{"id":"https://openalex.org/W70524345","doi":null,"title":"Part-of-Speech Tagging for Middle English through Alignment and Projection of Parallel Diachronic Texts","display_name":"Part-of-Speech Tagging for Middle English through Alignment and Projection of Parallel Diachronic Texts","publication_year":2007,"publication_date":"2007-12-01","ids":{"openalex":"https://openalex.org/W70524345","mag":"70524345"},"language":"en","primary_location":{"id":"mag:70524345","doi":null,"is_oa":false,"landing_page_url":"https://www.coli.uni-saarland.de/courses/tm-hist10/slides/presentation_yevgeni.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306418267","display_name":"Empirical Methods in Natural Language Processing","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"Empirical Methods in Natural Language Processing","raw_type":null},"volume":null,"type":"article","indexed_in":[],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5004719091","display_name":"Taesun Moon","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Taesun Moon","raw_affiliation_strings":["University of Texas at Austin#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Texas at Austin#TAB#","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5048931310","display_name":"Jason Baldridge","orcid":"https://orcid.org/0000-0002-4712-1841","observed_orcids":["https://orcid.org/0000-0002-4712-1841"]},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jason Baldridge","raw_affiliation_strings":["University of Texas at Austin#TAB#"],"raw_orcid":"https://orcid.org/0000-0002-4712-1841","affiliations":[{"raw_affiliation_string":"University of Texas at Austin#TAB#","institution_ids":["https://openalex.org/I86519309"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I86519309"],"apc_list":null,"apc_paid":null,"fwci":1.576,"has_fulltext":false,"cited_by_count":21,"citation_normalized_percentile":{"value":0.85234394,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"390","last_page":"399"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12377","display_name":"Digital Humanities and Scholarship","score":0.0,"subfield":{"id":"https://openalex.org/subfields/1208","display_name":"Literature and Literary Theory"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10034","display_name":"Syntax, Semantics, Linguistic Variation","score":0.0,"subfield":{"id":"https://openalex.org/subfields/1203","display_name":"Language and Linguistics"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/part-of-speech-tagging","display_name":"part-of-speech tagging","score":0.9449999928474426},{"id":"https://openalex.org/keywords/middle-english","display_name":"Middle English","score":0.9909999966621399},{"id":"https://openalex.org/keywords/parallel-corpora","display_name":"parallel corpus","score":0.4909999966621399},{"id":"https://openalex.org/keywords/bootstrap-method","display_name":"bootstrapping","score":0.6330000162124634},{"id":"https://openalex.org/keywords/historical-linguistics","display_name":"historical linguistics","score":0.4320000112056732}],"concepts":[{"id":"https://openalex.org/C108757681","wikidata":"https://www.wikidata.org/wiki/Q2773912","display_name":"Bigram","level":3,"score":0.969505786895752},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7989720106124878},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6506103277206421},{"id":"https://openalex.org/C207609745","wikidata":"https://www.wikidata.org/wiki/Q4944086","display_name":"Bootstrapping (finance)","level":2,"score":0.617178738117218},{"id":"https://openalex.org/C2780684714","wikidata":"https://www.wikidata.org/wiki/Q1271424","display_name":"Part-of-speech tagging","level":3,"score":0.5907049179077148},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5852326154708862},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.5392445921897888},{"id":"https://openalex.org/C9679016","wikidata":"https://www.wikidata.org/wiki/Q1417473","display_name":"Principle of maximum entropy","level":2,"score":0.4677830934524536},{"id":"https://openalex.org/C2985367798","wikidata":"https://www.wikidata.org/wiki/Q1346592","display_name":"Parallel corpora","level":3,"score":0.4449460506439209},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4131563901901245},{"id":"https://openalex.org/C123406163","wikidata":"https://www.wikidata.org/wiki/Q82042","display_name":"Part of speech","level":2,"score":0.3728864789009094},{"id":"https://openalex.org/C137546455","wikidata":"https://www.wikidata.org/wiki/Q3213474","display_name":"Trigram","level":2,"score":0.10163074731826782},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09571772813796997},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.08165711164474487},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"mag:70524345","doi":null,"is_oa":false,"landing_page_url":"https://www.coli.uni-saarland.de/courses/tm-hist10/slides/presentation_yevgeni.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306418267","display_name":"Empirical Methods in Natural Language Processing","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":"Empirical Methods in Natural Language Processing","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"sustainable_development_goals_aurora":[{"id":"https://metadata.un.org/sdg/4","score":0.7900000214576721,"display_name":"Quality education"}],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W200996604","https://openalex.org/W639106246","https://openalex.org/W1588612820","https://openalex.org/W1632114991","https://openalex.org/W1773803948","https://openalex.org/W1811404221","https://openalex.org/W1987869189","https://openalex.org/W2016630033","https://openalex.org/W2058635392","https://openalex.org/W2062822461","https://openalex.org/W2075517337","https://openalex.org/W2079442239","https://openalex.org/W2117400858","https://openalex.org/W2125492538","https://openalex.org/W2138584836","https://openalex.org/W2156985047"],"related_works":["https://openalex.org/W1632114991","https://openalex.org/W1553878378","https://openalex.org/W2076031003","https://openalex.org/W2326206218","https://openalex.org/W3022465890","https://openalex.org/W2185970782","https://openalex.org/W2739015351","https://openalex.org/W2044023740","https://openalex.org/W2963418526","https://openalex.org/W2156985047","https://openalex.org/W2079442239","https://openalex.org/W2169508526","https://openalex.org/W2126905976","https://openalex.org/W2242534280","https://openalex.org/W2125492538","https://openalex.org/W2770603736","https://openalex.org/W2598033104","https://openalex.org/W3210039896","https://openalex.org/W2989750031","https://openalex.org/W2145514301"],"abstract_inverted_index":{"We":[0,38],"demonstrate":[1],"an":[2,123],"approach":[3,124],"for":[4,8,15],"inducing":[5],"a":[6,47,61],"tagger":[7,49,64,71],"historical":[9],"languages":[10],"based":[11,125],"on":[12,34,65,72,80,94,102,126],"existing":[13],"resources":[14],"their":[16],"modern":[17],"varieties.":[18],"Tags":[19],"from":[20],"Present":[21],"Day":[22],"English":[23,30,83,105],"source":[24],"text":[25,31,76],"are":[26],"projected":[27,56],"to":[28,50,87,121],"Middle":[29,82,104],"using":[32],"alignments":[33],"parallel":[35],"Biblical":[36,75,95],"text.":[37,84],"explore":[39],"the":[40,52,55,66,69,73,91,100],"use":[41],"of":[42,68],"multiple":[43],"alignment":[44],"approaches":[45],"and":[46,77,98,117],"bigram":[48,70],"reduce":[51],"noise":[53],"in":[54,90,99],"tags.":[57],"Finally,":[58],"we":[59],"train":[60],"maximum":[62],"entropy":[63],"output":[67],"target":[74],"test":[78,96],"it":[79],"tagged":[81],"This":[85],"leads":[86],"tagging":[88],"accuracy":[89],"low":[92],"80\u2019s":[93],"material":[97],"60\u2019s":[101],"other":[103],"material.":[106],"Our":[107],"results":[108],"suggest":[109],"that":[110],"our":[111],"bootstrapping":[112],"methods":[113],"have":[114],"considerable":[115],"potential,":[116],"could":[118],"be":[119],"used":[120],"semi-automate":[122],"incremental":[127],"manual":[128],"annotation.":[129]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":2}],"updated_date":"2026-10-12T09:40:04.860316","created_date":"2025-10-10T00:00:00"}