{"id":"https://openalex.org/W2733040285","doi":"https://doi.org/10.1162/tacl_a_00054","title":"Nonparametric Bayesian Semi-supervised Word Segmentation","display_name":"Nonparametric Bayesian Semi-supervised Word Segmentation","publication_year":2017,"publication_date":"2017-12-01","ids":{"openalex":"https://openalex.org/W2733040285","doi":"https://doi.org/10.1162/tacl_a_00054","mag":"2733040285"},"language":"en","primary_location":{"id":"doi:10.1162/tacl_a_00054","is_oa":true,"landing_page_url":"https://doi.org/10.1162/tacl_a_00054","pdf_url":"http://www.mitpressjournals.org/doi/pdf/10.1162/tacl_a_00054","source":{"id":"https://openalex.org/S2729999759","display_name":"Transactions of the Association for Computational Linguistics","issn_l":"2307-387X","issn":["2307-387X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Transactions of the Association for Computational Linguistics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"http://www.mitpressjournals.org/doi/pdf/10.1162/tacl_a_00054","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5076720835","display_name":"Ryo Fujii","orcid":"https://orcid.org/0000-0002-9115-8414"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Ryo Fujii","raw_affiliation_strings":["Hakuhodo Inc. R&D Division, 5-3-1 Akasaka, Minato-ku, Tokyo,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hakuhodo Inc. R&D Division, 5-3-1 Akasaka, Minato-ku, Tokyo,","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062079967","display_name":"Ryo Domoto","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Ryo Domoto","raw_affiliation_strings":["Hakuhodo Inc. R&D Division, 5-3-1 Akasaka, Minato-ku, Tokyo,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hakuhodo Inc. R&D Division, 5-3-1 Akasaka, Minato-ku, Tokyo,","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078855310","display_name":"Daichi Mochihashi","orcid":"https://orcid.org/0000-0003-0344-5382"},"institutions":[{"id":"https://openalex.org/I4210134673","display_name":"The Institute of Statistical Mathematics","ror":"https://ror.org/03jcejr58","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1319490839","https://openalex.org/I4210134673","https://openalex.org/I4210158934"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Daichi Mochihashi","raw_affiliation_strings":["The Institute of Statistical Mathematics, 10-3 Midori-cho, Tachikawa city,                         Tokyo,","The Institute of Statistical Mathematics, 10-3 Midori-cho, Tachikawa city,\n Tokyo,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Institute of Statistical Mathematics, 10-3 Midori-cho, Tachikawa city,                         Tokyo,","institution_ids":["https://openalex.org/I4210134673"]},{"raw_affiliation_string":"The Institute of Statistical Mathematics, 10-3 Midori-cho, Tachikawa city,\n Tokyo,","institution_ids":["https://openalex.org/I4210134673"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5062079967","https://openalex.org/A5076720835","https://openalex.org/A5078855310"],"corresponding_institution_ids":["https://openalex.org/I4210134673"],"apc_list":null,"apc_paid":null,"fwci":1.4564,"has_fulltext":true,"cited_by_count":11,"citation_normalized_percentile":{"value":0.86691404,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"5","issue":null,"first_page":"179","last_page":"189"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9991999864578247,"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":0.9991999864578247,"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":0.996999979019165,"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/T11901","display_name":"Bayesian Methods and Mixture Models","score":0.9955000281333923,"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/discriminative-model","display_name":"Discriminative model","score":0.8642027378082275},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8331251740455627},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7097493410110474},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.6770867109298706},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5945496559143066},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5495048761367798},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4996802806854248},{"id":"https://openalex.org/keywords/text-segmentation","display_name":"Text segmentation","score":0.47611531615257263},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4613741636276245},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.4423925280570984},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3356199860572815},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07495138049125671}],"concepts":[{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.8642027378082275},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8331251740455627},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7097493410110474},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6770867109298706},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5945496559143066},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5495048761367798},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4996802806854248},{"id":"https://openalex.org/C98501671","wikidata":"https://www.wikidata.org/wiki/Q1948408","display_name":"Text segmentation","level":3,"score":0.47611531615257263},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4613741636276245},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.4423925280570984},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3356199860572815},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07495138049125671},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1162/tacl_a_00054","is_oa":true,"landing_page_url":"https://doi.org/10.1162/tacl_a_00054","pdf_url":"http://www.mitpressjournals.org/doi/pdf/10.1162/tacl_a_00054","source":{"id":"https://openalex.org/S2729999759","display_name":"Transactions of the Association for Computational Linguistics","issn_l":"2307-387X","issn":["2307-387X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Transactions of the Association for Computational Linguistics","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:9b1cc390c2f44261afe0855b6a7e7a74","is_oa":false,"landing_page_url":"https://doaj.org/article/9b1cc390c2f44261afe0855b6a7e7a74","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","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":"Transactions of the Association for Computational Linguistics, Vol 5 (2021)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1162/tacl_a_00054","is_oa":true,"landing_page_url":"https://doi.org/10.1162/tacl_a_00054","pdf_url":"http://www.mitpressjournals.org/doi/pdf/10.1162/tacl_a_00054","source":{"id":"https://openalex.org/S2729999759","display_name":"Transactions of the Association for Computational Linguistics","issn_l":"2307-387X","issn":["2307-387X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Transactions of the Association for Computational Linguistics","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.7699999809265137}],"awards":[],"funders":[{"id":"https://openalex.org/F4320324787","display_name":"Peking University","ror":"https://ror.org/02v51f717"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2733040285.pdf","grobid_xml":"https://content.openalex.org/works/W2733040285.grobid-xml"},"referenced_works_count":29,"referenced_works":["https://openalex.org/W10704533","https://openalex.org/W25062297","https://openalex.org/W91088564","https://openalex.org/W165283731","https://openalex.org/W1486212465","https://openalex.org/W1539673959","https://openalex.org/W1578488390","https://openalex.org/W2055226328","https://openalex.org/W2072634211","https://openalex.org/W2100052949","https://openalex.org/W2100768664","https://openalex.org/W2102301788","https://openalex.org/W2105908356","https://openalex.org/W2107240889","https://openalex.org/W2122228338","https://openalex.org/W2126504272","https://openalex.org/W2132957691","https://openalex.org/W2140177290","https://openalex.org/W2140991203","https://openalex.org/W2147880316","https://openalex.org/W2154099718","https://openalex.org/W2154292407","https://openalex.org/W2158188757","https://openalex.org/W2162465526","https://openalex.org/W2251362855","https://openalex.org/W2251563156","https://openalex.org/W2484412399","https://openalex.org/W2516334389","https://openalex.org/W4245883374"],"related_works":["https://openalex.org/W1487808658","https://openalex.org/W2393940967","https://openalex.org/W2159591557","https://openalex.org/W2385598138","https://openalex.org/W2366925922","https://openalex.org/W2346578824","https://openalex.org/W2905950556","https://openalex.org/W2112534334","https://openalex.org/W2115592387","https://openalex.org/W120168696"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"a":[3,32,49,69,87],"novel":[4],"hybrid":[5,66],"generative/discriminative":[6],"model":[7,29,67,95],"of":[8,35,90],"word":[9,19,79],"segmentation":[10,20,80],"based":[11],"on":[12,24,126],"nonparametric":[13],"Bayesian":[14],"methods.":[15],"Unlike":[16],"ordinary":[17],"discriminative":[18,70],"which":[21],"relies":[22],"only":[23],"labeled":[25,50],"data,":[26],"our":[27,65],"semi-supervised":[28,99],"also":[30],"leverages":[31],"huge":[33],"amounts":[34],"unlabeled":[36],"text":[37],"to":[38,52],"automatically":[39],"learn":[40],"new":[41],"\u201cwords\u201d,":[42],"and":[43,77,103,119,121,132],"further":[44],"constrains":[45],"them":[46],"by":[47],"using":[48],"data":[51],"segment":[53,112],"non-standard":[54,113],"texts":[55,114],"such":[56],"as":[57],"those":[58,116],"found":[59],"in":[60,117,129],"social":[61],"networking":[62],"services.":[63],"Specifically,":[64],"combines":[68],"classifier":[71],"(CRF;":[72],"Lafferty":[73],"et":[74,83],"al.":[75,84],"(2001)":[76],"unsupervised":[78],"(NPYLM;":[81],"Mochihashi":[82],"(2009)),":[85],"with":[86],"transparent":[88],"exchange":[89],"information":[91],"between":[92],"these":[93],"two":[94],"structures":[96],"within":[97],"the":[98],"framework":[100],"(JESS-CM;":[101],"Suzuki":[102],"Isozaki":[104],"(2008)).":[105],"We":[106],"confirmed":[107],"that":[108],"it":[109],"can":[110],"appropriately":[111],"like":[115],"Twitter":[118],"Weibo":[120],"has":[122],"nearly":[123],"state-of-the-art":[124],"accuracy":[125],"standard":[127],"datasets":[128],"Japanese,":[130],"Chinese,":[131],"Thai.":[133]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":3}],"updated_date":"2026-05-06T08:25:59.206177","created_date":"2025-10-10T00:00:00"}