{"id":"https://openalex.org/W2144508908","doi":null,"title":"A Bayesian LDA-based model for semi-supervised part-of-speech tagging","display_name":"A Bayesian LDA-based model for semi-supervised part-of-speech tagging","publication_year":2007,"publication_date":"2007-12-03","ids":{"openalex":"https://openalex.org/W2144508908","mag":"2144508908"},"language":"en","primary_location":{"id":"mag:2144508908","doi":null,"is_oa":false,"landing_page_url":"https://papers.nips.cc/paper/3317-a-bayesian-lda-based-model-for-semi-supervised-part-of-speech-tagging.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4363606243","display_name":"neural information processing systems","issn_l":"1049-5258","issn":["1049-5258"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-2"],"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":"Neural Information Processing Systems","raw_type":null},"volume":null,"type":"article","is_traditional":true,"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/A5053947885","display_name":"Kristina Toutanova","orcid":"https://orcid.org/0009-0005-3458-9049","observed_orcids":["https://orcid.org/0009-0005-3458-9049"]},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kristina Toutanova","raw_affiliation_strings":["Microsoft Research, Redmond, WA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research, Redmond, WA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034461489","display_name":"Mark Johnson","orcid":"https://orcid.org/0000-0003-4809-8441","observed_orcids":["https://orcid.org/0000-0003-4809-8441","https://orcid.org/0000-0001-9720-8761"]},"institutions":[{"id":"https://openalex.org/I27804330","display_name":"Brown University","ror":"https://ror.org/05gq02987","country_code":"US","type":"education","lineage":["https://openalex.org/I27804330"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mark Johnson","raw_affiliation_strings":["Brown University, Providence, RI,"],"raw_orcid":"https://orcid.org/0000-0003-4809-8441","affiliations":[{"raw_affiliation_string":"Brown University, Providence, RI,","institution_ids":["https://openalex.org/I27804330"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":11.4568,"has_fulltext":false,"cited_by_count":108,"citation_normalized_percentile":{"value":0.98557665,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":88,"max":99},"biblio":{"volume":"20","issue":null,"first_page":"1521","last_page":"1528"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9926999807357788,"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":0.9926999807357788,"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":0.004699999932199717,"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/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.0003000000142492354,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/part-of-speech-tagging","display_name":"part-of-speech tagging","score":0.921999990940094},{"id":"https://openalex.org/keywords/semi-supervised-learning","display_name":"semi-supervised learning","score":0.9929999709129333},{"id":"https://openalex.org/keywords/latent-dirichlet-allocation","display_name":"latent Dirichlet allocation","score":0.9079999923706055},{"id":"https://openalex.org/keywords/bayesian-model","display_name":"Bayesian model","score":0.9039999842643738},{"id":"https://openalex.org/keywords/lexical-ambiguity","display_name":"lexical ambiguity","score":0.5699999928474426}],"concepts":[{"id":"https://openalex.org/C500882744","wikidata":"https://www.wikidata.org/wiki/Q269236","display_name":"Latent Dirichlet allocation","level":3,"score":0.8271443247795105},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.76385498046875},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6413028240203857},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.5750208497047424},{"id":"https://openalex.org/C2780522230","wikidata":"https://www.wikidata.org/wiki/Q1140419","display_name":"Ambiguity","level":2,"score":0.5704437494277954},{"id":"https://openalex.org/C169214877","wikidata":"https://www.wikidata.org/wiki/Q981016","display_name":"Dirichlet distribution","level":3,"score":0.5355513095855713},{"id":"https://openalex.org/C171686336","wikidata":"https://www.wikidata.org/wiki/Q3532085","display_name":"Topic model","level":2,"score":0.5180535316467285},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.5167014598846436},{"id":"https://openalex.org/C132010649","wikidata":"https://www.wikidata.org/wiki/Q189222","display_name":"Intuition","level":2,"score":0.49929261207580566},{"id":"https://openalex.org/C160234255","wikidata":"https://www.wikidata.org/wiki/Q812535","display_name":"Bayesian inference","level":3,"score":0.4255768060684204},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.410264253616333},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3606574833393097},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3529554605484009},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.16967898607254028},{"id":"https://openalex.org/C182310444","wikidata":"https://www.wikidata.org/wiki/Q1332643","display_name":"Boundary value problem","level":2,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"mag:2144508908","doi":null,"is_oa":false,"landing_page_url":"https://papers.nips.cc/paper/3317-a-bayesian-lda-based-model-for-semi-supervised-part-of-speech-tagging.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4363606243","display_name":"neural information processing systems","issn_l":"1049-5258","issn":["1049-5258"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-2"],"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":"Neural Information Processing Systems","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W1570013475","https://openalex.org/W1612003148","https://openalex.org/W1880262756","https://openalex.org/W1976241232","https://openalex.org/W1996430422","https://openalex.org/W2008652694","https://openalex.org/W2078058974","https://openalex.org/W2078957420","https://openalex.org/W2096765155","https://openalex.org/W2099873701","https://openalex.org/W2112861996","https://openalex.org/W2121145703","https://openalex.org/W2137807925","https://openalex.org/W2149830985","https://openalex.org/W2158108973","https://openalex.org/W2170206653","https://openalex.org/W2951769629"],"related_works":["https://openalex.org/W7100278904","https://openalex.org/W7095342540","https://openalex.org/W7100236882","https://openalex.org/W137601953","https://openalex.org/W4300858855","https://openalex.org/W7098460577","https://openalex.org/W7097661448","https://openalex.org/W7097022209","https://openalex.org/W1736441281","https://openalex.org/W2131634727"],"abstract_inverted_index":{"We":[0],"present":[1],"a":[2,34,44,68],"novel":[3],"Bayesian":[4],"model":[5,11,17,35,57,63],"for":[6,36,64],"semi-supervised":[7],"part-of-speech":[8],"tagging.":[9],"Our":[10,56],"extends":[12],"the":[13,20,38,51,59],"Latent":[14],"Dirichlet":[15],"Allocation":[16],"and":[18],"incorporates":[19],"intuition":[21],"that":[22],"words'":[23],"distributions":[24],"over":[25],"tags,":[26],"p(t|w),":[27],"are":[28],"sparse.":[29],"In":[30],"addition":[31],"we":[32],"introduce":[33],"determining":[37],"set":[39],"of":[40,43,54],"possible":[41],"tags":[42],"word":[45],"which":[46],"captures":[47],"important":[48],"dependencies":[49],"in":[50],"ambiguity":[52],"classes":[53],"words.":[55],"outperforms":[58],"best":[60],"previously":[61],"proposed":[62],"this":[65],"task":[66],"on":[67],"standard":[69],"dataset.":[70]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":9},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":6},{"year":2015,"cited_by_count":11},{"year":2014,"cited_by_count":12},{"year":2013,"cited_by_count":6},{"year":2012,"cited_by_count":7}],"updated_date":"2026-11-10T11:39:43.021295","created_date":"2016-06-24T00:00:00"}