{"id":"https://openalex.org/W2460907386","doi":"https://doi.org/10.18653/v1/n16-1130","title":"Learning a POS tagger for AAVE-like language","display_name":"Learning a POS tagger for AAVE-like language","publication_year":2016,"publication_date":"2016-01-01","ids":{"openalex":"https://openalex.org/W2460907386","doi":"https://doi.org/10.18653/v1/n16-1130","mag":"2460907386"},"language":"en","primary_location":{"id":"doi:10.18653/v1/n16-1130","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/n16-1130","pdf_url":"https://www.aclweb.org/anthology/N16-1130.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/N16-1130.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5049407823","display_name":"Anna J\u00f8rgensen","orcid":"https://orcid.org/0000-0001-5614-567X"},"institutions":[{"id":"https://openalex.org/I887064364","display_name":"University of Amsterdam","ror":"https://ror.org/04dkp9463","country_code":"NL","type":"education","lineage":["https://openalex.org/I887064364"]}],"countries":["NL"],"is_corresponding":true,"raw_author_name":"Anna J\u00f8rgensen","raw_affiliation_strings":["University of Amsterdam Science Park 107 1098 XG Amsterdam, NL"],"affiliations":[{"raw_affiliation_string":"University of Amsterdam Science Park 107 1098 XG Amsterdam, NL","institution_ids":["https://openalex.org/I887064364"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084505122","display_name":"Dirk Hovy","orcid":"https://orcid.org/0000-0002-4618-3127"},"institutions":[{"id":"https://openalex.org/I124055696","display_name":"University of Copenhagen","ror":"https://ror.org/035b05819","country_code":"DK","type":"education","lineage":["https://openalex.org/I124055696"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Dirk Hovy","raw_affiliation_strings":["University of Copenhagen Njalsgade 140 2300 Copenhagen S, DK"],"affiliations":[{"raw_affiliation_string":"University of Copenhagen Njalsgade 140 2300 Copenhagen S, DK","institution_ids":["https://openalex.org/I124055696"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5018138946","display_name":"Anders S\u00f8gaard","orcid":"https://orcid.org/0000-0001-5250-4276"},"institutions":[{"id":"https://openalex.org/I124055696","display_name":"University of Copenhagen","ror":"https://ror.org/035b05819","country_code":"DK","type":"education","lineage":["https://openalex.org/I124055696"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Anders S\u00f8gaard","raw_affiliation_strings":["University of Copenhagen Njalsgade 140 2300 Copenhagen S, DK"],"affiliations":[{"raw_affiliation_string":"University of Copenhagen Njalsgade 140 2300 Copenhagen S, DK","institution_ids":["https://openalex.org/I124055696"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5049407823"],"corresponding_institution_ids":["https://openalex.org/I887064364"],"apc_list":null,"apc_paid":null,"fwci":5.3209,"has_fulltext":true,"cited_by_count":37,"citation_normalized_percentile":{"value":0.95851776,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9998999834060669,"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":0.9998999834060669,"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/T10028","display_name":"Topic Modeling","score":0.9961000084877014,"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/T10759","display_name":"Translation Studies and Practices","score":0.982699990272522,"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/lyrics","display_name":"Lyrics","score":0.8745260238647461},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8525070548057556},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6952038407325745},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6501734256744385},{"id":"https://openalex.org/keywords/part-of-speech-tagging","display_name":"Part-of-speech tagging","score":0.5390452742576599},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4893145263195038},{"id":"https://openalex.org/keywords/named-entity","display_name":"Named entity","score":0.46524155139923096},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4376369118690491},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.41277217864990234},{"id":"https://openalex.org/keywords/part-of-speech","display_name":"Part of speech","score":0.3804433047771454},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.0628097653388977}],"concepts":[{"id":"https://openalex.org/C2776436406","wikidata":"https://www.wikidata.org/wiki/Q602446","display_name":"Lyrics","level":2,"score":0.8745260238647461},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8525070548057556},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6952038407325745},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6501734256744385},{"id":"https://openalex.org/C2780684714","wikidata":"https://www.wikidata.org/wiki/Q1271424","display_name":"Part-of-speech tagging","level":3,"score":0.5390452742576599},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4893145263195038},{"id":"https://openalex.org/C2777889803","wikidata":"https://www.wikidata.org/wiki/Q25047676","display_name":"Named entity","level":2,"score":0.46524155139923096},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4376369118690491},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.41277217864990234},{"id":"https://openalex.org/C123406163","wikidata":"https://www.wikidata.org/wiki/Q82042","display_name":"Part of speech","level":2,"score":0.3804433047771454},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.0628097653388977},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/v1/n16-1130","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/n16-1130","pdf_url":"https://www.aclweb.org/anthology/N16-1130.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.atira.dk:publications/4c33222b-d9f6-4c7b-87e2-c0c64513b123","is_oa":true,"landing_page_url":"http://www.aclweb.org/anthology/N16-1130","pdf_url":"https://aclanthology.org/N16-1130.pdf","source":{"id":"https://openalex.org/S4306401983","display_name":"Research at the University of Copenhagen (University of Copenhagen)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I124055696","host_organization_name":"University of Copenhagen","host_organization_lineage":["https://openalex.org/I124055696"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"J\u00f8rgensen , A , Hovy , D & S\u00f8gaard , A 2016 , Learning a POS tagger for AAVE-like language . in Proceedings of NAACL-HLT 2016 . Association for Computational Linguistics , pp. 1115-1120 , NAACL , San Diego , United States , 12/06/2016 . < http://www.aclweb.org/anthology/N16-1130 >","raw_type":"contributionToPeriodical"},{"id":"pmh:oai:pure.atira.dk:openaire_cris_publications/4c33222b-d9f6-4c7b-87e2-c0c64513b123","is_oa":false,"landing_page_url":"https://researchprofiles.ku.dk/da/publications/4c33222b-d9f6-4c7b-87e2-c0c64513b123","pdf_url":null,"source":{"id":"https://openalex.org/S4306401983","display_name":"Research at the University of Copenhagen (University of Copenhagen)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I124055696","host_organization_name":"University of Copenhagen","host_organization_lineage":["https://openalex.org/I124055696"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"J\u00f8rgensen , A , Hovy , D & S\u00f8gaard , A 2016 , Learning a POS tagger for AAVE-like language . in Proceedings of NAACL-HLT 2016 . Association for Computational Linguistics , pp. 1115-1120 , NAACL , San Diego , United States , 12/06/2016 . < http://www.aclweb.org/anthology/N16-1130 >","raw_type":"contributionToPeriodical"}],"best_oa_location":{"id":"doi:10.18653/v1/n16-1130","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/n16-1130","pdf_url":"https://www.aclweb.org/anthology/N16-1130.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2460907386.pdf","grobid_xml":"https://content.openalex.org/works/W2460907386.grobid-xml"},"referenced_works_count":24,"referenced_works":["https://openalex.org/W371426616","https://openalex.org/W1574126082","https://openalex.org/W1614298861","https://openalex.org/W2008652694","https://openalex.org/W2043693083","https://openalex.org/W2141599568","https://openalex.org/W2143995218","https://openalex.org/W2146867136","https://openalex.org/W2157765050","https://openalex.org/W2161044106","https://openalex.org/W2168199177","https://openalex.org/W2177226758","https://openalex.org/W2250202591","https://openalex.org/W2250493512","https://openalex.org/W2251147480","https://openalex.org/W2252027930","https://openalex.org/W2295781714","https://openalex.org/W2296308078","https://openalex.org/W2784348179","https://openalex.org/W2919831714","https://openalex.org/W2950577311","https://openalex.org/W4233787372","https://openalex.org/W4302455086","https://openalex.org/W4412253302"],"related_works":["https://openalex.org/W1965453504","https://openalex.org/W2396342956","https://openalex.org/W3128305375","https://openalex.org/W2626026432","https://openalex.org/W2949108231","https://openalex.org/W2486838646","https://openalex.org/W2006539681","https://openalex.org/W4408329600","https://openalex.org/W2046224275","https://openalex.org/W2251183413"],"abstract_inverted_index":{"Part-of-speech":[0],"(POS)":[1],"taggers":[2],"trained":[3],"on":[4,9,89,92,96],"newswire":[5,107],"perform":[6],"much":[7],"worse":[8],"domains":[10,20],"such":[11],"as":[12],"subtitles,":[13,44,90],"lyrics,":[14,45,93],"or":[15],"tweets.":[16],"In":[17,31],"addition,":[18],"these":[19],"are":[21],"also":[22],"heterogeneous,":[23],"e.g.,":[24],"with":[25,49,98],"respect":[26],"to":[27,100],"registers":[28],"and":[29,46,62,67,73,94,110],"dialects.":[30],"this":[32],"paper,":[33],"we":[34,71],"consider":[35],"the":[36],"problem":[37],"of":[38,59,87],"learning":[39],"a":[40,57,84,105,115],"POS":[41,81,108,118],"tagger":[42,82],"for":[43],"tweets":[47],"associated":[48],"African-American":[50],"Vernacular":[51],"English":[52],"(AAVE).":[53],"We":[54],"learn":[55],"from":[56],"mixture":[58],"randomly":[60],"sampled":[61],"manually":[63],"annotated":[64],"Twitter":[65,117],"data":[66],"unlabeled":[68],"data,":[69],"which":[70],"automatically":[72],"partially":[74],"label":[75],"using":[76],"mined":[77],"tag":[78],"dictionaries.":[79],"Our":[80],"obtains":[83],"tagging":[85],"accuracy":[86],"89%":[88],"85%":[91],"83%":[95],"tweets,":[97],"up":[99],"55%":[101],"error":[102,112],"reductions":[103,113],"over":[104,114],"state-of-the-art":[106,116],"tagger,":[109],"15-25%":[111],"tagger.":[119]},"counts_by_year":[{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":2}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}