{"id":"https://openalex.org/W2138136853","doi":"https://doi.org/10.3115/v1/d14-1092","title":"A Joint Model for Unsupervised Chinese Word Segmentation","display_name":"A Joint Model for Unsupervised Chinese Word Segmentation","publication_year":2014,"publication_date":"2014-01-01","ids":{"openalex":"https://openalex.org/W2138136853","doi":"https://doi.org/10.3115/v1/d14-1092","mag":"2138136853"},"language":"en","primary_location":{"id":"doi:10.3115/v1/d14-1092","is_oa":true,"landing_page_url":"https://doi.org/10.3115/v1/d14-1092","pdf_url":"https://aclanthology.org/D14-1092.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 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/D14-1092.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5041741521","display_name":"Miaohong Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Miaohong Chen","raw_affiliation_strings":["Key Laboratory of Computational Linguistics, Ministry of Education School of Electronics Engineering and Computer Science, Peking University Beijing, P.R.China, 100871","Peking University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Key Laboratory of Computational Linguistics, Ministry of Education School of Electronics Engineering and Computer Science, Peking University Beijing, P.R.China, 100871","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021459300","display_name":"Baobao Chang","orcid":"https://orcid.org/0000-0003-2824-6750"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Baobao Chang","raw_affiliation_strings":["Key Laboratory of Computational Linguistics, Ministry of Education School of Electronics Engineering and Computer Science, Peking University Beijing, P.R.China, 100871","Peking University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Key Laboratory of Computational Linguistics, Ministry of Education School of Electronics Engineering and Computer Science, Peking University Beijing, P.R.China, 100871","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5068087759","display_name":"Wenzhe Pei","orcid":"https://orcid.org/0000-0002-0823-6793"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenzhe Pei","raw_affiliation_strings":["Key Laboratory of Computational Linguistics, Ministry of Education School of Electronics Engineering and Computer Science, Peking University Beijing, P.R.China, 100871","Peking University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Key Laboratory of Computational Linguistics, Ministry of Education School of Electronics Engineering and Computer Science, Peking University Beijing, P.R.China, 100871","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I20231570"],"apc_list":null,"apc_paid":null,"fwci":1.0339,"has_fulltext":true,"cited_by_count":19,"citation_normalized_percentile":{"value":0.78804582,"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":"854","last_page":"863"},"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":0.9993000030517578,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9944000244140625,"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":0.7773868441581726},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.731464684009552},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6609832048416138},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6106545925140381},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5719473361968994},{"id":"https://openalex.org/keywords/text-segmentation","display_name":"Text segmentation","score":0.5692070722579956},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5494786500930786},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.39647313952445984},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3274202346801758},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.12903302907943726},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07243499159812927}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7773868441581726},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.731464684009552},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6609832048416138},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6106545925140381},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5719473361968994},{"id":"https://openalex.org/C98501671","wikidata":"https://www.wikidata.org/wiki/Q1948408","display_name":"Text segmentation","level":3,"score":0.5692070722579956},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5494786500930786},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.39647313952445984},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3274202346801758},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.12903302907943726},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07243499159812927},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.3115/v1/d14-1092","is_oa":true,"landing_page_url":"https://doi.org/10.3115/v1/d14-1092","pdf_url":"https://aclanthology.org/D14-1092.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 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.684.694","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.684.694","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://emnlp2014.org/papers/pdf/EMNLP2014092.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.697.6268","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.697.6268","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/D/D14/D14-1092.pdf","raw_type":"text"}],"best_oa_location":{"id":"doi:10.3115/v1/d14-1092","is_oa":true,"landing_page_url":"https://doi.org/10.3115/v1/d14-1092","pdf_url":"https://aclanthology.org/D14-1092.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 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4896575247","display_name":null,"funder_award_id":"2014CB340504","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320324787","display_name":"Peking University","ror":"https://ror.org/02v51f717"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W25062297","https://openalex.org/W203625351","https://openalex.org/W1528203680","https://openalex.org/W2036516910","https://openalex.org/W2079182758","https://openalex.org/W2092977545","https://openalex.org/W2100163972","https://openalex.org/W2126377586","https://openalex.org/W2132961219","https://openalex.org/W2140991203","https://openalex.org/W2152104712","https://openalex.org/W2154756108","https://openalex.org/W2163377725","https://openalex.org/W2163738067","https://openalex.org/W2251479516","https://openalex.org/W2358307482","https://openalex.org/W2404744763","https://openalex.org/W2405762604","https://openalex.org/W2467575451","https://openalex.org/W2913521711","https://openalex.org/W3145501851","https://openalex.org/W4231517135"],"related_works":["https://openalex.org/W3107474891","https://openalex.org/W4206076898","https://openalex.org/W2510758617","https://openalex.org/W2897195263","https://openalex.org/W2357339972","https://openalex.org/W2161919705","https://openalex.org/W4226401448","https://openalex.org/W2754350655","https://openalex.org/W2951061418","https://openalex.org/W2804033347"],"abstract_inverted_index":{"In":[0,54],"this":[1],"paper,":[2],"we":[3,64],"propose":[4],"a":[5,146],"joint":[6,22,70,104,143],"model":[7,23,35,52,71,105,144],"for":[8,51],"unsupervised":[9],"Chinese":[10,157],"word":[11,158],"segmentation":[12],"(CWS).":[13],"Inspired":[14],"by":[15,41,72,90],"the":[16,59,77,91,103,130,142],"\"products":[17],"of":[18,61,112],"experts\"":[19],"idea,":[20],"our":[21,69,82],"firstly":[24],"combines":[25],"two":[26,99],"generative":[27],"models,":[28],"which":[29],"are":[30],"word-based":[31],"hierarchical":[32],"Dirichlet":[33],"process":[34],"and":[36,86,140,153],"character-based":[37],"hidden":[38],"Markov":[39],"model,":[40,63],"simply":[42],"multiplying":[43],"their":[44],"probabilities":[45],"together.":[46],"Gibbs":[47,78],"sampling":[48],"is":[49,123],"used":[50],"inference.":[53],"order":[55],"to":[56,75,149],"further":[57],"combine":[58],"strength":[60],"goodness-based":[62],"then":[65],"integrated":[66],"nVBE":[67,139],"into":[68],"using":[73],"it":[74,122],"initializing":[76],"sampler.":[79],"We":[80],"conduct":[81],"experiments":[83],"on":[84,97],"PKU":[85],"MSRA":[87],"datasets":[88,100],"provided":[89],"second":[92],"SIGHAN":[93],"bakeoff.":[94],"Test":[95],"results":[96,109],"these":[98],"show":[101,120],"that":[102,121,136],"achieves":[106],"much":[107],"better":[108,125],"than":[110,126],"all":[111],"its":[113],"component":[114],"models.":[115],"Statistical":[116],"significance":[117],"tests":[118],"also":[119],"significantly":[124],"stateof-the-art":[127],"systems,":[128],"achieving":[129],"highest":[131],"F-scores.":[132],"Finally,":[133],"analysis":[134],"indicates":[135],"compared":[137],"with":[138],"HDP,":[141],"has":[145],"stronger":[147],"ability":[148],"solve":[150],"both":[151],"combinational":[152],"overlapping":[154],"ambiguities":[155],"in":[156],"segmentation.":[159]},"counts_by_year":[{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}