{"id":"https://openalex.org/W2914324790","doi":"https://doi.org/10.1145/3292398","title":"Unsupervised Joint PoS Tagging and Stemming for Agglutinative Languages","display_name":"Unsupervised Joint PoS Tagging and Stemming for Agglutinative Languages","publication_year":2019,"publication_date":"2019-01-25","ids":{"openalex":"https://openalex.org/W2914324790","doi":"https://doi.org/10.1145/3292398","mag":"2914324790"},"language":"en","primary_location":{"id":"doi:10.1145/3292398","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3292398","pdf_url":null,"source":{"id":"https://openalex.org/S4306421405","display_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","issn_l":"2375-4699","issn":["2375-4699","2375-4702"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://hdl.handle.net/2436/623587","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5021857737","display_name":"Necva B\u00f6l\u00fcc\u00fc","orcid":"https://orcid.org/0000-0001-8121-3048"},"institutions":[{"id":"https://openalex.org/I66514158","display_name":"Hacettepe University","ror":"https://ror.org/04kwvgz42","country_code":"TR","type":"education","lineage":["https://openalex.org/I66514158"]}],"countries":["TR"],"is_corresponding":false,"raw_author_name":"Necva B\u00f6l\u00fcc\u00fc","raw_affiliation_strings":["Hacettepe University, Turkey"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hacettepe University, Turkey","institution_ids":["https://openalex.org/I66514158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5046915242","display_name":"Burcu Can","orcid":"https://orcid.org/0000-0002-1700-0395"},"institutions":[{"id":"https://openalex.org/I66514158","display_name":"Hacettepe University","ror":"https://ror.org/04kwvgz42","country_code":"TR","type":"education","lineage":["https://openalex.org/I66514158"]}],"countries":["TR"],"is_corresponding":false,"raw_author_name":"Burcu Can","raw_affiliation_strings":["Hacettepe University, Turkey"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hacettepe University, Turkey","institution_ids":["https://openalex.org/I66514158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I66514158"],"apc_list":null,"apc_paid":null,"fwci":0.9883,"has_fulltext":false,"cited_by_count":26,"citation_normalized_percentile":{"value":0.81539298,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"18","issue":"3","first_page":"1","last_page":"21"},"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":0.9998000264167786,"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/T12031","display_name":"Speech and dialogue systems","score":0.9986000061035156,"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/agglutinative-language","display_name":"Agglutinative language","score":0.9823497533798218},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8516876697540283},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7080830931663513},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6990929841995239},{"id":"https://openalex.org/keywords/inflection","display_name":"Inflection","score":0.6805809736251831},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5345911383628845},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.48194122314453125},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.4760570228099823},{"id":"https://openalex.org/keywords/dependency","display_name":"Dependency (UML)","score":0.4256768226623535},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.36453187465667725},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.1916784942150116},{"id":"https://openalex.org/keywords/morpheme","display_name":"Morpheme","score":0.1059538722038269}],"concepts":[{"id":"https://openalex.org/C80875076","wikidata":"https://www.wikidata.org/wiki/Q171263","display_name":"Agglutinative language","level":3,"score":0.9823497533798218},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8516876697540283},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7080830931663513},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6990929841995239},{"id":"https://openalex.org/C159403335","wikidata":"https://www.wikidata.org/wiki/Q207857","display_name":"Inflection","level":2,"score":0.6805809736251831},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5345911383628845},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.48194122314453125},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.4760570228099823},{"id":"https://openalex.org/C19768560","wikidata":"https://www.wikidata.org/wiki/Q320727","display_name":"Dependency (UML)","level":2,"score":0.4256768226623535},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.36453187465667725},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.1916784942150116},{"id":"https://openalex.org/C165297611","wikidata":"https://www.wikidata.org/wiki/Q43249","display_name":"Morpheme","level":2,"score":0.1059538722038269},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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":2,"locations":[{"id":"doi:10.1145/3292398","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3292398","pdf_url":null,"source":{"id":"https://openalex.org/S4306421405","display_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","issn_l":"2375-4699","issn":["2375-4699","2375-4702"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","raw_type":"journal-article"},{"id":"pmh:oai:wlv.openrepository.com:2436/623587","is_oa":true,"landing_page_url":"http://hdl.handle.net/2436/623587","pdf_url":null,"source":{"id":"https://openalex.org/S4306401000","display_name":"Wolverhampton Intellectual Repository and E-Theses (University of Wolverhampton)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I119664326","host_organization_name":"University of Wolverhampton","host_organization_lineage":["https://openalex.org/I119664326"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"3","raw_type":"Journal article"}],"best_oa_location":{"id":"pmh:oai:wlv.openrepository.com:2436/623587","is_oa":true,"landing_page_url":"http://hdl.handle.net/2436/623587","pdf_url":null,"source":{"id":"https://openalex.org/S4306401000","display_name":"Wolverhampton Intellectual Repository and E-Theses (University of Wolverhampton)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I119664326","host_organization_name":"University of Wolverhampton","host_organization_lineage":["https://openalex.org/I119664326"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"3","raw_type":"Journal article"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.75,"id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G2772390588","display_name":null,"funder_award_id":"EEEAG-115E464","funder_id":"https://openalex.org/F4320322626","funder_display_name":"T\u00fcrkiye Bilimsel ve Teknolojik Ara\u015ft\u0131rma Kurumu"}],"funders":[{"id":"https://openalex.org/F4320322626","display_name":"T\u00fcrkiye Bilimsel ve Teknolojik Ara\u015ft\u0131rma Kurumu","ror":"https://ror.org/04w9kkr77"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":46,"referenced_works":["https://openalex.org/W26591655","https://openalex.org/W69919596","https://openalex.org/W1518332699","https://openalex.org/W1524281572","https://openalex.org/W1968951234","https://openalex.org/W2002639244","https://openalex.org/W2008495066","https://openalex.org/W2012376027","https://openalex.org/W2020999234","https://openalex.org/W2022146661","https://openalex.org/W2026227174","https://openalex.org/W2029097226","https://openalex.org/W2042143122","https://openalex.org/W2046224275","https://openalex.org/W2058200372","https://openalex.org/W2063390378","https://openalex.org/W2078058974","https://openalex.org/W2078957420","https://openalex.org/W2086699924","https://openalex.org/W2097645701","https://openalex.org/W2098162425","https://openalex.org/W2101406128","https://openalex.org/W2101711363","https://openalex.org/W2108622839","https://openalex.org/W2121227244","https://openalex.org/W2129620481","https://openalex.org/W2138958299","https://openalex.org/W2147448291","https://openalex.org/W2152561112","https://openalex.org/W2157305458","https://openalex.org/W2163514362","https://openalex.org/W2166044723","https://openalex.org/W2252078875","https://openalex.org/W2252128651","https://openalex.org/W2343954916","https://openalex.org/W2463261572","https://openalex.org/W2493775673","https://openalex.org/W2579343286","https://openalex.org/W2618735189","https://openalex.org/W2792932412","https://openalex.org/W2912300410","https://openalex.org/W2949259776","https://openalex.org/W2950133940","https://openalex.org/W2963625764","https://openalex.org/W3007285918","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2059264632","https://openalex.org/W2627000962","https://openalex.org/W4386566400","https://openalex.org/W2486362477","https://openalex.org/W2468511347","https://openalex.org/W3204939729","https://openalex.org/W4205390819","https://openalex.org/W2083217544","https://openalex.org/W1462364648","https://openalex.org/W2251935567"],"abstract_inverted_index":{"The":[0,185],"number":[1],"of":[2,35,91,102,153,163],"possible":[3],"word":[4,58,127,136,155],"forms":[5,59],"is":[6,69],"theoretically":[7],"infinite":[8],"in":[9,23,96,205],"agglutinative":[10,24,206],"languages.":[11,25,207],"This":[12],"brings":[13],"up":[14],"the":[15,32,53,82,92,100,106,110,131,135,142,150,161],"out-of-vocabulary":[16],"(OOV)":[17],"issue":[18],"for":[19,78,192],"part-of-speech":[20],"(PoS)":[21],"tagging":[22,80,176,194],"Since":[26],"inflectional":[27],"morphology":[28],"does":[29,158],"not":[30,159],"change":[31,160],"PoS":[33,45,79,115,119,175,193,201],"tag":[34],"a":[36,65,74,154,164,189],"word,":[37],"we":[38,49,124],"propose":[39],"to":[40,51,98,129,148],"learn":[41],"stems":[42,83,113],"along":[43],"with":[44,170],"tags":[46,116,120],"simultaneously.":[47],"Therefore,":[48],"aim":[50],"overcome":[52],"sparsity":[54],"problem":[55],"by":[56],"reducing":[57],"into":[60],"their":[61],"stems.":[62],"We":[63,72,140,166],"adopt":[64],"Bayesian":[66],"model":[67,93,191],"that":[68,188],"fully":[70],"unsupervised.":[71],"build":[73],"Hidden":[75],"Markov":[76],"Model":[77],"where":[81],"are":[84,94],"emitted":[85],"through":[86],"hidden":[87],"states.":[88],"Several":[89],"versions":[90],"introduced":[95],"order":[97],"observe":[99],"effects":[101],"different":[103],"dependencies":[104],"throughout":[105],"corpus,":[107],"such":[108],"as":[109,145],"dependency":[111],"between":[112,118,134],"and":[114,121,138,174,183,195,203],"or":[117],"affixes.":[122],"Additionally,":[123],"use":[125,141],"neural":[126],"embeddings":[128],"estimate":[130],"semantic":[132,143],"similarity":[133,144],"form":[137],"stem.":[139],"prior":[146],"information":[147],"discover":[149],"actual":[151],"stem":[152],"since":[156],"inflection":[157],"meaning":[162],"word.":[165],"compare":[167],"our":[168],"models":[169,177],"other":[171],"unsupervised":[172],"stemming":[173,196],"on":[178,198],"Turkish,":[179],"Hungarian,":[180],"Finnish,":[181],"Basque,":[182],"English.":[184],"results":[186],"show":[187],"joint":[190],"improves":[197],"an":[199],"independent":[200],"tagger":[202],"stemmer":[204]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":10},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}
