_url": "#DIRECTORY#fk01442_1839-02_2#SEPARATOR#00005.#EXTENSION#", "text_issue_date": "02.1839", "text_issue_no": "2", "text_issue_title": "MEHIL\u00c4INEN.", "text_label": "MEHIL\u00c4INEN. no. 2 02.1839", "text_language": "fi", "text_page_no": "5", "text_publ_id": "fk01442", "text_publ_title": "Mehil\u00e4inen", "text_publ_type": "aikakausi", "text_sentcount": "18", "text_tokencount": "177" }, "tokens": [ { "dephead": "3", "deprel": "auxpass", "lemma": "olla", "lemmacomp": "olla", "lex": "|olla..vb.1|", "msd": "PRS_Sg3|VOICE_Act|MOOD_Imprt|CASECHANGE_Up", "ocr": "0.91", "pos": "V", "ref": "1", "structs": { "open": [ "sentence" ] }, "word": "Olkoon" }, { "dephead": "3", "deprel": "dobj", "lemma": "t\u00e4m\u00e4", "lemmacomp": "t\u00e4m\u00e4", "lex": "|t\u00e4m\u00e4..pn.1|", "msd": "SUBCAT_Dem|NUM_Sg|CASE_Nom", "ocr": "0.94", "pos": "Pron", "ref": "2", "word": "t\u00e4m\u00e4" }, { "dephead": "0", "deprel": "ROOT", "lemma": "sanoa", "lemmacomp": "sanoa", "lex": "|sanoa..vb.1|", "msd": "NUM_Sg|CASE_Nom|VOICE_Pass|PCP_PrfPrc|CMP_Pos", "ocr": "0.94", "pos": "V", "ref": "3", "word": "sanottu" }, { "dephead": "5", "deprel": "nn", "lemma": "joksiki", "lemmacomp": "joksiki", "lex": "|joksiki..nn.1|", "msd": "NUM_Sg|CASE_Nom|OTHER_UNK", "ocr": "0.92", "pos": "N", "ref": "4", "word": "joksiki" }, { "dephead": "3", "deprel": "nommod", "lemma": "mietinnaksi", "lemmacomp": "mietinnaksi", "lex": "|mietinnaksi..nn.1|", "msd": "NUM_Sg|CASE_Tra|OTHER_UNK", "ocr": "0.96", "pos": "N", "ref": "5", "word": "mietinnaksi" }, { "dephead": "3", "deprel": "punct", "lemma": ",", "lemmacomp": ",", "lex": "|,..xx.1|", "msd": "_", "ocr": "0.96", "pos": "Punct", "ref": "6", "word": "," }, { "dephead": "9", "deprel": "poss", "lemma": "minkat\u00e4hden", "lemmacomp": "minkat\u00e4hden", "lex": "|minkat\u00e4hden..nn.1|", "msd": "NUM_Pl|CASE_Gen|OTHER_UNK", "ocr": "0.94", "pos": "N", "ref": "7", "word": "minkat\u00e4hden" }, { "dephead": "9", "deprel": "poss", "lemma": "Suomi", "lemmacomp": "Suomi", "lex": "|Suomi..nn.1|", "msd": "SUBCAT_Prop|NUM_Sg|CASE_Gen|CASECHANGE_Up", "ocr": "0.97", "pos": "N", "ref": "8", "word": "Suomen" }, { "dephead": "11", "deprel": "nsubj", "lemma": "kansa", "lemmacomp": "kansa", "lex": "|kansa..nn.1|", "msd": "NUM_Sg|CASE_Nom", "ocr": "0.98", "pos": "N", "ref": "9", "word": "kansa" }, { "dephead": "11", "deprel": "advmod", "lemma": "niin", "lemmacomp": "niin", "lex": "|niin..ab.1|", "msd": "_", "ocr": "1.00", "pos": "Adv", "ref": "10", "word": "niin" }, { "dephead": "3", "deprel": "conj", "lemma": "muinasaikaan", "lemmacomp": "muinasaikaan", "lex": "|muinasaikaan..vb.1|", "msd": "PRS_Sg3|VOICE_Act|TENSE_Prt|MOOD_Ind|CLIT_Foc_kaan|OTHER_UNK", "ocr": "0.96", "pos": "V", "ref": "11", "word": "muinasaikaan" }, { "dephead": "21", "deprel": "punct", "lemma": ",", "lemmacomp": ",", "lex": "|,..xx.1|", "msd": "_", "ocr": "0.96", "pos": "Punct", "ref": "12", "word": "," }, { "dephead": "21", "deprel": "mark", "lemma": "kun", "lemmacomp": "kun", "lex": "|kun..kn.1|", "msd": "SUBCAT_CS", "ocr": "0.96", "pos": "C", "ref": "13", "word": "kun" }, { "dephead": "21", "deprel": "nsubj", "lemma": "n\u00e4ky\u00e4\u00e4nki", "lemmacomp": "n\u00e4ky\u00e4\u00e4nki", "lex": "|n\u00e4ky\u00e4\u00e4nki..nn.1|", "msd": "NUM_Sg|CASE_Nom|OTHER_UNK", "ocr": "0.83", "pos": "N", "ref": "14", "word": "n\u00e4ky\u00e4\u00e4nki" }, { "dephead": "21", "deprel": "aux", "lemma": "olla", "lemmacomp": "olla", "lex": "|olla..vb.1|", "msd": "PRS_Sg3|VOICE_Act|TENSE_Prs|MOOD_Ind", "ocr": "1.00", "pos": "V", "ref": "15", "word": "on" }, { "dephead": "17", "deprel": "advmod", "lemma": "yli", "lemmacomp": "yli", "lex": "|yli..ab.1|", "msd": "_", "ocr": "0.94", "pos": "Adv", "ref": "16", "word": "yli" }, { "dephead": "19", "deprel": "det", "lemma": "moni", "lemmacomp": "moni", "lex": "|moni..pn.1|", "msd": "NUM_Sg|CASE_Gen", "ocr": "0.95", "pos": "Pron", "ref": "17", "word": "monen" }, { "dephead": "19", "deprel": "det", "lemma": "muu", "lemmacomp": "muu", "lex": "|muu..jj.1|", "msd": "NUM_Sg|CASE_Gen|CMP_Pos", "ocr": "0.98", "pos": "A", "ref": "18", "word": "muun" }, { "dephead": "20", "deprel": "poss", "lemma": "kansa", "lemmacomp": "kansa", "lex": "|kansa..nn.1|", "msd": "NUM_Sg|CASE_Gen", "ocr": "0.94", "pos": "N", "ref": "19", "word": "kansan" }, { "dephead": "21", "deprel": "nommod", "lemma": "lauluhin", "lemmacomp": "lauluhin", "lex": "|lauluhin..nn.1|", "msd": "NUM_Pl|CASE_Ill|OTHER_UNK", "ocr": "0.94", "pos": "N", "ref": "20", "word": "lauluhin" }, { "dephead": "11", "deprel": "advcl", "lemma": "harrastua", "lemmacomp": "harrastua", "lex": "|harrastua..vb.1|", "msd": "NUM_Sg|CASE_Nom|VOICE_Act|PCP_PrfPrc|CMP_Pos", "ocr": "0.91", "pos": "V", "ref": "21", "word": "harrastunut" }, { "dephead": "3", "deprel": "punct", "lemma": ".", "lemmacomp": ".", "lex": "|...xx.1|", "msd": "_", "ocr": "0.91", "pos": "Punct", "ref": "22", "structs": { "close": [ "sentence" ] }, "word": "." } ] }, { "corpus": "KLK_FI_1839", "match": { "end": 11, "position": 5068, "start": 10 }, "structs": { "paragraph_id": "5", "sentence_id": "347", "sentence_local_id": "7", "sentence_parse_state": "parsed", "text_binding_id": "502562", "text_datefrom": "18390202", "text_dateto": "18390228", "text_elec_date": "2008-05-09", "text_img_url": "#DIRECTORY#fk01442_1839-02_2#SEPARATOR#00007.#EXTENSION#", "text_issue_date": "02.1839", "text_issue_no": "2", "text_issue_title": "MEHIL\u00c4INEN.", "text_label": "MEHIL\u00c4INEN. no. 2 02.1839", "text_language": "fi", "text_page_no": "7", "text_publ_id": "fk01442", "text_publ_title": "Mehil\u00e4inen", "text_publ_type": "aikakausi", "text_sentcount": "21", "text_tokencount": "217" }, "tokens": [ { "dephead": "2", "deprel": "det", "lemma": "min\u00e4", "lemmacomp": "min\u00e4", "lex": "|min\u00e4..pn.1|", "msd": "SUBCAT_Pers|NUM_Sg|CASE_Nom|CASECHANGE_Up", "ocr": "0.97", "pos": "Pron", "ref": "1", "structs": { "open": [ "paragraph", "sentence" ] }, "word": "Min\u00e4" }, { "dephead": "4", "deprel": "nsubj-cop", "lemma": "tytt\u00f6", "lemmacomp": "tytt\u00f6", "lex": "|tytt\u00f6..nn.1|", "msd": "NUM_Sg|CASE_Nom", "ocr": "0.95", "pos": "N", "ref": "2", "word": "tytt\u00f6" }, { "dephead": "4", "deprel": "amod", "lemma": "nuori", "lemmacomp": "nuori", "lex": "|nuori..jj.1|", "msd": "NUM_Sg|CASE_Nom|CMP_Pos", "ocr": "0.97", "pos": "A", "ref": "3", "word": "nuori" }, { "dephead": "10", "deprel": "nsubj", "lemma": "tytt\u00f6", "lemmacomp": "tytt\u00f6", "lex": "|tytt\u00f6..nn.1|", "msd": "NUM_Sg|CASE_Nom", "ocr": "0.95", "pos": "N", "ref": "4", "word": "tytt\u00f6" }, { "dephead": "7", "deprel": "punct", "lemma": ",", "lemmacomp": ",", "lex": "|,..xx.1|", "msd": "_", "ocr": "0.95", "pos": "Punct", "ref": "5", "word": "," }, { "dephead": "7", "deprel": "advmod", "lemma": "niinkun", "lemmacomp": "niinkun", "lex": "|niinkun..ab.1|", "msd": "_", "ocr": "0.96", "pos": "Adv", "ref": "6", "word": "niinkun" }, { "dephead": "4", "deprel": "appos", "lemma": "merikaisla", "lemmacomp": "meri|kaisla", "lex": "|merikaisla..nn.1|", "msd": "NUM_Sg|CASE_Nom", "ocr": "0.94", "pos": "N", "ref": "7", "word": "merikaisla" }, { "dephead": "7", "deprel": "punct", "lemma": ",", "lemmacomp": ",", "lex": "|,..xx.1|", "msd": "_", "ocr": "0.94", "pos": "Punct", "ref": "8", "word": "," }, { "dephead": "10", "deprel": "neg", "lemma": "ei", "lemmacomp": "ei", "lex": "|ei..vb.1|", "msd": "SUBCAT_Neg|PRS_Sg3|VOICE_Act|CLIT_Foc_pa|CASECHANGE_Up", "ocr": "0.94", "pos": "V", "ref": "9", "word": "Eip\u00e4" }, { "dephead": "0", "deprel": "ROOT", "lemma": "synty\u00e4", "lemmacomp": "synty\u00e4", "lex": "|synty\u00e4..vb.1|", "msd": "TENSE_Prs|MOOD_Ind|NEG_ConNeg", "ocr": "0.98", "pos": "V", "ref": "10", "word": "synny" }, { "dephead": "12", "deprel": "poss", "lemma": "Suomi", "lemmacomp": "Suomi", "lex": "|Suomi..nn.1|", "msd": "SUBCAT_Prop|NUM_Sg|CASE_Gen|CASECHANGE_Up", "ocr": "0.96", "pos": "N", "ref": "11", "word": "Suomen" }, { "dephead": "10", "deprel": "nommod", "lemma": "maa", "lemmacomp": "maa", "lex": "|maa..nn.1|", "msd": "NUM_Sg|CASE_Ade", "ocr": "0.94", "pos": "N", "ref": "12", "word": "maalla" }, { "dephead": "10", "deprel": "nsubj", "lemma": "toinen", "lemmacomp": "toinen", "lex": "|toinen..nn.1|", "msd": "NUM_Sg|CASE_Par", "ocr": "0.96", "pos": "N", "ref": "13", "word": "toista" }, { "dephead": "13", "deprel": "nommod", "lemma": "t\u00e4m\u00e4nlainen", "lemmacomp": "t\u00e4m\u00e4nlainen", "lex": "|t\u00e4m\u00e4nlainen..jj.1|", "msd": "NUM_Sg|CASE_Par|CMP_Pos", "ocr": "0.95", "pos": "A", "ref": "14", "word": "t\u00e4m\u00e4nlaista" }, { "dephead": "10", "deprel": "punct", "lemma": ".", "lemmacomp": ".", "lex": "|...xx.1|", "msd": "_", "ocr": "0.95", "pos": "Punct", "ref": "15", "structs": { "close": [ "sentence", "paragraph" ] }, "word": "." } ] }, { "corpus": "KLK_FI_1839", "match": { "end": 3, "position": 5144, "start": 2 }, "structs": { "paragraph_id": "12", "sentence_id": "355", "sentence_local_id": "15", "sentence_parse_state": "parsed", "text_binding_id": "502562", "text_datefrom": "18390202", "text_dateto": "18390228", "text_elec_date": "2008-05-09", "text_img_url": "#DIRECTORY#fk01442_1839-02_2#SEPARATOR#00007.#EXTENSION#", "text_issue_date": "02.1839", "text_issue_no": "2", "text_issue_title": "MEHIL\u00c4INEN.", "text_label": "MEHIL\u00c4INEN. no. 2 02.1839", "text_language": "fi", "text_page_no": "7", "text_publ_id": "fk01442", "text_publ_title": "Mehil\u00e4inen", "text_publ_type": "aikakausi", "text_sentcount": "21", "text_tokencount": "217" }, "tokens": [ { "dephead": "4", "deprel": "nsubj-cop", "lemma": "min\u00e4", "lemmacomp": "min\u00e4", "lex": "|min\u00e4..pn.1|", "msd": "SUBCAT_Pers|NUM_Sg|CASE_Nom|CASECHANGE_Up", "ocr": "0.99", "pos": "Pron", "ref": "1", "structs": { "open": [ "paragraph", "sentence" ] }, "word": "Min\u00e4" }, { "dephead": "4", "deprel": "cop", "lemma": "olla", "lemmacomp": "olla", "lex": "|olla..vb.1|", "msd": "PRS_Sg1|VOICE_Act|TENSE_Prs|MOOD_Ind", "ocr": "0.94", "pos": "V", "ref": "2", "word": "olen" }, { "dephead": "4", "deprel": "poss", "lemma": "Suomi", "lemmacomp": "Suomi", "lex": "|Suomi..nn.1|", "msd": "SUBCAT_Prop|NUM_Sg|CASE_Gen|CASECHANGE_Up", "ocr": "0.96", "pos": "N", "ref": "3", "word": "Suomen" }, { "dephead": "0", "deprel": "ROOT", "lemma": "neito", "lemmacomp": "neito", "lex": "|neito..nn.1|", "msd": "NUM_Sg|CASE_Nom", "ocr": "0.94", "pos": "N", "ref": "4", "word": "neito" }, { "dephead": "4", "deprel": "punct", "lemma": ",", "lemmacomp": ",", "lex": "|,..xx.1|", "msd": "_", "ocr": "0.94", "pos": "Punct", "ref": "5", "word": "," }, { "dephead": "7", "deprel": "poss", "lemma": "Suomi", "lemmacomp": "Suomi", "lex": "|Suomi..nn.1|", "msd": "SUBCAT_Prop|NUM_Sg|CASE_Gen|CASECHANGE_Up", "ocr": "0.97", "pos": "N", "ref": "6", "word": "Suomen" }, { "dephead": "8", "deprel": "name", "lemma": "kori", "lemmacomp": "kori", "lex": "|kori..nn.1|", "msd": "NUM_Sg|CASE_Par", "ocr": "0.95", "pos": "N", "ref": "7", "word": "koria" }, { "dephead": "4", "deprel": "conj", "lemma": "kukka", "lemmacomp": "kukka", "lex": "|kukka..nn.1|", "msd": "NUM_Sg|CASE_Nom", "ocr": "0.96", "pos": "N", "ref": "8", "word": "kukka" }, { "dephead": "13", "deprel": "punct", "lemma": ",", "lemmacomp": ",", "lex": "|,..xx.1|", "msd": "_", "ocr": "0.96", "pos": "Punct", "ref": "9", "word": "," }, { "dephead": "11", "deprel": "det", "lemma": "moni", "lemmacomp": "moni", "lex": "|moni..pn.1|", "msd": "NUM_Sg|CASE_Nom|CASECHANGE_Up", "ocr": "0.97", "pos": "Pron", "ref": "10", "word": "Moni" }, { "dephead": "13", "deprel": "nsubj", "lemma": "poika", "lemmacomp": "poika", "lex": "|poika..nn.1|", "msd": "NUM_Sg|CASE_Nom", "ocr": "0.98", "pos": "N", "ref": "11", "word": "poika" }, { "dephead": "13", "deprel": "dobj", "lemma": "min\u00e4", "lemmacomp": "min\u00e4", "lex": "|min\u00e4..pn.1|", "msd": "SUBCAT_Pers|NUM_Sg|CASE_Par", "ocr": "0.98", "pos": "Pron", "ref": "12", "word": "minua" }, { "dephead": "8", "deprel": "rcmod", "lemma": "huokutteli", "lemmacomp": "huokutteli", "lex": "|huokutteli..vb.1|", "msd": "PRS_Sg3|VOICE_Act|TENSE_Prt|MOOD_Ind|OTHER_UNK", "ocr": "0.94", "pos": "V", "ref": "13", "word": "huokutteli" }, { "dephead": "13", "deprel": "advmod", "lemma": "hukkaan", "lemmacomp": "hukkaan", "lex": "|hukkaan..ab.1|", "msd": "_", "ocr": "0.95", "pos": "Adv", "ref": "14", "word": "hukkaan" }, { "dephead": "4", "deprel": "punct", "lemma": ".", "lemmacomp": ".", "lex": "|...xx.1|", "msd": "_", "ocr": "0.95", "pos": "Punct", "ref": "15", "structs": { "close": [ "sentence", "paragraph" ] }, "word": "." } ] }, { "corpus": "KLK_FI_1839", "match": { "end": 6, "position": 5147, "start": 5 }, "structs": { "paragraph_id": "12", "sentence_id": "355", "sentence_local_id": "15", "sentence_parse_state": "parsed", "text_binding_id": "502562", "text_datefrom": "18390202", "text_dateto": "18390228", "text_elec_date": "2008-05-09", "text_img_url": "#DIRECTORY#fk01442_1839-02_2#SEPARATOR#00007.#EXTENSION#", "text_issue_date": "02.1839", "text_issue_no": "2", "text_issue_title": "MEHIL\u00c4INEN.", "text_label": "MEHIL\u00c4INEN. no. 2 02.1839", "text_language": "fi", "text_page_no": "7", "text_publ_id": "fk01442", "text_publ_title": "Mehil\u00e4inen", "text_publ_type": "aikakausi", "text_sentcount": "21", "text_tokencount": "217" }, "tokens": [ { "dephead": "4", "deprel": "nsubj-cop", "lemma": "min\u00e4", "lemmacomp": "min\u00e4", "lex": "|min\u00e4..pn.1|", "msd": "SUBCAT_Pers|NUM_Sg|CASE_Nom|CASECHANGE_Up", "ocr": "0.99", "pos": "Pron", "ref": "1", "structs": { "open": [ "paragraph", "sentence" ] }, "word": "Min\u00e4" }, { "dephead": "4", "deprel": "cop", "lemma": "olla", "lemmacomp": "olla", "lex": "|olla..vb.1|", "msd": "PRS_Sg1|VOICE_Act|TENSE_Prs|MOOD_Ind", "ocr": "0.94", "pos": "V", "ref": "2", "word": "olen" }, { "dephead": "4", "deprel": "poss", "lemma": "Suomi", "lemmacomp": "Suomi", "lex": "|Suomi..nn.1|", "msd": "SUBCAT_Prop|NUM_Sg|CASE_Gen|CASECHANGE_Up", "ocr": "0.96", "pos": "N", "ref": "3", "word": "Suomen" }, { "dephead": "0", "deprel": "ROOT", "lemma": "neito", "lemmacomp": "neito", "lex": "|neito..nn.1|", "msd": "NUM_Sg|CASE_Nom", "ocr": "0.94", "pos": "N", "ref": "4", "word": "neito" }, { "dephead": "4", "deprel": "punct", "lemma": ",", "lemmacomp": ",", "lex": "|,..xx.1|", "msd": "_", "ocr": "0.94", "pos": "Punct", "ref": "5", "word": "," }, { "dephead": "7", "deprel": "poss", "lemma": "Suomi", "lemmacomp": "Suomi", "lex": "|Suomi..nn.1|", "msd": "SUBCAT_Prop|NUM_Sg|CASE_Gen|CASECHANGE_Up", "ocr": "0.97", "pos": "N", "ref": "6", "word": "Suomen" }, { "dephead": "8", "deprel": "name", "lemma": "kori", "lemmacomp": "kori", "lex": "|kori..nn.1|", "msd": "NUM_Sg|CASE_Par", "ocr": "0.95", "pos": "N", "ref": "7", "word": "koria" }, { "dephead": "4", "deprel": "conj", "lemma": "kukka", "lemmacomp": "kukka", "lex": "|kukka..nn.1|", "msd": "NUM_Sg|CASE_Nom", "ocr": "0.96", "pos": "N", "ref": "8", "word": "kukka" }, { "dephead": "13", "deprel": "punct", "lemma": ",", "lemmacomp": ",", "lex": "|,..xx.1|", "msd": "_", "ocr": "0.96", "pos": "Punct", "ref": "9", "word": "," }, { "dephead": "11", "deprel": "det", "lemma": "moni", "lemmacomp": "moni", "lex": "|moni..pn.1|", "msd": "NUM_Sg|CASE_Nom|CASECHANGE_Up", "ocr": "0.97", "pos": "Pron", "ref": "10", "word": "Moni" }, { "dephead": "13", "deprel": "nsubj", "lemma": "poika", "lemmacomp": "poika", "lex": "|poika..nn.1|", "msd": "NUM_Sg|CASE_Nom", "ocr": "0.98", "pos": "N", "ref": "11", "word": "poika" }, { "dephead": "13", "deprel": "dobj", "lemma": "min\u00e4", "lemmacomp": "min\u00e4", "lex": "|min\u00e4..pn.1|", "msd": "SUBCAT_Pers|NUM_Sg|CASE_Par", "ocr": "0.98", "pos": "Pron", "ref": "12", "word": "minua" }, { "dephead": "8", "deprel": "rcmod", "lemma": "huokutteli", "lemmacomp": "huokutteli", "lex": "|huokutteli..vb.1|", "msd": "PRS_Sg3|VOICE_Act|TENSE_Prt|MOOD_Ind|OTHER_UNK", "ocr": "0.94", "pos": "V", "ref": "13", "word": "huokutteli" }, { "dephead": "13", "deprel": "advmod", "lemma": "hukkaan", "lemmacomp": "hukkaan", "lex": "|hukkaan..ab.1|", "msd": "_", "ocr": "0.95", "pos": "Adv", "ref": "14", "word": "hukkaan" }, { "dephead": "4", "deprel": "punct", "lemma": ".", "lemmacomp": ".", "lex": "|...xx.1|", "msd": "_", "ocr": "0.95", "pos": "Punct", "ref": "15", "structs": { "close": [ "sentence", "paragraph" ] }, "word": "." } ] }, { "corpus": "KLK_FI_1839", "match": { "end": 2, "position": 5275, "start": 1 }, "structs": { "paragraph_id": "4", "sentence_id": "367", "sentence_local_id": "6", "sentence_parse_state": "parsed", "text_binding_id": "502562", "text_datefrom": "18390202", "text_dateto": "18390228", "text_elec_date": "2008-05-09", "text_img_url": "#DIRECTORY#fk01442_1839-02_2#SEPARATOR#00008.#EXTENSION#", "text_issue_date": "02.1839", "text_issue_no": "2", "text_issue_title": "MEHIL\u00c4INEN.", "text_label": "MEHIL\u00c4INEN. no. 2 02.1839", "text_language": "fi", "text_page_no": "8", "text_publ_id": "fk01442", "text_publ_title": "Mehil\u00e4inen", "text_publ_type": "aikakausi", "text_sentcount": "21", "text_tokencount": "234" }, "tokens": [ { "dephead": "6", "deprel": "nommod", "lemma": "Kaswo", "lemmacomp": "Kaswo", "lex": "|Kaswo..nn.1|", "msd": "NUM_Sg|CASE_Nom|CASECHANGE_Up|OTHER_UNK", "ocr": "0.93", "pos": "N", "ref": "1", "structs": { "open": [ "paragraph", "sentence" ] }, "word": "Kaswo" }, { "dephead": "3", "deprel": "poss", "lemma": "Suomi", "lemmacomp": "Suomi", "lex": "|Suomi..nn.1|", "msd": "SUBCAT_Prop|NUM_Sg|CASE_Gen|CASECHANGE_Up", "ocr": "0.87", "pos": "N", "ref": "2", "word": "Suomen" }, { "dephead": "1", "deprel": "nommod", "lemma": "ranta", "lemmacomp": "ranta", "lex": "|ranta..nn.1|", "msd": "NUM_Sg|CASE_Ade", "ocr": "0.94", "pos": "N", "ref": "3", "word": "rannalla" }, { "dephead": "6", "deprel": "det", "lemma": "se", "lemmacomp": "se", "lex": "|se..pn.1|", "msd": "SUBCAT_Dem|NUM_Sg|CASE_Nom", "ocr": "0.96", "pos": "Pron", "ref": "4", "word": "se" }, { "dephead": "6", "deprel": "amod", "lemma": "ympyrainen", "lemmacomp": "ympyrainen", "lex": "|ympyrainen..jj.1|", "msd": "NUM_Sg|CASE_Nom|CMP_Pos|OTHER_UNK", "ocr": "0.91", "pos": "A", "ref": "5", "word": "ympyrainen" }, { "dephead": "0", "deprel": "ROOT", "lemma": "nauris", "lemmacomp": "nauris", "lex": "|nauris..nn.1|", "msd": "NUM_Sg|CASE_Nom", "ocr": "0.94", "pos": "N", "ref": "6", "word": "nauris" }, { "dephead": "11", "deprel": "punct", "lemma": ",", "lemmacomp": ",", "lex": "|,..xx.1|", "msd": "_", "ocr": "0.94", "pos": "Punct", "ref": "7", "word": "," }, { "dephead": "9", "deprel": "det", "lemma": "t\u00e4m\u00e4", "lemmacomp": "t\u00e4m\u00e4", "lex": "|t\u00e4m\u00e4..pn.1|", "msd": "SUBCAT_Dem|NUM_Sg|CASE_Nom|CASECHANGE_Up", "ocr": "0.80", "pos": "Pron", "ref": "8", "word": "T\u00e4m\u00e4" }, { "dephead": "11", "deprel": "nsubj-cop", "lemma": "likka", "lemmacomp": "likka", "lex": "|likka..nn.1|", "msd": "NUM_Sg|CASE_Nom", "ocr": "0.95", "pos": "N", "ref": "9", "word": "likka" }, { "dephead": "11", "deprel": "cop", "lemma": "olla", "lemmacomp": "olla", "lex": "|olla..vb.1|", "msd": "PRS_Sg3|VOICE_Act|TENSE_Prs|MOOD_Ind", "ocr": "0.91", "pos": "V", "ref": "10", "word": "on" }, { "dephead": "6", "deprel": "rcmod", "lemma": "lihawa", "lemmacomp": "lihawa", "lex": "|lihawa..nn.1|", "msd": "NUM_Sg|CASE_Nom|OTHER_UNK", "ocr": "0.91", "pos": "N", "ref": "11", "word": "lihawa" }, { "dephead": "11", "deprel": "cc", "lemma": "ja", "lemmacomp": "ja", "lex": "|ja..kn.1|", "msd": "SUBCAT_CC", "ocr": "0.87", "pos": "C", "ref": "12", "word": "ja" }, { "dephead": "14", "deprel": "nsubj-cop", "lemma": "punaposki", "lemmacomp": "puna|poski", "lex": "|punaposki..nn.1|", "msd": "NUM_Sg|CASE_Nom", "ocr": "0.89", "pos": "N", "ref": "13", "word": "punaposki" }, { "dephead": "11", "deprel": "conj", "lemma": "kaunis", "lemmacomp": "kaunis", "lex": "|kaunis..jj.1|", "msd": "NUM_Sg|CASE_Nom|CMP_Pos", "ocr": "0.96", "pos": "A", "ref": "14", "word": "kaunis" }, { "dephead": "6", "deprel": "punct", "lemma": ".", "lemmacomp": ".", "lex": "|...xx.1|", "msd": "_", "ocr": "0.96", "pos": "Punct", "ref": "15", "structs": { "close": [ "sentence", "paragraph" ] }, "word": "." } ] }, { "corpus": "KLK_FI_1839", "match": { "end": 1, "position": 5907, "start": 0 }, "structs": { "paragraph_id": "15", "sentence_id": "418", "sentence_local_id": "15", "sentence_parse_state": "parsed", "text_binding_id": "502562", "text_datefrom": "18390202", "text_dateto": "18390228", "text_elec_date": "2008-05-09", "text_img_url": "#DIRECTORY#fk01442_1839-02_2#SEPARATOR#00010.#EXTENSION#", "text_issue_date": "02.1839", "text_issue_no": "2", "text_issue_title": "MEHIL\u00c4INEN.", "text_label": "MEHIL\u00c4INEN. no. 2 02.1839", "text_language": "fi", "text_page_no": "10", "text_publ_id": "fk01442", "text_publ_title": "Mehil\u00e4inen", "text_publ_type": "aikakausi", "text_sentcount": "17", "text_tokencount": "236" }, "tokens": [ { "dephead": "2", "deprel": "poss", "lemma": "Suomi", "lemmacomp": "Suomi", "lex": "|Suomi..nn.1|", "msd": "SUBCAT_Prop|NUM_Sg|CASE_Gen|CASECHANGE_Up", "ocr": "0.98", "pos": "N", "ref": "1", "structs": { "open": [ "paragraph", "sentence" ] }, "word": "Suomen" }, { "dephead": "4", "deprel": "nommod", "lemma": "maa", "lemmacomp": "maa", "lex": "|maa..nn.1|", "msd": "NUM_Sg|CASE_Ine", "ocr": "0.96", "pos": "N", "ref": "2", "word": "maassa" }, { "dephead": "4", "deprel": "nommod", "lemma": "Karjala", "lemmacomp": "Karjala", "lex": "|Karjala..nn.1|", "msd": "SUBCAT_Prop|NUM_Sg|CASE_Ine|CASECHANGE_Up", "ocr": "0.93", "pos": "N", "ref": "3", "word": "Karjalassa" }, { "dephead": "0", "deprel": "ROOT", "lemma": "olla", "lemmacomp": "olla", "lex": "|olla..vb.1|", "msd": "PRS_Sg3|VOICE_Act|TENSE_Prs|MOOD_Ind", "ocr": "0.91", "pos": "V", "ref": "4", "word": "on" }, { "dephead": "6", "deprel": "poss", "lemma": "m\u00e4", "lemmacomp": "m\u00e4", "lex": "|m\u00e4..pn.1|", "msd": "NUM_Sg|CASE_Gen", "ocr": "0.94", "pos": "Pron", "ref": "5", "word": "mun" }, { "dephead": "4", "deprel": "nsubj", "lemma": "kulta", "lemmacomp": "kulta", "lex": "|kulta..nn.1|", "msd": "NUM_Pl|CASE_Nom|POSS_PxSg1", "ocr": "0.93", "pos": "N", "ref": "6", "word": "kultani" }, { "dephead": "18", "deprel": "advmod", "lemma": "juuri", "lemmacomp": "juuri", "lex": "|juuri..ab.1|", "msd": "_", "ocr": "0.93", "pos": "Adv", "ref": "7", "word": "juuri" }, { "dephead": "10", "deprel": "punct", "lemma": ",", "lemmacomp": ",", "lex": "|,..xx.1|", "msd": "_", "ocr": "0.93", "pos": "Punct", "ref": "8", "word": "," }, { "dephead": "10", "deprel": "advmod", "lemma": "Waikk^", "lemmacomp": "Waikk^", "lex": "|Waikk^..ab.1|", "msd": "CASECHANGE_Up|OTHER_UNK", "ocr": "0.74", "pos": "Adv", "ref": "9", "word": "Waikk^" }, { "dephead": "6", "deprel": "rcmod", "lemma": "ei", "lemmacomp": "ei", "lex": "|ei..vb.1|", "msd": "SUBCAT_Neg|PRS_Sg1|VOICE_Act", "ocr": "0.91", "pos": "V", "ref": "10", "word": "en" }, { "dephead": "10", "deprel": "dobj", "lemma": "tie\u00e4", "lemmacomp": "tie\u00e4", "lex": "|tie\u00e4..nn.1|", "msd": "NUM_Sg|CASE_Par|OTHER_UNK", "ocr": "0.96", "pos": "N", "ref": "11", "word": "tie\u00e4" }, { "dephead": "10", "deprel": "punct", "lemma": ",", "lemmacomp": ",", "lex": "|,..xx.1|", "msd": "_", "ocr": "0.96", "pos": "Punct", "ref": "12", "word": "," }, { "dephead": "4", "deprel": "cc", "lemma": "ei", "lemmacomp": "ei", "lex": "|ei..vb.1|", "msd": "SUBCAT_Neg|PRS_Sg1|VOICE_Act|CLIT_Foc_ka", "ocr": "0.94", "pos": "V", "ref": "13", "word": "enk\u00e4" }, { "dephead": "4", "deprel": "conj", "lemma": "tuntea", "lemmacomp": "tuntea", "lex": "|tuntea..vb.1|", "msd": "TENSE_Prs|MOOD_Ind|NEG_ConNeg", "ocr": "0.92", "pos": "V", "ref": "14", "word": "tunne" }, { "dephead": "14", "deprel": "ccomp", "lemma": "pieni\u00e4", "lemmacomp": "pieni\u00e4", "lex": "|pieni\u00e4..vb.1|", "msd": "PRS_Sg3|VOICE_Act|TENSE_Prt|MOOD_Ind|CLIT_Qst", "ocr": "0.96", "pos": "V", "ref": "15", "word": "pienik\u00f6" }, { "dephead": "18", "deprel": "cop", "lemma": "olla", "lemmacomp": "olla", "lex": "|olla..vb.1|", "msd": "VOICE_Act|MOOD_Pot|NEG_ConNeg", "ocr": "0.97", "pos": "V", "ref": "16", "word": "lie" }, { "dephead": "18", "deprel": "advmod", "lemma": "mai", "lemmacomp": "mai", "lex": "|mai..ab.1|", "msd": "OTHER_UNK", "ocr": "0.94", "pos": "Adv", "ref": "17", "word": "mai" }, { "dephead": "15", "deprel": "ccomp", "lemma": "suuri", "lemmacomp": "suuri", "lex": "|suuri..jj.1|", "msd": "NUM_Sg|CASE_Nom|CMP_Pos", "ocr": "0.93", "pos": "A", "ref": "18", "word": "suuri" }, { "dephead": "4", "deprel": "punct", "lemma": ".", "lemmacomp": ".", "lex": "|...xx.1|", "msd": "_", "ocr": "0.93", "pos": "Punct", "ref": "19", "structs": { "close": [ "sentence", "paragraph" ] }, "word": "." } ] }, { "corpus": "KLK_FI_1839", "match": { "end": 1, "position": 6434, "start": 0 }, "structs": { "paragraph_id": "2", "sentence_id": "463", "sentence_local_id": "3", "sentence_parse_state": "parsed", "text_binding_id": "502562", "text_datefrom": "18390202", "text_dateto": "18390228", "text_elec_date": "2008-05-09", "text_img_url": "#DIRECTORY#fk01442_1839-02_2#SEPARATOR#00013.#EXTENSION#", "text_issue_date": "02.1839", "text_issue_no": "2", "text_issue_title": "MEHIL\u00c4INEN.", "text_label": "MEHIL\u00c4INEN. no. 2 02.1839", "text_language": "fi", "text_page_no": "13", "text_publ_id": "fk01442", "text_publ_title": "Mehil\u00e4inen", "text_publ_type": "aikakausi", "text_sentcount": "21", "text_tokencount": "266" }, "tokens": [ { "dephead": "2", "deprel": "poss", "lemma": "Suomi", "lemmacomp": "Suomi", "lex": "|Suomi..nn.1|", "msd": "SUBCAT_Prop|NUM_Sg|CASE_Gen|CASECHANGE_Up", "ocr": "0.91", "pos": "N", "ref": "1", "structs": { "open": [ "sentence" ] }, "word": "Suomen" }, { "dephead": "4", "deprel": "nsubj", "lemma": "poika", "lemmacomp": "poika", "lex": "|poika..nn.1|", "msd": "NUM_Pl|CASE_Nom", "ocr": "0.71", "pos": "N", "ref": "2", "word": "pojat" }, { "dephead": "4", "deprel": "advmod", "lemma": "poies", "lemmacomp": "poies", "lex": "|poies..ab.1|", "msd": "_", "ocr": "0.91", "pos": "Adv", "ref": "3", "word": "poies" }, { "dephead": "0", "deprel": "ROOT", "lemma": "menn\u00e4", "lemmacomp": "menn\u00e4", "lex": "|menn\u00e4..vb.1|", "msd": "PRS_Pl3|VOICE_Act|MOOD_Imprt", "ocr": "0.88", "pos": "V", "ref": "4", "word": "menk\u00f6\u00f6t" }, { "dephead": "6", "deprel": "poss", "lemma": "engelsmanni", "lemmacomp": "engelsmanni", "lex": "|engelsmanni..nn.1|", "msd": "NUM_Sg|CASE_Gen|CASECHANGE_Up", "ocr": "0.88", "pos": "N", "ref": "5", "word": "Engelsmannin" }, { "dephead": "4", "deprel": "nommod", "lemma": "laiwaan", "lemmacomp": "laiwaan", "lex": "|laiwaan..nn.1|", "msd": "NUM_Sg|CASE_Ill|OTHER_UNK", "ocr": "0.88", "pos": "N", "ref": "6", "word": "laiwaan" }, { "dephead": "4", "deprel": "punct", "lemma": ",", "lemmacomp": ",", "lex": "|,..xx.1|", "msd": "_", "ocr": "0.88", "pos": "Punct", "ref": "7", "structs": { "close": [ "sentence", "paragraph" ] }, "word": "," } ] }, { "corpus": "KLK_FI_1839", "match": { "end": 3, "position": 6454, "start": 2 }, "structs": { "paragraph_id": "4", "sentence_id": "465", "sentence_local_id": "5", "sentence_parse_state": "parsed", "text_binding_id": "502562", "text_datefrom": "18390202", "text_dateto": "18390228", "text_elec_date": "2008-05-09", "text_img_url": "#DIRECTORY#fk01442_1839-02_2#SEPARATOR#00013.#EXTENSION#", "text_issue_date": "02.1839", "text_issue_no": "2", "text_issue_title": "MEHIL\u00c4INEN.", "text_label": "MEHIL\u00c4INEN. no. 2 02.1839", "text_language": "fi", "text_page_no": "13", "text_publ_id": "fk01442", "text_publ_title": "Mehil\u00e4inen", "text_publ_type": "aikakausi", "text_sentcount": "21", "text_tokencount": "266" }, "tokens": [ { "dephead": "2", "deprel": "advmod", "lemma": "poies", "lemmacomp": "poies", "lex": "|poies..ab.1|", "msd": "CASECHANGE_Up", "ocr": "0.91", "pos": "Adv", "ref": "1", "structs": { "open": [ "paragraph", "sentence" ] }, "word": "Poies" }, { "dephead": "0", "deprel": "ROOT", "lemma": "wiea\u00e4n", "lemmacomp": "wiea\u00e4n", "lex": "|wiea\u00e4n..vb.1|", "msd": "PRS_Pe4|VOICE_Pass|TENSE_Prs|MOOD_Ind|OTHER_UNK", "ocr": "0.93", "pos": "V", "ref": "2", "word": "wiea\u00e4n" }, { "dephead": "5", "deprel": "poss", "lemma": "Suomi", "lemmacomp": "Suomi", "lex": "|Suomi..nn.1|", "msd": "SUBCAT_Prop|NUM_Sg|CASE_Gen|CASECHANGE_Up", "ocr": "0.79", "pos": "N", "ref": "3", "word": "Suomen" }, { "dephead": "3", "deprel": "punct", "lemma": "\u00bb", "lemmacomp": "\u00bb", "lex": "|\u00bb..xx.1|", "msd": "_", "ocr": "0.79", "pos": "Punct", "ref": "4", "word": "\u00bb" }, { "dephead": "2", "deprel": "dobj", "lemma": "poika", "lemmacomp": "poika", "lex": "|poika..nn.1|", "msd": "NUM_Pl|CASE_Nom", "ocr": "0.89", "pos": "N", "ref": "5", "word": "pojat" }, { "dephead": "7", "deprel": "poss", "lemma": "ruunun", "lemmacomp": "ruunun", "lex": "|ruunun..nn.1|", "msd": "NUM_Sg|CASE_Gen|OTHER_UNK", "ocr": "0.94", "pos": "N", "ref": "6", "word": "ruunun" }, { "dephead": "2", "deprel": "nommod", "lemma": "ankkurpajaan", "lemmacomp": "ankkurpajaan", "lex": "|ankkurpajaan..nn.1|", "msd": "NUM_Sg|CASE_Ill|OTHER_UNK", "ocr": "0.91", "pos": "N", "ref": "7", "word": "ankkurpajaan" }, { "dephead": "2", "deprel": "punct", "lemma": ",", "lemmacomp": ",", "lex": "|,..xx.1|", "msd": "_", "ocr": "0.91", "pos": "Punct", "ref": "8", "word": "," }, { "dephead": "10", "deprel": "advmod", "lemma": "siell\u00e4", "lemmacomp": "siell\u00e4", "lex": "|siell\u00e4..ab.1|", "msd": "CASECHANGE_Up", "ocr": "0.80", "pos": "Adv", "ref": "9", "word": "Siell\u00e4" }, { "dephead": "2", "deprel": "conj", "lemma": "lyow\u00e4t", "lemmacomp": "lyow\u00e4t", "lex": "|lyow\u00e4t..vb.1|", "msd": "PRS_Pl3|VOICE_Act|TENSE_Prs|MOOD_Ind|OTHER_UNK", "ocr": "0.88", "pos": "V", "ref": "10", "word": "lyow\u00e4t" }, { "dephead": "10", "deprel": "nommod", "lemma": "rapa", "lemmacomp": "rapa", "lex": "|rapa..nn.1|", "msd": "NUM_Sg|CASE_Gen", "ocr": "0.87", "pos": "N", "ref": "11", "word": "ravan" }, { "dephead": "11", "deprel": "adpos", "lemma": "p\u00e4\u00e4lle", "lemmacomp": "p\u00e4\u00e4lle", "lex": "|p\u00e4\u00e4lle..pp.1|", "msd": "SUBCAT_Po", "ocr": "0.97", "pos": "Adp", "ref": "12", "word": "p\u00e4\u00e4lle" }, { "dephead": "10", "deprel": "punct", "lemma": ",", "lemmacomp": ",", "lex": "|,..xx.1|", "msd": "_", "ocr": "0.97", "pos": "Punct", "ref": "13", "word": "," }, { "dephead": "15", "deprel": "nsubj-cop", "lemma": "kivimuuri", "lemmacomp": "kivi|muuri", "lex": "|kivimuuri..nn.1|", "msd": "NUM_Pl|CASE_Nom", "ocr": "0.83", "pos": "N", "ref": "14", "word": "kivimuurit" }, { "dephead": "10", "deprel": "conj", "lemma": "kajaa", "lemmacomp": "kajaa", "lex": "|kajaa..nn.1|", "msd": "NUM_Sg|CASE_Par|OTHER_UNK", "ocr": "0.90", "pos": "N", "ref": "15", "word": "kajaa" }, { "dephead": "2", "deprel": "punct", "lemma": ".", "lemmacomp": ".", "lex": "|...xx.1|", "msd": "_", "ocr": "0.90", "pos": "Punct", "ref": "16", "structs": { "close": [ "sentence", "paragraph" ] }, "word": "." } ] }, { "corpus": "KLK_FI_1839", "match": { "end": 3, "position": 6490, "start": 2 }, "structs": { "paragraph_id": "6", "sentence_id": "468", "sentence_local_id": "8", "sentence_parse_state": "parsed", "text_binding_id": "502562", "text_datefrom": "18390202", "text_dateto": "18390228", "text_elec_date": "2008-05-09", "text_img_url": "#DIRECTORY#fk01442_1839-02_2#SEPARATOR#00013.#EXTENSION#", "text_issue_date": "02.1839", "text_issue_no": "2", "text_issue_title": "MEHIL\u00c4INEN.", "text_label": "MEHIL\u00c4INEN. no. 2 02.1839", "text_language": "fi", "text_page_no": "13", "text_publ_id": "fk01442", "text_publ_title": "Mehil\u00e4inen", "text_publ_type": "aikakausi", "text_sentcount": "21", "text_tokencount": "266" }, "tokens": [ { "dephead": "2", "deprel": "nsubj", "lemma": "mik\u00e4", "lemmacomp": "mik\u00e4", "lex": "|mik\u00e4..pn.1|", "msd": "SUBCAT_Interr|NUM_Sg|CASE_Nom|CASECHANGE_Up", "ocr": "0.95", "pos": "Pron", "ref": "1", "structs": { "open": [ "sentence" ] }, "word": "Mik\u00e4s" }, { "dephead": "0", "deprel": "ROOT", "lemma": "auttaa", "lemmacomp": "auttaa", "lex": "|auttaa..vb.1|", "msd": "PRS_Sg3|VOICE_Act|TENSE_Prs|MOOD_Ind", "ocr": "0.88", "pos": "V", "ref": "2", "word": "auttaa" }, { "dephead": "4", "deprel": "poss", "lemma": "Suomi", "lemmacomp": "Suomi", "lex": "|Suomi..nn.1|", "msd": "SUBCAT_Prop|NUM_Sg|CASE_Gen|CASECHANGE_Up", "ocr": "0.86", "pos": "N", "ref": "3", "word": "Suomen" }, { "dephead": "2", "deprel": "dobj", "lemma": "poika", "lemmacomp": "poika", "lex": "|poika..nn.1|", "msd": "NUM_Pl|CASE_Par", "ocr": "0.89", "pos": "N", "ref": "4", "word": "poikia" }, { "dephead": "9", "deprel": "punct", "lemma": ",", "lemmacomp": ",", "lex": "|,..xx.1|", "msd": "_", "ocr": "0.85", "pos": "Punct", "ref": "5", "word": "," }, { "dephead": "9", "deprel": "mark", "lemma": "kun", "lemmacomp": "kun", "lex": "|kun..kn.1|", "msd": "SUBCAT_CS", "ocr": "0.79", "pos": "C", "ref": "6", "word": "kun" }, { "dephead": "8", "deprel": "poss", "lemma": "ci", "lemmacomp": "ci", "lex": "|ci..nn.1|", "msd": "NUM_Sg|CASE_Gen|OTHER_UNK", "ocr": "0.70", "pos": "N", "ref": "7", "word": "ci" }, { "dephead": "9", "deprel": "nsubj", "lemma": "raha", "lemmacomp": "raha", "lex": "|raha..nn.1|", "msd": "NUM_Pl|CASE_Nom", "ocr": "0.80", "pos": "N", "ref": "8", "word": "rahat" }, { "dephead": "2", "deprel": "advcl", "lemma": "auttaa", "lemmacomp": "auttaa", "lex": "|auttaa..vb.1|", "msd": "TENSE_Prs|MOOD_Ind|NEG_ConNeg", "ocr": "0.83", "pos": "V", "ref": "9", "word": "auta" }, { "dephead": "2", "deprel": "punct", "lemma": "\u2014", "lemmacomp": "\u2014", "lex": "|\u2014..xx.1|", "msd": "_", "ocr": "1.00", "pos": "Punct", "ref": "10", "word": "\u2014" }, { "dephead": "2", "deprel": "conj", "lemma": "t\u00e4yty\u00e4", "lemmacomp": "t\u00e4yty\u00e4", "lex": "|t\u00e4yty\u00e4..vb.1|", "msd": "PRS_Sg3|VOICE_Act|TENSE_Prs|MOOD_Ind|CASECHANGE_Up", "ocr": "0.82", "pos": "V", "ref": "11", "word": "T\u00e4ytyy" }, { "dephead": "2", "deprel": "punct", "lemma": ",", "lemmacomp": ",", "lex": "|,..xx.1|", "msd": "_", "ocr": "0.82", "pos": "Punct", "ref": "12", "word": "," }, { "dephead": "2", "deprel": "conj", "lemma": "menn\u00e4", "lemmacomp": "menn\u00e4", "lex": "|menn\u00e4..vb.1|", "msd": "NUM_Sg|CASE_Lat|VOICE_Act|INF_Inf1", "ocr": "0.76", "pos": "V", "ref": "13", "word": "menn\u00e4" }, { "dephead": "13", "deprel": "nommod", "lemma": "maa", "lemmacomp": "maa", "lex": "|maa..nn.1|", "msd": "NUM_Sg|CASE_Abl", "ocr": "0.90", "pos": "N", "ref": "14", "word": "maalta" }, { "dephead": "13", "deprel": "ccomp", "lemma": "poics", "lemmacomp": "poics", "lex": "|poics..xx.1|", "msd": "OTHER_UNK", "ocr": "0.80", "pos": "Foreign", "ref": "15", "word": "poics" }, { "dephead": "2", "deprel": "punct", "lemma": ",", "lemmacomp": ",", "lex": "|,..xx.1|", "msd": "_", "ocr": "0.80", "pos": "Punct", "ref": "16", "word": "," }, { "dephead": "2", "deprel": "conj", "lemma": "takoa", "lemmacomp": "takoa", "lex": "|takoa..vb.1|", "msd": "NUM_Sg|CASE_Lat|VOICE_Act|INF_Inf1", "ocr": "0.81", "pos": "V", "ref": "17", "word": "takoa" }, { "dephead": "19", "deprel": "amod", "lemma": "kylm\u00e4", "lemmacomp": "kylm\u00e4", "lex": "|kylm\u00e4..jj.1|", "msd": "NUM_Sg|CASE_Par|CMP_Pos", "ocr": "0.88", "pos": "A", "ref": "18", "word": "kylm\u00e4\u00e4" }, { "dephead": "17", "deprel": "dobj", "lemma": "rauta", "lemmacomp": "rauta", "lex": "|rauta..nn.1|", "msd": "NUM_Sg|CASE_Par", "ocr": "0.84", "pos": "N", "ref": "19", "word": "rautaa" }, { "dephead": "2", "deprel": "punct", "lemma": ".", "lemmacomp": ".", "lex": "|...xx.1|", "msd": "_", "ocr": "0.84", "pos": "Punct", "ref": "20", "structs": { "close": [ "sentence", "paragraph" ] }, "word": "." } ] }, { "corpus": "KLK_FI_1839", "match": { "end": 3, "position": 7595, "start": 2 }, "structs": { "paragraph_id": "3", "sentence_id": "565", "sentence_local_id": "4", "sentence_parse_state": "parsed", "text_binding_id": "501266", "text_datefrom": "18390303", "text_dateto": "18390331", "text_elec_date": "2008-05-09", "text_img_url": "#DIRECTORY#fk01442_1839-03_3#SEPARATOR#00002.#EXTENSION#", "text_issue_date": "03.1839", "text_issue_no": "3", "text_issue_title": "MEHIL\u00c4INEN.", "text_label": "MEHIL\u00c4INEN. no. 3 03.1839", "text_language": "fi", "text_page_no": "2", "text_publ_id": "fk01442", "text_publ_title": "Mehil\u00e4inen", "text_publ_type": "aikakausi", "text_sentcount": "18", "text_tokencount": "233" }, "tokens": [ { "dephead": "2", "deprel": "nsubj", "lemma": "kulta", "lemmacomp": "kulta", "lex": "|kulta..nn.1|", "msd": "NUM_Sg|CASE_Nom|POSS_PxSg1|CASECHANGE_Up", "ocr": "0.94", "pos": "N", "ref": "1", "structs": { "open": [ "paragraph", "sentence" ] }, "word": "Kultani" }, { "dephead": "0", "deprel": "ROOT", "lemma": "k\u00e4ypi", "lemmacomp": "k\u00e4ypi", "lex": "|k\u00e4ypi..vb.1|", "msd": "PRS_Sg3|VOICE_Act|TENSE_Prt|MOOD_Ind|OTHER_UNK", "ocr": "0.96", "pos": "V", "ref": "2", "word": "k\u00e4ypi" }, { "dephead": "4", "deprel": "poss", "lemma": "Suomi", "lemmacomp": "Suomi", "lex": "|Suomi..nn.1|", "msd": "SUBCAT_Prop|NUM_Sg|CASE_Gen|CASECHANGE_Up", "ocr": "0.88", "pos": "N", "ref": "3", "word": "Suomen" }, { "dephead": "2", "deprel": "nommod", "lemma": "maa", "lemmacomp": "maa", "lex": "|maa..nn.1|", "msd": "NUM_Pl|CASE_Par", "ocr": "0.79", "pos": "N", "ref": "4", "word": "maita" }, { "dephead": "4", "deprel": "adpos", "lemma": "poikki", "lemmacomp": "poikki", "lex": "|poikki..pp.1|", "msd": "SUBCAT_Po", "ocr": "0.93", "pos": "Adp", "ref": "5", "word": "poikki" }, { "dephead": "5", "deprel": "cc", "lemma": "sek\u00e4", "lemmacomp": "sek\u00e4", "lex": "|sek\u00e4..kn.1|", "msd": "SUBCAT_CC", "ocr": "0.95", "pos": "C", "ref": "6", "word": "sek\u00e4" }, { "dephead": "5", "deprel": "conj", "lemma": "pitkin", "lemmacomp": "pitkin", "lex": "|pitkin..pp.1|", "msd": "SUBCAT_Po", "ocr": "0.78", "pos": "Adp", "ref": "7", "word": "pitkin" }, { "dephead": "2", "deprel": "punct", "lemma": ",", "lemmacomp": ",", "lex": "|,..xx.1|", "msd": "_", "ocr": "0.78", "pos": "Punct", "ref": "8", "word": "," }, { "dephead": "10", "deprel": "poss", "lemma": "kyl\u00e4", "lemmacomp": "kyl\u00e4", "lex": "|kyl\u00e4..nn.1|", "msd": "NUM_Sg|CASE_Gen|CASECHANGE_Up", "ocr": "0.76", "pos": "N", "ref": "9", "word": "Kyl\u00e4n" }, { "dephead": "11", "deprel": "nsubj", "lemma": "nainen", "lemmacomp": "nainen", "lex": "|nainen..nn.1|", "msd": "NUM_Pl|CASE_Nom", "ocr": "0.90", "pos": "N", "ref": "10", "word": "naiset" }, { "dephead": "2", "deprel": "conj", "lemma": "naUrowat", "lemmacomp": "naUrowat", "lex": "|naUrowat..vb.1|", "msd": "PRS_Pl3|VOICE_Act|TENSE_Prs|MOOD_Ind|OTHER_UNK", "ocr": "0.90", "pos": "V", "ref": "11", "word": "naUrowat" }, { "dephead": "11", "deprel": "cc", "lemma": "ja", "lemmacomp": "ja", "lex": "|ja..kn.1|", "msd": "SUBCAT_CC", "ocr": "0.78", "pos": "C", "ref": "12", "word": "ja" }, { "dephead": "15", "deprel": "nsubj", "lemma": "min\u00e4", "lemmacomp": "min\u00e4", "lex": "|min\u00e4..pn.1|", "msd": "SUBCAT_Pers|NUM_Sg|CASE_Nom", "ocr": "0.96", "pos": "Pron", "ref": "13", "word": "min\u00e4" }, { "dephead": "13", "deprel": "amod", "lemma": "raukka", "lemmacomp": "raukka", "lex": "|raukka..jj.1|", "msd": "NUM_Sg|CASE_Nom|CMP_Pos", "ocr": "0.95", "pos": "A", "ref": "14", "word": "raukka" }, { "dephead": "11", "deprel": "conj", "lemma": "itke\u00e4", "lemmacomp": "itke\u00e4", "lex": "|itke\u00e4..vb.1|", "msd": "PRS_Sg1|VOICE_Act|TENSE_Prt|MOOD_Ind", "ocr": "0.95", "pos": "V", "ref": "15", "word": "itkin" }, { "dephead": "2", "deprel": "punct", "lemma": ".", "lemmacomp": ".", "lex": "|...xx.1|", "msd": "_", "ocr": "0.95", "pos": "Punct", "ref": "16", "structs": { "close": [ "sentence", "paragraph" ] }, "word": "." } ] }, { "corpus": "KLK_FI_1839", "match": { "end": 4, "position": 16001, "start": 3 }, "structs": { "paragraph_id": "10", "sentence_id": "1106", "sentence_local_id": "11", "sentence_parse_state": "parsed", "text_binding_id": "501518", "text_datefrom": "18390505", "text_dateto": "18390531", "text_elec_date": "2008-05-09", "text_img_url": "#DIRECTORY#fk01442_1839-05_5#SEPARATOR#00001.#EXTENSION#", "text_issue_date": "05.1839", "text_issue_no": "5", "text_issue_title": "MEHIL\u00c4INEN.", "text_label": "MEHIL\u00c4INEN. no. 5 05.1839", "text_language": "fi", "text_page_no": "1", "text_publ_id": "fk01442", "text_publ_title": "Mehil\u00e4inen", "text_publ_type": "aikakausi", "text_sentcount": "12", "text_tokencount": "101" }, "tokens": [ { "dephead": "6", "deprel": "nommod", "lemma": "15", "lemmacomp": "15", "lex": "|15..rg.1|", "msd": "_", "ocr": "0.46", "pos": "Num", "ref": "1", "structs": { "open": [ "paragraph", "sentence" ] }, "word": "15" }, { "dephead": "5", "deprel": "advmod", "lemma": "heti", "lemmacomp": "heti", "lex": "|heti..ab.1|", "msd": "CASECHANGE_Up", "ocr": "0.83", "pos": "Adv", "ref": "2", "word": "Heti" }, { "dephead": "5", "deprel": "nn", "lemma": "kohta", "lemmacomp": "kohta", "lex": "|kohta..nn.1|", "msd": "NUM_Sg|CASE_Nom", "ocr": "0.93", "pos": "N", "ref": "3", "word": "kohta" }, { "dephead": "5", "deprel": "poss", "lemma": "Suomi", "lemmacomp": "Suomi", "lex": "|Suomi..nn.1|", "msd": "SUBCAT_Prop|NUM_Sg|CASE_Gen|CASECHANGE_Up", "ocr": "0.95", "pos": "N", "ref": "4", "word": "Suomen" }, { "dephead": "6", "deprel": "nsubj", "lemma": "herra", "lemmacomp": "herra", "lex": "|herra..nn.1|", "msd": "NUM_Pl|CASE_Nom", "ocr": "0.81", "pos": "N", "ref": "5", "word": "herrat" }, { "dephead": "0", "deprel": "ROOT", "lemma": "Tunsnvat", "lemmacomp": "Tunsnvat", "lex": "|Tunsnvat..vb.1|", "msd": "PRS_Pl3|VOICE_Act|TENSE_Prs|MOOD_Ind|CASECHANGE_Up|OTHER_UNK", "ocr": "0.90", "pos": "V", "ref": "6", "word": "Tunsnvat" }, { "dephead": "8", "deprel": "det", "lemma": "t\u00e4m\u00e4", "lemmacomp": "t\u00e4m\u00e4", "lex": "|t\u00e4m\u00e4..pn.1|", "msd": "SUBCAT_Dem|NUM_Sg|CASE_Gen", "ocr": "0.95", "pos": "Pron", "ref": "7", "word": "t\u00e4m\u00e4n" }, { "dephead": "6", "deprel": "nommod", "lemma": "hyw\u00e4ksi", "lemmacomp": "hyw\u00e4ksi", "lex": "|hyw\u00e4ksi..nn.1|", "msd": "NUM_Sg|CASE_Tra|OTHER_UNK", "ocr": "0.92", "pos": "N", "ref": "8", "word": "hyw\u00e4ksi" }, { "dephead": "13", "deprel": "punct", "lemma": ",", "lemmacomp": ",", "lex": "|,..xx.1|", "msd": "_", "ocr": "0.92", "pos": "Punct", "ref": "9", "word": "," }, { "dephead": "13", "deprel": "rel", "lemma": "joka", "lemmacomp": "joka", "lex": "|joka..pn.1|", "msd": "SUBCAT_Rel|NUM_Sg|CASE_Gen|CASECHANGE_Up", "ocr": "0.89", "pos": "Pron", "ref": "10", "word": "Jonka" }, { "dephead": "13", "deprel": "advmod", "lemma": "itse", "lemmacomp": "itse", "lex": "|itse..ab.1|", "msd": "_", "ocr": "0.89", "pos": "Adv", "ref": "11", "word": "itse" }, { "dephead": "13", "deprel": "nsubj", "lemma": "luoja", "lemmacomp": "luoja", "lex": "|luoja..nn.1|", "msd": "NUM_Sg|CASE_Nom", "ocr": "0.86", "pos": "N", "ref": "12", "word": "luoja" }, { "dephead": "8", "deprel": "rcmod", "lemma": "laitti", "lemmacomp": "laitti", "lex": "|laitti..vb.1|", "msd": "PRS_Sg3|VOICE_Act|TENSE_Prt|MOOD_Ind|OTHER_UNK", "ocr": "0.97", "pos": "V", "ref": "13", "word": "laitti" }, { "dephead": "13", "deprel": "punct", "lemma": ",", "lemmacomp": ",", "lex": "|,..xx.1|", "msd": "_", "ocr": "0.97", "pos": "Punct", "ref": "14", "word": "," }, { "dephead": "16", "deprel": "det", "lemma": "se", "lemmacomp": "se", "lex": "|se..pn.1|", "msd": "SUBCAT_Dem|NUM_Sg|CASE_All|CASECHANGE_Up", "ocr": "0.86", "pos": "Pron", "ref": "15", "word": "Sille" }, { "dephead": "17", "deprel": "nommod", "lemma": "saaylle", "lemmacomp": "saaylle", "lex": "|saaylle..nn.1|", "msd": "NUM_Sg|CASE_All|OTHER_UNK", "ocr": "0.94", "pos": "N", "ref": "16", "word": "saaylle" }, { "dephead": "13", "deprel": "conj", "lemma": "sowitti", "lemmacomp": "sowitti", "lex": "|sowitti..vb.1|", "msd": "PRS_Sg3|VOICE_Act|TENSE_Prt|MOOD_Ind|OTHER_UNK", "ocr": "0.96", "pos": "V", "ref": "17", "word": "sowitti" }, { "dephead": "6", "deprel": "punct", "lemma": ",", "lemmacomp": ",", "lex": "|,..xx.1|", "msd": "_", "ocr": "0.96", "pos": "Punct", "ref": "18", "word": "," }, { "dephead": "21", "deprel": "nsubj", "lemma": "loll'", "lemmacomp": "loll'", "lex": "|loll'..nn.1|", "msd": "NUM_Sg|CASE_Nom|OTHER_UNK", "ocr": "0.90", "pos": "N", "ref": "19", "word": "loll'" }, { "dephead": "21", "deprel": "cop", "lemma": "olla", "lemmacomp": "olla", "lex": "|olla..vb.1|", "msd": "PRS_Sg3|VOICE_Act|TENSE_Prs|MOOD_Ind", "ocr": "0.93", "pos": "V", "ref": "20", "word": "on" }, { "dephead": "6", "deprel": "conj", "lemma": "oppia", "lemmacomp": "oppia", "lex": "|oppia..vb.1|", "msd": "NUM_Sg|CASE_Lat|VOICE_Act|INF_Inf1", "ocr": "0.92", "pos": "V", "ref": "21", "word": "oppia" }, { "dephead": "21", "deprel": "nommod", "lemma": "otsa", "lemmacomp": "otsa", "lex": "|otsa..nn.1|", "msd": "NUM_Sg|CASE_Ine", "ocr": "0.83", "pos": "N", "ref": "22", "word": "otsassa" }, { "dephead": "6", "deprel": "punct", "lemma": ",", "lemmacomp": ",", "lex": "|,..xx.1|", "msd": "_", "ocr": "0.83", "pos": "Punct", "ref": "23", "structs": { "close": [ "sentence", "paragraph" ] }, "word": "," } ] }, { "corpus": "KLK_FI_1839", "match": { "end": 17, "position": 19425, "start": 16 }, "structs": { "paragraph_id": "5", "sentence_id": "1440", "sentence_local_id": "5", "sentence_parse_state": "parsed", "text_binding_id": "502540", "text_datefrom": "18390606", "text_dateto": "18390630", "text_elec_date": "2008-05-09", "text_img_url": "#DIRECTORY#fk01442_1839-06_6#SEPARATOR#00006.#EXTENSION#", "text_issue_date": "06.1839", "text_issue_no": "6", "text_issue_title": "MEHIL\u00c4INEN.", "text_label": "MEHIL\u00c4INEN. no. 6 06.1839", "text_language": "fi", "text_page_no": "6", "text_publ_id": "fk01442", "text_publ_title": "Mehil\u00e4inen", "text_publ_type": "aikakausi", "text_sentcount": "20", "text_tokencount": "234" }, "tokens": [ { "dephead": "9", "deprel": "poss", "lemma": "min\u00e4", "lemmacomp": "min\u00e4", "lex": "|min\u00e4..pn.1|", "msd": "SUBCAT_Pers|NUM_Sg|CASE_Gen|CASECHANGE_Up", "ocr": "0.97", "pos": "Pron", "ref": "1", "structs": { "open": [ "paragraph", "sentence" ] }, "word": "Minun" }, { "dephead": "3", "deprel": "poss", "lemma": "kulta", "lemmacomp": "kulta", "lex": "|kulta..nn.1|", "msd": "NUM_Sg|CASE_Gen|POSS_PxSg1", "ocr": "0.98", "pos": "N", "ref": "2", "word": "kultani" }, { "dephead": "9", "deprel": "nsubj-cop", "lemma": "walkia", "lemmacomp": "walkia", "lex": "|walkia..nn.1|", "msd": "NUM_Pl|CASE_Par|OTHER_UNK", "ocr": "0.98", "pos": "N", "ref": "3", "word": "walkia" }, { "dephead": "9", "deprel": "cop", "lemma": "olla", "lemmacomp": "olla", "lex": "|olla..vb.1|", "msd": "PRS_Sg3|VOICE_Act|TENSE_Prs|MOOD_Ind", "ocr": "0.89", "pos": "V", "ref": "4", "word": "on" }, { "dephead": "9", "deprel": "punct", "lemma": ",", "lemmacomp": ",", "lex": "|,..xx.1|", "msd": "_", "ocr": "0.89", "pos": "Punct", "ref": "5", "word": "," }, { "dephead": "11", "deprel": "cop", "lemma": "olla", "lemmacomp": "olla", "lex": "|olla..vb.1|", "msd": "PRS_Sg3|VOICE_Act|TENSE_Prs|MOOD_Ind", "ocr": "0.93", "pos": "V", "ref": "6", "word": "on" }, { "dephead": "9", "deprel": "mark", "lemma": "kun", "lemmacomp": "kun", "lex": "|kun..kn.1|", "msd": "SUBCAT_CS", "ocr": "0.91", "pos": "C", "ref": "7", "word": "kun" }, { "dephead": "9", "deprel": "poss", "lemma": "lumi", "lemmacomp": "lumi", "lex": "|lumi..nn.1|", "msd": "NUM_Sg|CASE_Gen", "ocr": "0.98", "pos": "N", "ref": "8", "word": "lumen" }, { "dephead": "18", "deprel": "nsubj-cop", "lemma": "walo", "lemmacomp": "walo", "lex": "|walo..nn.1|", "msd": "NUM_Sg|CASE_Nom|OTHER_UNK", "ocr": "0.96", "pos": "N", "ref": "9", "word": "walo" }, { "dephead": "9", "deprel": "punct", "lemma": ",", "lemmacomp": ",", "lex": "|,..xx.1|", "msd": "_", "ocr": "0.96", "pos": "Punct", "ref": "10", "word": "," }, { "dephead": "9", "deprel": "conj", "lemma": "hyv\u00e4", "lemmacomp": "hyv\u00e4", "lex": "|hyv\u00e4..jj.1|", "msd": "NUM_Sg|CASE_Nom|CMP_Comp|CASECHANGE_Up", "ocr": "0.95", "pos": "A", "ref": "11", "word": "Parempi" }, { "dephead": "18", "deprel": "cop", "lemma": "olla", "lemmacomp": "olla", "lex": "|olla..vb.1|", "msd": "PRS_Sg3|VOICE_Act|TENSE_Prs|MOOD_Ind", "ocr": "1.00", "pos": "V", "ref": "12", "word": "on" }, { "dephead": "18", "deprel": "nommod", "lemma": "mieli", "lemmacomp": "mieli", "lex": "|mieli..nn.1|", "msd": "NUM_Sg|CASE_Ela|POSS_PxSg1", "ocr": "0.96", "pos": "N", "ref": "13", "word": "mielest\u00e4ni" }, { "dephead": "18", "deprel": "punct", "lemma": ",", "lemmacomp": ",", "lex": "|,..xx.1|", "msd": "_", "ocr": "0.96", "pos": "Punct", "ref": "14", "word": "," }, { "dephead": "18", "deprel": "mark", "lemma": "kun", "lemmacomp": "kun", "lex": "|kun..kn.1|", "msd": "SUBCAT_CS", "ocr": "1.00", "pos": "C", "ref": "15", "word": "kun" }, { "dephead": "18", "deprel": "amod", "lemma": "hyv\u00e4", "lemmacomp": "hyv\u00e4", "lex": "|hyv\u00e4..jj.1|", "msd": "NUM_Sg|CASE_Nom|CMP_Superl", "ocr": "0.95", "pos": "A", "ref": "16", "word": "paras" }, { "dephead": "18", "deprel": "name", "lemma": "Suomi", "lemmacomp": "Suomi", "lex": "|Suomi..nn.1|", "msd": "SUBCAT_Prop|NUM_Sg|CASE_Gen|CASECHANGE_Up", "ocr": "0.96", "pos": "N", "ref": "17", "word": "Suomen" }, { "dephead": "0", "deprel": "ROOT", "lemma": "talo", "lemmacomp": "talo", "lex": "|talo..nn.1|", "msd": "NUM_Sg|CASE_Nom", "ocr": "0.99", "pos": "N", "ref": "18", "word": "talo" }, { "dephead": "18", "deprel": "punct", "lemma": ".", "lemmacomp": ".", "lex": "|...xx.1|", "msd": "_", "ocr": "0.99", "pos": "Punct", "ref": "19", "structs": { "close": [ "sentence", "paragraph" ] }, "word": "." } ] }, { "corpus": "KLK_FI_1839", "match": { "end": 10, "position": 27410, "start": 9 }, "structs": { "paragraph_id": "3", "sentence_id": "2078", "sentence_local_id": "9", "sentence_parse_state": "parsed", "text_binding_id": "499810", "text_datefrom": "18390808", "text_dateto": "18390831", "text_elec_date": "2008-05-09", "text_img_url": "#DIRECTORY#fk01442_1839-08_8#SEPARATOR#00010.#EXTENSION#", "text_issue_date": "08.1839", "text_issue_no": "8", "text_issue_title": "MEHIL\u00c4INEN.", "text_label": "MEHIL\u00c4INEN. no. 8 08.1839", "text_language": "fi", "text_page_no": "10", "text_publ_id": "fk01442", "text_publ_title": "Mehil\u00e4inen", "text_publ_type": "aikakausi", "text_sentcount": "14", "text_tokencount": "187" }, "tokens": [ { "dephead": "2", "deprel": "det", "lemma": "mik\u00e4", "lemmacomp": "mik\u00e4", "lex": "|mik\u00e4..pn.1|", "msd": "SUBCAT_Rel|NUM_Sg|CASE_Nom|CASECHANGE_Up", "ocr": "0.97", "pos": "Pron", "ref": "1", "structs": { "open": [ "paragraph", "sentence" ] }, "word": "Mik\u00e4" }, { "dephead": "0", "deprel": "ROOT", "lemma": "pouke", "lemmacomp": "pouke", "lex": "|pouke..nn.1|", "msd": "NUM_Sg|CASE_Nom|OTHER_UNK", "ocr": "0.97", "pos": "N", "ref": "2", "word": "pouke" }, { "dephead": "2", "deprel": "nommod", "lemma": "Borgoassa", "lemmacomp": "Borgoassa", "lex": "|Borgoassa..nn.1|", "msd": "SUBCAT_Prop|NUM_Sg|CASE_Ine|CASECHANGE_Up|OTHER_UNK", "ocr": "0.97", "pos": "N", "ref": "3", "word": "Borgoassa" }, { "dephead": "2", "deprel": "punct", "lemma": ",", "lemmacomp": ",", "lex": "|,..xx.1|", "msd": "_", "ocr": "0.97", "pos": "Punct", "ref": "4", "word": "," }, { "dephead": "6", "deprel": "punct", "lemma": ",", "lemmacomp": ",", "lex": "|,..xx.1|", "msd": "_", "ocr": "0.97", "pos": "Punct", "ref": "5", "word": "," }, { "dephead": "2", "deprel": "conj", "lemma": "melu", "lemmacomp": "melu", "lex": "|melu..nn.1|", "msd": "NUM_Sg|CASE_Nom|CASECHANGE_Up", "ocr": "0.95", "pos": "N", "ref": "6", "word": "Melu" }, { "dephead": "6", "deprel": "nommod", "lemma": "merikaupunki", "lemmacomp": "meri|kaupunki", "lex": "|merikaupunki..nn.1|", "msd": "NUM_Sg|CASE_Ine", "ocr": "0.96", "pos": "N", "ref": "7", "word": "merikaupungissa" }, { "dephead": "2", "deprel": "punct", "lemma": ",", "lemmacomp": ",", "lex": "|,..xx.1|", "msd": "_", "ocr": "0.96", "pos": "Punct", "ref": "8", "word": "," }, { "dephead": "2", "deprel": "conj", "lemma": "suru", "lemmacomp": "suru", "lex": "|suru..nn.1|", "msd": "NUM_Sg|CASE_Nom|CASECHANGE_Up", "ocr": "0.93", "pos": "N", "ref": "9", "word": "Suru" }, { "dephead": "11", "deprel": "poss", "lemma": "Suomi", "lemmacomp": "Suomi", "lex": "|Suomi..nn.1|", "msd": "SUBCAT_Prop|NUM_Sg|CASE_Gen|CASECHANGE_Up", "ocr": "0.97", "pos": "N", "ref": "10", "word": "Suomen" }, { "dephead": "9", "deprel": "nommod", "lemma": "rannikko", "lemmacomp": "rannikko", "lex": "|rannikko..nn.1|", "msd": "NUM_Pl|CASE_Ade", "ocr": "0.96", "pos": "N", "ref": "11", "word": "rannikoilla" }, { "dephead": "2", "deprel": "punct", "lemma": "?", "lemmacomp": "?", "lex": "|?..xx.1|", "msd": "_", "ocr": "0.96", "pos": "Punct", "ref": "12", "structs": { "close": [ "sentence" ] }, "word": "?" } ] }, { "corpus": "KLK_FI_1839", "match": { "end": 8, "position": 35969, "start": 7 }, "structs": { "paragraph_id": "1", "sentence_id": "2691", "sentence_local_id": "1", "sentence_parse_state": "parsed", "text_binding_id": "500383", "text_datefrom": "18391010", "text_dateto": "18391031", "text_elec_date": "2008-05-09", "text_img_url": "#DIRECTORY#fk01442_1839-10_10#SEPARATOR#00012.#EXTENSION#", "text_issue_date": "10.1839", "text_issue_no": "10", "text_issue_title": "MEHIL\u00c4INEN.", "text_label": "MEHIL\u00c4INEN. no. 10 10.1839", "text_language": "fi", "text_page_no": "12", "text_publ_id": "fk01442", "text_publ_title": "Mehil\u00e4inen", "text_publ_type": "aikakausi", "text_sentcount": "12", "text_tokencount": "319" }, "tokens": [ { "dephead": "0", "deprel": "ROOT", "lemma": "alkaa", "lemmacomp": "alkaa", "lex": "|alkaa..vb.1|", "msd": "PRS_Sg1|VOICE_Act|TENSE_Prs|MOOD_Ind", "ocr": "0.98", "pos": "V", "ref": "1", "structs": { "open": [ "paragraph", "sentence" ] }, "word": "alan" }, { "dephead": "3", "deprel": "advmod", "lemma": "suorastaan", "lemmacomp": "suo|rastaan", "lex": "|suorastaan..ab.1|", "msd": "_", "ocr": "0.94", "pos": "Adv", "ref": "2", "word": "suorastaan" }, { "dephead": "1", "deprel": "xcomp", "lemma": "selwitclla", "lemmacomp": "selwitclla", "lex": "|selwitclla..vb.1|", "msd": "NUM_Sg|CASE_Lat|VOICE_Act|INF_Inf1|OTHER_UNK", "ocr": "0.89", "pos": "V", "ref": "3", "word": "selwitclla" }, { "dephead": "3", "deprel": "dobj", "lemma": "syy", "lemmacomp": "syy", "lex": "|syy..nn.1|", "msd": "NUM_Pl|CASE_Par", "ocr": "0.95", "pos": "N", "ref": "4", "word": "syit\u00e4" }, { "dephead": "6", "deprel": "advmod", "lemma": "wah\u00e4n", "lemmacomp": "wah\u00e4n", "lex": "|wah\u00e4n..ab.1|", "msd": "OTHER_UNK", "ocr": "0.79", "pos": "Adv", "ref": "5", "word": "wah\u00e4n" }, { "dephead": "3", "deprel": "advcl", "lemma": "muistaa", "lemmacomp": "muistaa", "lex": "|muistaa..vb.1|", "msd": "TENSE_Prs|MOOD_Ind|NEG_ConNeg", "ocr": "0.96", "pos": "V", "ref": "6", "word": "muista" }, { "dephead": "9", "deprel": "amod", "lemma": "critapaseen", "lemmacomp": "critapaseen", "lex": "|critapaseen..jj.1|", "msd": "NUM_Sg|CASE_Ill|CMP_Pos|OTHER_UNK", "ocr": "0.90", "pos": "A", "ref": "7", "word": "critapaseen" }, { "dephead": "9", "deprel": "poss", "lemma": "Suomi", "lemmacomp": "Suomi", "lex": "|Suomi..nn.1|", "msd": "SUBCAT_Prop|NUM_Sg|CASE_Gen|CASECHANGE_Up", "ocr": "0.96", "pos": "N", "ref": "8", "word": "Suomen" }, { "dephead": "6", "deprel": "nommod", "lemma": "kirjotuslaatuuni", "lemmacomp": "kirjotuslaatuuni", "lex": "|kirjotuslaatuuni..nn.1|", "msd": "NUM_Sg|CASE_Ill|OTHER_UNK", "ocr": "0.92", "pos": "N", "ref": "9", "word": "kirjotuslaatuuni" }, { "dephead": "14", "deprel": "punct", "lemma": ",", "lemmacomp": ",", "lex": "|,..xx.1|", "msd": "_", "ocr": "0.92", "pos": "Punct", "ref": "10", "word": "," }, { "dephead": "14", "deprel": "rel", "lemma": "joka", "lemmacomp": "joka", "lex": "|joka..pn.1|", "msd": "SUBCAT_Rel|NUM_Sg|CASE_Ela", "ocr": "0.75", "pos": "Pron", "ref": "11", "word": "josta" }, { "dephead": "13", "deprel": "partmod", "lemma": "mainita", "lemmacomp": "mainita", "lex": "|mainita..vb.1|", "msd": "NUM_Sg|CASE_Ine|VOICE_Pass|PCP_PrfPrc|CMP_Pos", "ocr": "0.91", "pos": "V", "ref": "12", "word": "mainitussa" }, { "dephead": "14", "deprel": "nommod", "lemma": "kirja", "lemmacomp": "kirja", "lex": "|kirja..nn.1|", "msd": "NUM_Sg|CASE_Ine|POSS_PxSg2", "ocr": "0.78", "pos": "N", "ref": "13", "word": "kirjassasi" }, { "dephead": "9", "deprel": "rcmod", "lemma": "mainita", "lemmacomp": "mainita", "lex": "|mainita..vb.1|", "msd": "PRS_Sg2|VOICE_Act|TENSE_Prs|MOOD_Ind", "ocr": "0.95", "pos": "V", "ref": "14", "word": "mainitset" }, { "dephead": "1", "deprel": "punct", "lemma": ".", "lemmacomp": ".", "lex": "|...xx.1|", "msd": "_", "ocr": "0.95", "pos": "Punct", "ref": "15", "structs": { "close": [ "sentence", "paragraph" ] }, "word": "." } ] }, { "corpus": "KLK_FI_1839", "match": { "end": 19, "position": 37447, "start": 18 }, "structs": { "paragraph_id": "1", "sentence_id": "2742", "sentence_local_id": "8", "sentence_parse_state": "parsed", "text_binding_id": "500383", "text_datefrom": "18391010", "text_dateto": "18391031", "text_elec_date": "2008-05-09", "text_img_url": "#DIRECTORY#fk01442_1839-10_10#SEPARATOR#00016.#EXTENSION#", "text_issue_date": "10.1839", "text_issue_no": "10", "text_issue_title": "MEHIL\u00c4INEN.", "text_label": "MEHIL\u00c4INEN. no. 10 10.1839", "text_language": "fi", "text_page_no": "16", "text_publ_id": "fk01442", "text_publ_title": "Mehil\u00e4inen", "text_publ_type": "aikakausi", "text_sentcount": "12", "text_tokencount": "286" }, "tokens": [ { "dephead": "2", "deprel": "name", "lemma": "Warren", "lemmacomp": "Warren", "lex": "|Warren..nn.1|", "msd": "SUBCAT_Prop|CASECHANGE_Up|OTHER_UNK", "ocr": "0.90", "pos": "N", "ref": "1", "structs": { "open": [ "sentence" ] }, "word": "Warren" }, { "dephead": "4", "deprel": "nsubj-cop", "lemma": "olemma", "lemmacomp": "olemma", "lex": "|olemma..nn.1|", "msd": "NUM_Sg|CASE_Nom|OTHER_UNK", "ocr": "0.94", "pos": "N", "ref": "2", "word": "olemma" }, { "dephead": "4", "deprel": "advmod", "lemma": "miten", "lemmacomp": "miten", "lex": "|miten..ab.1|", "msd": "_", "ocr": "0.95", "pos": "Adv", "ref": "3", "word": "miten" }, { "dephead": "18", "deprel": "amod", "lemma": "mahdollinen", "lemmacomp": "mahdollinen", "lex": "|mahdollinen..jj.1|", "msd": "NUM_Sg|CASE_Nom|CMP_Pos", "ocr": "0.94", "pos": "A", "ref": "4", "word": "mahdollinen" }, { "dephead": "6", "deprel": "nommod", "lemma": "sisall\u00e4nsa", "lemmacomp": "sisall\u00e4nsa", "lex": "|sisall\u00e4nsa..nn.1|", "msd": "SUBCAT_Prop|NUM_Sg|CASE_Ine|OTHER_UNK", "ocr": "0.92", "pos": "N", "ref": "5", "word": "sisall\u00e4nsa" }, { "dephead": "18", "deprel": "partmod", "lemma": "pit\u00e4\u00e4", "lemmacomp": "pit\u00e4\u00e4", "lex": "|pit\u00e4\u00e4..vb.1|", "msd": "NUM_Pl|CASE_Nom|VOICE_Act|PCP_PrfPrc|CMP_Pos", "ocr": "0.90", "pos": "V", "ref": "6", "word": "pit\u00e4neet" }, { "dephead": "6", "deprel": "punct", "lemma": ",", "lemmacomp": ",", "lex": "|,..xx.1|", "msd": "_", "ocr": "0.90", "pos": "Punct", "ref": "7", "word": "," }, { "dephead": "9", "deprel": "amod", "lemma": "waan", "lemmacomp": "waan", "lex": "|waan..jj.1|", "msd": "NUM_Sg|CASE_Gen|CMP_Pos|OTHER_UNK", "ocr": "1.00", "pos": "A", "ref": "8", "word": "waan" }, { "dephead": "18", "deprel": "poss", "lemma": "p\u00e4\u00e4te", "lemmacomp": "p\u00e4\u00e4te", "lex": "|p\u00e4\u00e4te..nn.1|", "msd": "NUM_Sg|CASE_Gen", "ocr": "0.83", "pos": "N", "ref": "9", "word": "p\u00e4\u00e4tteen" }, { "dephead": "14", "deprel": "punct", "lemma": ",", "lemmacomp": ",", "lex": "|,..xx.1|", "msd": "_", "ocr": "0.83", "pos": "Punct", "ref": "10", "word": "," }, { "dephead": "14", "deprel": "rel", "lemma": "joka", "lemmacomp": "joka", "lex": "|joka..pn.1|", "msd": "SUBCAT_Rel|NUM_Sg|CASE_Nom", "ocr": "0.94", "pos": "Pron", "ref": "11", "word": "joka" }, { "dephead": "24", "deprel": "nommod", "lemma": "alkukieli", "lemmacomp": "alku|kieli", "lex": "|alkukieli..nn.1|", "msd": "NUM_Pl|CASE_Ine|POSS_Px3", "ocr": "0.94", "pos": "N", "ref": "12", "word": "alkukieliss\u00e4ns\u00e4" }, { "dephead": "14", "deprel": "cop", "lemma": "olla", "lemmacomp": "olla", "lex": "|olla..vb.1|", "msd": "PRS_Sg3|VOICE_Act|TENSE_Prt|MOOD_Ind", "ocr": "0.91", "pos": "V", "ref": "13", "word": "oli" }, { "dephead": "9", "deprel": "rcmod", "lemma": "Greikalainen", "lemmacomp": "Greikalainen", "lex": "|Greikalainen..jj.1|", "msd": "NUM_Sg|CASE_Nom|CMP_Pos|CASECHANGE_Up|OTHER_UNK", "ocr": "0.94", "pos": "A", "ref": "14", "word": "Greikalainen" }, { "dephead": "14", "deprel": "cc", "lemma": "eli", "lemmacomp": "eli", "lex": "|eli..kn.1|", "msd": "SUBCAT_CC", "ocr": "0.95", "pos": "C", "ref": "15", "word": "eli" }, { "dephead": "14", "deprel": "conj", "lemma": "latinalainen", "lemmacomp": "latinalainen", "lex": "|latinalainen..jj.1|", "msd": "NUM_Sg|CASE_Nom|CMP_Pos|CASECHANGE_Up", "ocr": "0.95", "pos": "A", "ref": "16", "word": "Latinalainen" }, { "dephead": "14", "deprel": "punct", "lemma": ",", "lemmacomp": ",", "lex": "|,..xx.1|", "msd": "_", "ocr": "0.95", "pos": "Punct", "ref": "17", "word": "," }, { "dephead": "24", "deprel": "nsubj", "lemma": "olemma", "lemmacomp": "olemma", "lex": "|olemma..nn.1|", "msd": "NUM_Sg|CASE_Nom|OTHER_UNK", "ocr": "0.94", "pos": "N", "ref": "18", "word": "olemma" }, { "dephead": "20", "deprel": "poss", "lemma": "Suomi", "lemmacomp": "Suomi", "lex": "|Suomi..nn.1|", "msd": "SUBCAT_Prop|NUM_Sg|CASE_Gen|CASECHANGE_Up", "ocr": "0.91", "pos": "N", "ref": "19", "word": "Suomen" }, { "dephead": "21", "deprel": "nommod", "lemma": "lielessa", "lemmacomp": "lielessa", "lex": "|lielessa..nn.1|", "msd": "NUM_Sg|CASE_Ine|OTHER_UNK", "ocr": "0.89", "pos": "N", "ref": "20", "word": "lielessa" }, { "dephead": "18", "deprel": "partmod", "lemma": "tehd\u00e4", "lemmacomp": "tehd\u00e4", "lex": "|tehd\u00e4..vb.1|", "msd": "NUM_Pl|CASE_Nom|VOICE_Act|PCP_PrfPrc|CMP_Pos", "ocr": "0.75", "pos": "V", "ref": "21", "word": "tehneet" }, { "dephead": "21", "deprel": "acomp", "lemma": "suomalainen", "lemmacomp": "suomalainen", "lex": "|suomalainen..jj.1|", "msd": "NUM_Sg|CASE_Tra|CMP_Pos|CASECHANGE_Up", "ocr": "0.97", "pos": "A", "ref": "22", "word": "Suomalaiseksi" }, { "dephead": "21", "deprel": "punct", "lemma": ",", "lemmacomp": ",", "lex": "|,..xx.1|", "msd": "_", "ocr": "0.97", "pos": "Punct", "ref": "23", "word": "," }, { "dephead": "0", "deprel": "ROOT", "lemma": "kuitenki", "lemmacomp": "kuitenki", "lex": "|kuitenki..vb.1|", "msd": "PRS_Sg3|VOICE_Act|TENSE_Prt|MOOD_Ind|OTHER_UNK", "ocr": "0.99", "pos": "V", "ref": "24", "word": "kuitenki" }, { "dephead": "24", "deprel": "advmod", "lemma": "aina", "lemmacomp": "aina", "lex": "|aina..ab.1|", "msd": "_", "ocr": "0.98", "pos": "Adv", "ref": "25", "word": "aina" }, { "dephead": "28", "deprel": "advmod", "lemma": "niin", "lemmacomp": "niin", "lex": "|niin..ab.1|", "msd": "_", "ocr": "0.93", "pos": "Adv", "ref": "26", "word": "niin" }, { "dephead": "28", "deprel": "advmod", "lemma": "likipitain", "lemmacomp": "likipitain", "lex": "|likipitain..ab.1|", "msd": "OTHER_UNK", "ocr": "0.93", "pos": "Adv", "ref": "27", "word": "likipitain" }, { "dephead": "29", "deprel": "amod", "lemma": "alkukielinen", "lemmacomp": "alku|kielinen", "lex": "|alkukielinen..jj.1|", "msd": "NUM_Sg|CASE_Par|CMP_Pos", "ocr": "0.93", "pos": "A", "ref": "28", "word": "alkukielist\u00e4" }, { "dephead": "24", "deprel": "dobj", "lemma": "p\u00e4\u00e4te", "lemmacomp": "p\u00e4\u00e4te", "lex": "|p\u00e4\u00e4te..nn.1|", "msd": "NUM_Sg|CASE_Par", "ocr": "0.99", "pos": "N", "ref": "29", "word": "p\u00e4\u00e4tett\u00e4" }, { "dephead": "34", "deprel": "punct", "lemma": ",", "lemmacomp": ",", "lex": "|,..xx.1|", "msd": "_", "ocr": "0.99", "pos": "Punct", "ref": "30", "word": "," }, { "dephead": "34", "deprel": "mark", "lemma": "kun", "lemmacomp": "kun", "lex": "|kun..kn.1|", "msd": "SUBCAT_CS", "ocr": "0.96", "pos": "C", "ref": "31", "word": "kun" }, { "dephead": "34", "deprel": "amod", "lemma": "mahdollinen", "lemmacomp": "mahdollinen", "lex": "|mahdollinen..jj.1|", "msd": "NUM_Sg|CASE_Nom|CMP_Pos", "ocr": "0.95", "pos": "A", "ref": "32", "word": "mahdollinen" }, { "dephead": "24", "deprel": "punct", "lemma": ".", "lemmacomp": ".", "lex": "|...xx.1|", "msd": "_", "ocr": "0.95", "pos": "Punct", "ref": "33", "word": "." }, { "dephead": "29", "deprel": "appos", "lemma": "toiste", "lemmacomp": "toiste", "lex": "|toiste..nn.1|", "msd": "NUM_Sg|CASE_Nom", "ocr": "0.85", "pos": "N", "ref": "34", "word": "toiste" }, { "dephead": "34", "deprel": "punct", "lemma": ".", "lemmacomp": ".", "lex": "|...xx.1|", "msd": "_", "ocr": "0.85", "pos": "Punct", "ref": "35", "word": "." }, { "dephead": "34", "deprel": "punct", "lemma": ")", "lemmacomp": ")", "lex": "|)..xx.1|", "msd": "_", "ocr": "0.85", "pos": "Punct", "ref": "36", "structs": { "close": [ "sentence", "paragraph" ] }, "word": ")" } ] }, { "corpus": "KLK_FI_1839", "match": { "end": 9, "position": 38232, "start": 8 }, "structs": { "paragraph_id": "4", "sentence_id": "2778", "sentence_local_id": "5", "sentence_parse_state": "parsed", "text_binding_id": "502212", "text_datefrom": "18391111", "text_dateto": "18391130", "text_elec_date": "2008-05-09", "text_img_url": "#DIRECTORY#fk01442_1839-11_11#SEPARATOR#00003.#EXTENSION#", "text_issue_date": "11.1839", "text_issue_no": "11", "text_issue_title": "MEHIL\u00c4INEN.", "text_label": "MEHIL\u00c4INEN. no. 11 11.1839", "text_language": "fi", "text_page_no": "3", "text_publ_id": "fk01442", "text_publ_title": "Mehil\u00e4inen", "text_publ_type": "aikakausi", "text_sentcount": "15", "text_tokencount": "241" }, "tokens": [ { "dephead": "2", "deprel": "name", "lemma": "H.", "lemmacomp": "H.", "lex": "|H...nn.1|", "msd": "SUBCAT_Prop|CASECHANGE_Up|OTHER_UNK", "ocr": "0.94", "pos": "N", "ref": "1", "structs": { "open": [ "paragraph", "sentence" ] }, "word": "H." }, { "dephead": "3", "deprel": "name", "lemma": "W.", "lemmacomp": "W.", "lex": "|W...nn.1|", "msd": "SUBCAT_Prop|CASECHANGE_Up|OTHER_UNK", "ocr": "0.93", "pos": "N", "ref": "2", "word": "W." }, { "dephead": "4", "deprel": "nommod", "lemma": "t\u00e4m\u00e4", "lemmacomp": "t\u00e4m\u00e4", "lex": "|t\u00e4m\u00e4..pn.1|", "msd": "SUBCAT_Dem|NUM_Sg|CASE_Ine|CASECHANGE_Up", "ocr": "0.92", "pos": "Pron", "ref": "3", "word": "T\u00e4ss\u00e4" }, { "dephead": "0", "deprel": "ROOT", "lemma": "l\u00e4hett\u00e4\u00e4", "lemmacomp": "l\u00e4hett\u00e4\u00e4", "lex": "|l\u00e4hett\u00e4\u00e4..vb.1|", "msd": "PRS_Sg1|VOICE_Act|TENSE_Prs|MOOD_Ind", "ocr": "0.96", "pos": "V", "ref": "4", "word": "l\u00e4het\u00e4n" }, { "dephead": "4", "deprel": "nommod", "lemma": "sin\u00e4", "lemmacomp": "sin\u00e4", "lex": "|sin\u00e4..pn.1|", "msd": "SUBCAT_Pers|NUM_Sg|CASE_All", "ocr": "0.97", "pos": "Pron", "ref": "5", "word": "sinulle" }, { "dephead": "8", "deprel": "det", "lemma": "se", "lemmacomp": "se", "lex": "|se..pn.1|", "msd": "SUBCAT_Dem|NUM_Sg|CASE_Gen", "ocr": "0.97", "pos": "Pron", "ref": "6", "word": "sen" }, { "dephead": "8", "deprel": "amod", "lemma": "ennenluwatun", "lemmacomp": "ennenluwatun", "lex": "|ennenluwatun..jj.1|", "msd": "NUM_Sg|CASE_Gen|CMP_Pos|OTHER_UNK", "ocr": "0.97", "pos": "A", "ref": "7", "word": "ennenluwatun" }, { "dephead": "4", "deprel": "dobj", "lemma": "arweluni", "lemmacomp": "arweluni", "lex": "|arweluni..nn.1|", "msd": "NUM_Sg|CASE_Gen|OTHER_UNK", "ocr": "0.98", "pos": "N", "ref": "8", "word": "arweluni" }, { "dephead": "10", "deprel": "poss", "lemma": "Suomi", "lemmacomp": "Suomi", "lex": "|Suomi..nn.1|", "msd": "SUBCAT_Prop|NUM_Sg|CASE_Gen|CASECHANGE_Up", "ocr": "0.99", "pos": "N", "ref": "9", "word": "Suomen" }, { "dephead": "8", "deprel": "nommod", "lemma": "nimi", "lemmacomp": "nimi", "lex": "|nimi..nn.1|", "msd": "NUM_Sg|CASE_Ela", "ocr": "0.98", "pos": "N", "ref": "10", "word": "nimest\u00e4" }, { "dephead": "4", "deprel": "punct", "lemma": ".", "lemmacomp": ".", "lex": "|...xx.1|", "msd": "_", "ocr": "0.98", "pos": "Punct", "ref": "11", "structs": { "close": [ "sentence" ] }, "word": "." } ] }, { "corpus": "KLK_FI_1839", "match": { "end": 6, "position": 38410, "start": 5 }, "structs": { "paragraph_id": "3", "sentence_id": "2794", "sentence_local_id": "6", "sentence_parse_state": "parsed", "text_binding_id": "502212", "text_datefrom": "18391111", "text_dateto": "18391130", "text_elec_date": "2008-05-09", "text_img_url": "#DIRECTORY#fk01442_1839-11_11#SEPARATOR#00004.#EXTENSION#", "text_issue_date": "11.1839", "text_issue_no": "11", "text_issue_title": "MEHIL\u00c4INEN.", "text_label": "MEHIL\u00c4INEN. no. 11 11.1839", "text_language": "fi", "text_page_no": "4", "text_publ_id": "fk01442", "text_publ_title": "Mehil\u00e4inen", "text_publ_type": "aikakausi", "text_sentcount": "13", "text_tokencount": "270" }, "tokens": [ { "dephead": "2", "deprel": "advmod", "lemma": "niin", "lemmacomp": "niin", "lex": "|niin..ab.1|", "msd": "CASECHANGE_Up", "ocr": "0.96", "pos": "Adv", "ref": "1", "structs": { "open": [ "sentence" ] }, "word": "Niin" }, { "dephead": "0", "deprel": "ROOT", "lemma": "olla", "lemmacomp": "olla", "lex": "|olla..vb.1|", "msd": "PRS_Sg3|VOICE_Act|TENSE_Prs|MOOD_Ind", "ocr": "0.96", "pos": "V", "ref": "2", "word": "on" }, { "dephead": "5", "deprel": "det", "lemma": "joku", "lemmacomp": "joku", "lex": "|joku..pn.1|", "msd": "NUM_Sg|CASE_Nom", "ocr": "0.86", "pos": "Pron", "ref": "3", "word": "joku" }, { "dephead": "5", "deprel": "nn", "lemma": "muistaa", "lemmacomp": "muistaa", "lex": "|muistaa..vb.1|", "msd": "NUM_Sg|CASE_Tra|POSS_PxSg1|VOICE_Act|INF_Inf1", "ocr": "0.91", "pos": "V", "ref": "4", "word": "muistaakseni" }, { "dephead": "2", "deprel": "nsubj", "lemma": "arwaillu", "lemmacomp": "arwaillu", "lex": "|arwaillu..nn.1|", "msd": "NUM_Sg|CASE_Nom|OTHER_UNK", "ocr": "0.96", "pos": "N", "ref": "5", "word": "arwaillu" }, { "dephead": "7", "deprel": "nsubj", "lemma": "Suomi", "lemmacomp": "Suomi", "lex": "|Suomi..nn.1|", "msd": "SUBCAT_Prop|NUM_Sg|CASE_Gen|CASECHANGE_Up", "ocr": "0.96", "pos": "N", "ref": "6", "word": "Suomen" }, { "dephead": "8", "deprel": "partmod", "lemma": "saada", "lemmacomp": "saada", "lex": "|saada..vb.1|", "msd": "NUM_Sg|CASE_Gen|VOICE_Act|PCP_PrfPrc|CMP_Pos", "ocr": "0.97", "pos": "V", "ref": "7", "word": "saaneen" }, { "dephead": "9", "deprel": "poss", "lemma": "nimi", "lemmacomp": "nimi", "lex": "|nimi..nn.1|", "msd": "NUM_Sg|CASE_Gen|POSS_Px3", "ocr": "0.98", "pos": "N", "ref": "8", "word": "nimens\u00e4" }, { "dephead": "10", "deprel": "poss", "lemma": "kala", "lemmacomp": "kala", "lex": "|kala..nn.1|", "msd": "NUM_Pl|CASE_Gen", "ocr": "0.97", "pos": "N", "ref": "9", "word": "kalain" }, { "dephead": "5", "deprel": "nommod", "lemma": "suomu", "lemmacomp": "suomu", "lex": "|suomu..nn.1|", "msd": "NUM_Pl|CASE_Ela", "ocr": "0.97", "pos": "N", "ref": "10", "word": "suomuista" }, { "dephead": "23", "deprel": "punct", "lemma": ",", "lemmacomp": ",", "lex": "|,..xx.1|", "msd": "_", "ocr": "0.97", "pos": "Punct", "ref": "11", "word": "," }, { "dephead": "23", "deprel": "nommod", "lemma": "joki", "lemmacomp": "joki", "lex": "|joki..nn.1|", "msd": "NUM_Pl|CASE_Ela", "ocr": "0.94", "pos": "N", "ref": "12", "word": "joista" }, { "dephead": "18", "deprel": "advmod", "lemma": "t\u00e4\u00e4ll\u00e4", "lemmacomp": "t\u00e4\u00e4ll\u00e4", "lex": "|t\u00e4\u00e4ll\u00e4..ab.1|", "msd": "_", "ocr": "0.93", "pos": "Adv", "ref": "13", "word": "t\u00e4\u00e4ll\u00e4" }, { "dephead": "18", "deprel": "nsubj-cop", "lemma": "j\u00e4rwet", "lemmacomp": "j\u00e4rwet", "lex": "|j\u00e4rwet..nn.1|", "msd": "NUM_Pl|CASE_Nom|OTHER_UNK", "ocr": "0.83", "pos": "N", "ref": "14", "word": "j\u00e4rwet" }, { "dephead": "18", "deprel": "advmod", "lemma": "Muinoseen", "lemmacomp": "Muinoseen", "lex": "|Muinoseen..ab.1|", "msd": "CASECHANGE_Up|OTHER_UNK", "ocr": "0.94", "pos": "Adv", "ref": "15", "word": "Muinoseen" }, { "dephead": "17", "deprel": "aux", "lemma": "owat", "lemmacomp": "owat", "lex": "|owat..vb.1|", "msd": "PRS_Pl3|VOICE_Act|TENSE_Prs|MOOD_Ind|OTHER_UNK", "ocr": "0.95", "pos": "V", "ref": "16", "word": "owat" }, { "dephead": "18", "deprel": "cop", "lemma": "olla", "lemmacomp": "olla", "lex": "|olla..vb.1|", "msd": "NUM_Pl|CASE_Nom|VOICE_Act|PCP_PrfPrc|CMP_Pos", "ocr": "0.98", "pos": "V", "ref": "17", "word": "olleet" }, { "dephead": "23", "deprel": "amod", "lemma": "rikas", "lemmacomp": "rikas", "lex": "|rikas..jj.1|", "msd": "NUM_Pl|CASE_Nom|CMP_Pos", "ocr": "0.96", "pos": "A", "ref": "18", "word": "rikkaat" }, { "dephead": "18", "deprel": "punct", "lemma": ",", "lemmacomp": ",", "lex": "|,..xx.1|", "msd": "_", "ocr": "0.96", "pos": "Punct", "ref": "19", "word": "," }, { "dephead": "18", "deprel": "cc", "lemma": "ja", "lemmacomp": "ja", "lex": "|ja..kn.1|", "msd": "SUBCAT_CC", "ocr": "0.96", "pos": "C", "ref": "20", "word": "ja" }, { "dephead": "22", "deprel": "advmod", "lemma": "niin", "lemmacomp": "niin", "lex": "|niin..ab.1|", "msd": "_", "ocr": "0.99", "pos": "Adv", "ref": "21", "word": "niin" }, { "dephead": "18", "deprel": "conj", "lemma": "osaillu", "lemmacomp": "osaillu", "lex": "|osaillu..jj.1|", "msd": "NUM_Sg|CASE_Nom|CMP_Pos|OTHER_UNK", "ocr": "0.95", "pos": "A", "ref": "22", "word": "osaillu" }, { "dephead": "10", "deprel": "appos", "lemma": "suomu-maa", "lemmacomp": "suomu|maa", "lex": "|suomu-maa..nn.1|", "msd": "NUM_Sg|CASE_Nom|CASECHANGE_Up", "ocr": "0.97", "pos": "N", "ref": "23", "word": "Suomu-maa" }, { "dephead": "27", "deprel": "punct", "lemma": ",", "lemmacomp": ",", "lex": "|,..xx.1|", "msd": "_", "ocr": "0.97", "pos": "Punct", "ref": "24", "word": "," }, { "dephead": "27", "deprel": "rel", "lemma": "joka", "lemmacomp": "joka", "lex": "|joka..pn.1|", "msd": "SUBCAT_Rel|NUM_Sg|CASE_Ela", "ocr": "0.93", "pos": "Pron", "ref": "25", "word": "josta" }, { "dephead": "27", "deprel": "advmod", "lemma": "sitte", "lemmacomp": "sitte", "lex": "|sitte..ab.1|", "msd": "OTHER_UNK", "ocr": "0.95", "pos": "Adv", "ref": "26", "word": "sitte" }, { "dephead": "23", "deprel": "rcmod", "lemma": "suomi-maa", "lemmacomp": "suomi|maa", "lex": "|suomi-maa..nn.1|", "msd": "NUM_Sg|CASE_Nom|CASECHANGE_Up", "ocr": "0.86", "pos": "N", "ref": "27", "word": "Suomen-maa" }, { "dephead": "2", "deprel": "punct", "lemma": ".", "lemmacomp": ".", "lex": "|...xx.1|", "msd": "_", "ocr": "0.86", "pos": "Punct", "ref": "28", "structs": { "close": [ "sentence" ] }, "word": "." } ] } ], "querydata": "b'x\\x9c\\r\\xc6\\xc1\\r\\x000\\x08\\x03\\xb1\\x95\\x08\\xa1\\x80t\\xfb\\xefU\\xfc\\xb2\\xd6]\\x19\\x9e\\xe5\\xc6\\x0e\\xb7\\x14\\x8aG\\x07[\\xa4\\x03\\xa9\\x91\\xa9\\xfc\\xec}\\t\\xd5'", "time": 3.7128119468688965 }