{"id":"https://openalex.org/W2905474383","doi":"https://doi.org/10.1609/aaai.v33i01.33017200","title":"Unsupervised Learning Helps Supervised Neural Word Segmentation","display_name":"Unsupervised Learning Helps Supervised Neural Word Segmentation","publication_year":2019,"publication_date":"2019-07-17","ids":{"openalex":"https://openalex.org/W2905474383","doi":"https://doi.org/10.1609/aaai.v33i01.33017200","mag":"2905474383"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v33i01.33017200","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v33i01.33017200","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/4704/4582","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://ojs.aaai.org/index.php/AAAI/article/download/4704/4582","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100604909","display_name":"Xiaobin Wang","orcid":"https://orcid.org/0009-0007-6809-8058"},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiaobin Wang","raw_affiliation_strings":["Alibaba Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061528283","display_name":"Deng Cai","orcid":"https://orcid.org/0000-0003-3444-8383"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Deng Cai","raw_affiliation_strings":["The Chinese University of Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100318930","display_name":"Linlin Li","orcid":"https://orcid.org/0009-0004-4985-2623"},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Linlin Li","raw_affiliation_strings":["Alibaba Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102028230","display_name":"Guangwei Xu","orcid":"https://orcid.org/0000-0002-8472-5572"},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Guangwei Xu","raw_affiliation_strings":["Alibaba Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036050911","display_name":"Hai Zhao","orcid":"https://orcid.org/0000-0001-7290-0487"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hai Zhao","raw_affiliation_strings":["Shanghai Jiao Tong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101718341","display_name":"Luo Si","orcid":"https://orcid.org/0000-0002-3263-234X"},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Luo Si","raw_affiliation_strings":["Alibaba Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group","institution_ids":["https://openalex.org/I4210095624"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":18,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"33","issue":"01","first_page":"7200","last_page":"7207"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","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"}},"topics":[{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","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/T10028","display_name":"Topic Modeling","score":0.9997000098228455,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9952999949455261,"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":0.8194873929023743},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.691277801990509},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.647642195224762},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5112755298614502},{"id":"https://openalex.org/keywords/unsupervised-learning","display_name":"Unsupervised learning","score":0.49794483184814453},{"id":"https://openalex.org/keywords/test-set","display_name":"Test set","score":0.4976373016834259},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.48568853735923767},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.48297253251075745},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.46700891852378845},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.46409764885902405},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4545419216156006},{"id":"https://openalex.org/keywords/labeled-data","display_name":"Labeled data","score":0.44639456272125244},{"id":"https://openalex.org/keywords/word-embedding","display_name":"Word embedding","score":0.4440877437591553},{"id":"https://openalex.org/keywords/test-data","display_name":"Test data","score":0.4394153952598572},{"id":"https://openalex.org/keywords/semi-supervised-learning","display_name":"Semi-supervised learning","score":0.4143671691417694},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.35080158710479736},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.34817057847976685},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07503211498260498}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8194873929023743},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.691277801990509},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.647642195224762},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5112755298614502},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.49794483184814453},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.4976373016834259},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.48568853735923767},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.48297253251075745},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.46700891852378845},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.46409764885902405},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4545419216156006},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.44639456272125244},{"id":"https://openalex.org/C2777462759","wikidata":"https://www.wikidata.org/wiki/Q18395344","display_name":"Word embedding","level":3,"score":0.4440877437591553},{"id":"https://openalex.org/C16910744","wikidata":"https://www.wikidata.org/wiki/Q7705759","display_name":"Test data","level":2,"score":0.4394153952598572},{"id":"https://openalex.org/C58973888","wikidata":"https://www.wikidata.org/wiki/Q1041418","display_name":"Semi-supervised learning","level":2,"score":0.4143671691417694},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.35080158710479736},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.34817057847976685},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07503211498260498},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"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:10.1609/aaai.v33i01.33017200","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v33i01.33017200","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/4704/4582","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},{"id":"pmh:oai:ojs.aaai.org:article/4704","is_oa":false,"landing_page_url":"https://ojs.aaai.org/index.php/AAAI/article/view/4704","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2159-5399","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v33i01.33017200","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v33i01.33017200","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/4704/4582","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.7699999809265137,"id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G1999725278","display_name":null,"funder_award_id":"No. 2017YFB0304100","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G2567398775","display_name":"\u9762\u5411\u5b64\u72ec\u75c7\u65e9\u671f\u8bca\u7597\u7684\u673a\u5668\u8f85\u52a9\u7cfb\u7edf\u5173\u952e\u6280\u672f\u7814\u7a76","funder_award_id":"61733011","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3289329514","display_name":null,"funder_award_id":"2017YFB0304100","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4276612039","display_name":null,"funder_award_id":"2017YFB0304100","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G6791796133","display_name":null,"funder_award_id":"No. 61733011","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/F4320322999","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2905474383.pdf","grobid_xml":"https://content.openalex.org/works/W2905474383.grobid-xml"},"referenced_works_count":45,"referenced_works":["https://openalex.org/W25062297","https://openalex.org/W1528203680","https://openalex.org/W1886814818","https://openalex.org/W1971678616","https://openalex.org/W2005828695","https://openalex.org/W2036516910","https://openalex.org/W2126377586","https://openalex.org/W2126504272","https://openalex.org/W2133556223","https://openalex.org/W2138136853","https://openalex.org/W2140991203","https://openalex.org/W2152104712","https://openalex.org/W2163377725","https://openalex.org/W2165664509","https://openalex.org/W2233994034","https://openalex.org/W2250739653","https://openalex.org/W2250799792","https://openalex.org/W2251811146","https://openalex.org/W2252225757","https://openalex.org/W2252264945","https://openalex.org/W2341695656","https://openalex.org/W2358307482","https://openalex.org/W2404744763","https://openalex.org/W2507296208","https://openalex.org/W2516334389","https://openalex.org/W2609232568","https://openalex.org/W2733040285","https://openalex.org/W2757350179","https://openalex.org/W2785522575","https://openalex.org/W2788824299","https://openalex.org/W2808482853","https://openalex.org/W2962885853","https://openalex.org/W2963355640","https://openalex.org/W2963628345","https://openalex.org/W2963842982","https://openalex.org/W2964093505","https://openalex.org/W2964269722","https://openalex.org/W2964352165","https://openalex.org/W3145501851","https://openalex.org/W6666761814","https://openalex.org/W6717968132","https://openalex.org/W6726140849","https://openalex.org/W6736544834","https://openalex.org/W6736812215","https://openalex.org/W6754069474"],"related_works":["https://openalex.org/W3148060700","https://openalex.org/W34092691","https://openalex.org/W2949671220","https://openalex.org/W2365028544","https://openalex.org/W4309984931","https://openalex.org/W4282977123","https://openalex.org/W2074435087","https://openalex.org/W2794908468","https://openalex.org/W2096363773","https://openalex.org/W2531570999"],"abstract_inverted_index":{"By":[0],"exploiting":[1],"unlabeled":[2,53,109,135],"data":[3,58,110],"for":[4,8,46],"further":[5],"performance":[6],"improvement":[7,96],"Chinese":[9],"word":[10,40],"segmentation,":[11],"this":[12],"work":[13],"makes":[14],"the":[15,35,39,62,67,76,80,84,104,118,122],"first":[16],"attempt":[17],"at":[18],"exploring":[19],"adding":[20],"unsupervised":[21,48],"segmentation":[22,77],"information":[23,49],"into":[24],"neural":[25],"supervised":[26],"segmenter.":[27],"We":[28],"survey":[29],"various":[30],"effective":[31],"strategies,":[32],"including":[33],"extending":[34],"character":[36],"embedding,":[37],"augmenting":[38],"score":[41],"and":[42,73,93],"applying":[43],"multi-task":[44],"learning,":[45],"leveraging":[47],"derived":[50],"from":[51],"abundant":[52,134],"data.":[54,136],"Experiments":[55],"on":[56],"standard":[57],"sets":[59],"show":[60],"that":[61],"explored":[63],"strategies":[64,102],"indeed":[65],"improve":[66],"recall":[68],"rate":[69],"of":[70,106,128,132],"out-of-vocabulary":[71],"words":[72],"thus":[74],"boost":[75],"accuracy.":[78],"Moreover,":[79],"model":[81],"enhanced":[82],"by":[83],"proposed":[85,119],"methods":[86],"outperforms":[87,121],"state-of-theart":[88],"models":[89],"in":[90,126],"closed":[91],"test":[92],"shows":[94],"promising":[95],"trend":[97],"when":[98],"adopting":[99],"three":[100],"different":[101],"with":[103],"help":[105],"a":[107],"large":[108],"set.":[111],"Our":[112],"thorough":[113],"empirical":[114],"study":[115],"eventually":[116],"verifies":[117],"approach":[120,125],"widelyused":[123],"pre-training":[124],"terms":[127],"effectively":[129],"making":[130],"use":[131],"freely":[133]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":4}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}