{"id":"https://openalex.org/W2101406128","doi":"https://doi.org/10.3115/v1/p14-2044","title":"POS induction with distributional and morphological information using a distance-dependent Chinese restaurant process","display_name":"POS induction with distributional and morphological information using a distance-dependent Chinese restaurant process","publication_year":2014,"publication_date":"2014-01-01","ids":{"openalex":"https://openalex.org/W2101406128","doi":"https://doi.org/10.3115/v1/p14-2044","mag":"2101406128"},"language":"en","primary_location":{"id":"doi:10.3115/v1/p14-2044","is_oa":true,"landing_page_url":"https://doi.org/10.3115/v1/p14-2044","pdf_url":"https://aclanthology.org/P14-2044.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 52nd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/P14-2044.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5035358986","display_name":"Kairit Sirts","orcid":"https://orcid.org/0000-0001-7388-2583"},"institutions":[{"id":"https://openalex.org/I111112146","display_name":"Tallinn University of Technology","ror":"https://ror.org/0443cwa12","country_code":"EE","type":"education","lineage":["https://openalex.org/I111112146"]},{"id":"https://openalex.org/I2799600557","display_name":"Japan External Trade Organization","ror":"https://ror.org/0480zh114","country_code":"JP","type":"government","lineage":["https://openalex.org/I1287223417","https://openalex.org/I2799600557"]}],"countries":["EE","JP"],"is_corresponding":false,"raw_author_name":"Kairit Sirts","raw_affiliation_strings":["Institute of Cybernetics at Tallinn University of Technology","external organisation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Cybernetics at Tallinn University of Technology","institution_ids":["https://openalex.org/I111112146"]},{"raw_affiliation_string":"external organisation","institution_ids":["https://openalex.org/I2799600557"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047699861","display_name":"Jacob Eisenstein","orcid":null},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jacob Eisenstein","raw_affiliation_strings":["School of Interactive Computing Georgia Institute of Technology","[Georgia Institute of Technology.]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Interactive Computing Georgia Institute of Technology","institution_ids":["https://openalex.org/I130701444"]},{"raw_affiliation_string":"[Georgia Institute of Technology.]","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017409643","display_name":"Micha Elsner","orcid":"https://orcid.org/0000-0002-1432-2129"},"institutions":[{"id":"https://openalex.org/I175594653","display_name":"John Brown University","ror":"https://ror.org/02ct41q97","country_code":"US","type":"education","lineage":["https://openalex.org/I175594653"]},{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Micha Elsner","raw_affiliation_strings":["Department of Linguistics The Ohio State University","Brown University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Linguistics The Ohio State University","institution_ids":["https://openalex.org/I52357470"]},{"raw_affiliation_string":"Brown University","institution_ids":["https://openalex.org/I175594653"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5075564798","display_name":"Sharon Goldwater","orcid":"https://orcid.org/0000-0002-7298-0947"},"institutions":[{"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":"Sharon Goldwater","raw_affiliation_strings":["ILCC, School of Informatics University of Edinburgh","University of Edinburgh"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ILCC, School of Informatics University of Edinburgh","institution_ids":["https://openalex.org/I98677209"]},{"raw_affiliation_string":"University of Edinburgh","institution_ids":["https://openalex.org/I98677209"]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.2687,"has_fulltext":true,"cited_by_count":7,"citation_normalized_percentile":{"value":0.85632232,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"265","last_page":"271"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9980000257492065,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9918000102043152,"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":0.6477629542350769},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.630983829498291},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6121998429298401},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5468246340751648},{"id":"https://openalex.org/keywords/nonparametric-statistics","display_name":"Nonparametric statistics","score":0.5359988808631897},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5172699093818665},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.5126758813858032},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.41823461651802063},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.41583746671676636},{"id":"https://openalex.org/keywords/joint-probability-distribution","display_name":"Joint probability distribution","score":0.41408926248550415},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2856147289276123},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.14721769094467163}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6477629542350769},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.630983829498291},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6121998429298401},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5468246340751648},{"id":"https://openalex.org/C102366305","wikidata":"https://www.wikidata.org/wiki/Q1097688","display_name":"Nonparametric statistics","level":2,"score":0.5359988808631897},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5172699093818665},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.5126758813858032},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.41823461651802063},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.41583746671676636},{"id":"https://openalex.org/C18653775","wikidata":"https://www.wikidata.org/wiki/Q1333358","display_name":"Joint probability distribution","level":2,"score":0.41408926248550415},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2856147289276123},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.14721769094467163},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.3115/v1/p14-2044","is_oa":true,"landing_page_url":"https://doi.org/10.3115/v1/p14-2044","pdf_url":"https://aclanthology.org/P14-2044.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 52nd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.653.7679","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.653.7679","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/P/P14/P14-2044.pdf","raw_type":"text"},{"id":"pmh:oai:pure.ed.ac.uk:openaire/d916b351-cffd-4973-b5b0-3b617fe444b5","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/d916b351-cffd-4973-b5b0-3b617fe444b5","pdf_url":null,"source":{"id":"https://openalex.org/S4406922455","display_name":"Edinburgh Research Explorer","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Sirts, K, Eisenstein, J, Elsner, M & Goldwater, S 2014, POS induction with distributional and morphological information using a distance-dependent Chinese restaurant process. in Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers). Baltimore, Maryland, pp. 265-271. < http://www.aclweb.org/anthology/P/P14/P14-2044.pdf >","raw_type":"contributionToPeriodical"},{"id":"pmh:oai:pure.ed.ac.uk:publications/d916b351-cffd-4973-b5b0-3b617fe444b5","is_oa":false,"landing_page_url":"https://www.research.ed.ac.uk/portal/en/publications/pos-induction-with-distributional-and-morphological-information-using-a-distancedependent-chinese-restaurant-process(d916b351-cffd-4973-b5b0-3b617fe444b5).html","pdf_url":null,"source":{"id":"https://openalex.org/S4406922455","display_name":"Edinburgh Research Explorer","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""}],"best_oa_location":{"id":"doi:10.3115/v1/p14-2044","is_oa":true,"landing_page_url":"https://doi.org/10.3115/v1/p14-2044","pdf_url":"https://aclanthology.org/P14-2044.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 52nd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320322700","display_name":"Hariduse Infotehnoloogia Sihtasutus","ror":"https://ror.org/02e2avb86"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2101406128.pdf","grobid_xml":"https://content.openalex.org/works/W2101406128.grobid-xml"},"referenced_works_count":28,"referenced_works":["https://openalex.org/W1523296404","https://openalex.org/W1551324301","https://openalex.org/W1626542014","https://openalex.org/W1831478036","https://openalex.org/W1909733559","https://openalex.org/W1972805353","https://openalex.org/W2018789714","https://openalex.org/W2045344178","https://openalex.org/W2078058974","https://openalex.org/W2104441213","https://openalex.org/W2107959623","https://openalex.org/W2108622839","https://openalex.org/W2110799598","https://openalex.org/W2120636621","https://openalex.org/W2138615112","https://openalex.org/W2141599568","https://openalex.org/W2142119958","https://openalex.org/W2142590786","https://openalex.org/W2143995218","https://openalex.org/W2147448291","https://openalex.org/W2150195756","https://openalex.org/W2158139315","https://openalex.org/W2251012068","https://openalex.org/W2252158512","https://openalex.org/W2615915281","https://openalex.org/W2916021403","https://openalex.org/W2963216505","https://openalex.org/W4245883374"],"related_works":["https://openalex.org/W4243114048","https://openalex.org/W2529605301","https://openalex.org/W4237896776","https://openalex.org/W4231665652","https://openalex.org/W1837630526","https://openalex.org/W2000242494","https://openalex.org/W2335589441","https://openalex.org/W4296826658","https://openalex.org/W1979697693","https://openalex.org/W2010857194"],"abstract_inverted_index":{"We":[0],"present":[1],"a":[2,19,38],"new":[3],"approach":[4],"to":[5,70],"inducing":[6,65],"the":[7,26,44,48,58,73],"syntactic":[8],"categories":[9],"of":[10,41,50,57],"words,":[11],"combining":[12],"their":[13],"distributional":[14,74],"and":[15],"morphological":[16,42],"properties":[17],"in":[18],"joint":[20],"nonparametric":[21],"Bayesian":[22],"model":[23,40,60],"based":[24],"on":[25,82],"distance-dependent":[27],"Chinese":[28],"Restaurant":[29],"Process.":[30],"The":[31,55,76],"prior":[32],"distribution":[33],"over":[34],"word":[35,53],"clusterings":[36],"uses":[37],"log-linear":[39],"similarity;":[43],"likelihood":[45],"function":[46],"is":[47],"probability":[49],"generating":[51],"vector":[52],"embeddings.":[54],"weights":[56],"morphology":[59],"are":[61],"learned":[62],"jointly":[63],"while":[64],"part-ofspeech":[66],"clusters,":[67],"encouraging":[68],"them":[69],"cohere":[71],"with":[72],"features.":[75],"resulting":[77],"algorithm":[78],"outperforms":[79],"competitive":[80],"alternatives":[81],"English":[83],"POS":[84],"induction.":[85]},"counts_by_year":[{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":3},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}