{"id":"https://openalex.org/W1621942032","doi":"https://doi.org/10.3115/v1/e14-1013","title":"Modelling the Lexicon in Unsupervised Part of Speech Induction","display_name":"Modelling the Lexicon in Unsupervised Part of Speech Induction","publication_year":2014,"publication_date":"2014-01-01","ids":{"openalex":"https://openalex.org/W1621942032","doi":"https://doi.org/10.3115/v1/e14-1013","mag":"1621942032"},"language":"en","primary_location":{"id":"doi:10.3115/v1/e14-1013","is_oa":true,"landing_page_url":"https://doi.org/10.3115/v1/e14-1013","pdf_url":"https://aclanthology.org/E14-1013.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 14th Conference of the European Chapter of the Association for Computational Linguistics","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/E14-1013.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5050462569","display_name":"Greg Dubbin","orcid":null},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Gregory Dubbin","raw_affiliation_strings":["Department of Computer Science University of Oxford United Kingdom","University of Oxford"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science University of Oxford United Kingdom","institution_ids":["https://openalex.org/I40120149"]},{"raw_affiliation_string":"University of Oxford","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014309771","display_name":"Phil Blunsom","orcid":null},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]},{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Phil Blunsom","raw_affiliation_strings":["Department of Computer Science University of Oxford United Kingdom","University of Edinburgh, Edinburgh, United Kingdom"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science University of Oxford United Kingdom","institution_ids":["https://openalex.org/I40120149"]},{"raw_affiliation_string":"University of Edinburgh, Edinburgh, United Kingdom","institution_ids":["https://openalex.org/I98677209"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5050462569"],"corresponding_institution_ids":["https://openalex.org/I40120149"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.03868129,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"116","last_page":"125"},"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/T10028","display_name":"Topic Modeling","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/T11269","display_name":"Algorithms and Data Compression","score":0.9970999956130981,"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/computer-science","display_name":"Computer science","score":0.8251458406448364},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.667395830154419},{"id":"https://openalex.org/keywords/lexicon","display_name":"Lexicon","score":0.6558476686477661},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6219555735588074},{"id":"https://openalex.org/keywords/part-of-speech-tagging","display_name":"Part-of-speech tagging","score":0.6163480877876282},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6134557127952576},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5612748861312866},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4757014214992523},{"id":"https://openalex.org/keywords/part-of-speech","display_name":"Part of speech","score":0.46092861890792847},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.4541834890842438},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.26766157150268555},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.0865008533000946}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8251458406448364},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.667395830154419},{"id":"https://openalex.org/C2778121359","wikidata":"https://www.wikidata.org/wiki/Q8096","display_name":"Lexicon","level":2,"score":0.6558476686477661},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6219555735588074},{"id":"https://openalex.org/C2780684714","wikidata":"https://www.wikidata.org/wiki/Q1271424","display_name":"Part-of-speech tagging","level":3,"score":0.6163480877876282},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6134557127952576},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5612748861312866},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4757014214992523},{"id":"https://openalex.org/C123406163","wikidata":"https://www.wikidata.org/wiki/Q82042","display_name":"Part of speech","level":2,"score":0.46092861890792847},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.4541834890842438},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.26766157150268555},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.0865008533000946},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":7,"locations":[{"id":"doi:10.3115/v1/e14-1013","is_oa":true,"landing_page_url":"https://doi.org/10.3115/v1/e14-1013","pdf_url":"https://aclanthology.org/E14-1013.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 14th Conference of the European Chapter of the Association for Computational Linguistics","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1402.6516","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1402.6516","pdf_url":"https://arxiv.org/pdf/1402.6516","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"mag:1621942032","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1402.6516.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.651.4763","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.651.4763","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://aclweb.org/anthology/E/E14/E14-1013.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.762.1833","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.762.1833","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://arxiv.org/pdf/1402.6516.pdf","raw_type":"text"},{"id":"pmh:oai:ora.ox.ac.uk:uuid:6a453ff1-c848-46f3-aeb1-d303d338ed85","is_oa":false,"landing_page_url":"https://ora.ox.ac.uk/objects/uuid:6a453ff1-c848-46f3-aeb1-d303d338ed85","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Department of Computer Science","raw_type":"Conference item"},{"id":"doi:10.48550/arxiv.1402.6516","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1402.6516","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.3115/v1/e14-1013","is_oa":true,"landing_page_url":"https://doi.org/10.3115/v1/e14-1013","pdf_url":"https://aclanthology.org/E14-1013.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 14th Conference of the European Chapter of the Association for Computational Linguistics","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W1621942032.pdf","grobid_xml":"https://content.openalex.org/works/W1621942032.grobid-xml"},"referenced_works_count":20,"referenced_works":["https://openalex.org/W1501586228","https://openalex.org/W1517951867","https://openalex.org/W1551324301","https://openalex.org/W1574126082","https://openalex.org/W1632114991","https://openalex.org/W1909733559","https://openalex.org/W2018789714","https://openalex.org/W2027979924","https://openalex.org/W2099873701","https://openalex.org/W2100796029","https://openalex.org/W2104441213","https://openalex.org/W2108622839","https://openalex.org/W2112861996","https://openalex.org/W2121227244","https://openalex.org/W2142523187","https://openalex.org/W2144508908","https://openalex.org/W2154099718","https://openalex.org/W2154368244","https://openalex.org/W2159399018","https://openalex.org/W2166044723"],"related_works":["https://openalex.org/W2963432269","https://openalex.org/W2089436184","https://openalex.org/W2107038437","https://openalex.org/W3037945766","https://openalex.org/W2107440560","https://openalex.org/W2774843407","https://openalex.org/W2905102582","https://openalex.org/W1908479511","https://openalex.org/W2576081183","https://openalex.org/W1962902644","https://openalex.org/W2780012921","https://openalex.org/W2252024278","https://openalex.org/W2950415592","https://openalex.org/W2573665311","https://openalex.org/W3207789057","https://openalex.org/W2949237929","https://openalex.org/W2397390277","https://openalex.org/W3021713638","https://openalex.org/W2183207781","https://openalex.org/W2143078730"],"abstract_inverted_index":{"Automatically":[0],"inducing":[1,111],"the":[2,18,32,54,97,125,145],"syntactic":[3,78],"part-of-speech":[4,48],"categories":[5],"for":[6,66,121],"words":[7],"in":[8,14],"text":[9],"is":[10,73,139],"a":[11,40,46,67,85,107,118],"fundamental":[12],"task":[13],"Computational":[15],"Linguistics.":[16],"While":[17],"performance":[19],"of":[20,39,56,96,127],"unsupervised":[21],"tagging":[22],"models":[23],"has":[24],"been":[25],"slowly":[26],"improving,":[27],"current":[28],"state-of-the-art":[29,86,146],"systems":[30],"make":[31],"obviously":[33],"incorrect":[34],"assumption":[35],"that":[36,134,136],"all":[37],"tokens":[38],"given":[41,68],"word":[42,69],"type":[43],"must":[44],"share":[45],"single":[47],"tag.":[49],"This":[50],"one-tag-per-type":[51],"heuristic":[52],"counters":[53],"tendency":[55],"Hidden":[57,88],"Markov":[58,89],"Model":[59,90],"based":[60],"taggers":[61],"to":[62,105],"over":[63],"generate":[64],"tags":[65,113],"type.":[70,115],"However,":[71],"it":[72],"clearly":[74],"incompatible":[75],"with":[76,92,141],"basic":[77],"theory.":[79],"In":[80,99],"this":[81],"paper":[82],"we":[83,102],"extend":[84],"Pitman-Yor":[87],"tagger":[91],"an":[93],"explicit":[94],"model":[95,129,138],"lexicon.":[98],"doing":[100],"so":[101],"are":[103],"able":[104],"incorporate":[106],"soft":[108],"bias":[109],"towards":[110],"few":[112],"per":[114],"We":[116],"develop":[117],"particle":[119],"filter":[120],"drawing":[122],"samples":[123],"from":[124],"posterior":[126],"our":[128,137],"and":[130,142],"present":[131],"empirical":[132],"results":[133],"show":[135],"competitive":[140],"faster":[143],"than":[144],"without":[147],"making":[148],"any":[149],"unrealistic":[150],"restrictions.":[151]},"counts_by_year":[],"updated_date":"2026-02-09T09:26:11.010843","created_date":"2025-10-10T00:00:00"}