{"id":"https://openalex.org/W2911295364","doi":"https://doi.org/10.1145/3308558.3313437","title":"Neural Chinese Word Segmentation with Lexicon and Unlabeled Data via Posterior Regularization","display_name":"Neural Chinese Word Segmentation with Lexicon and Unlabeled Data via Posterior Regularization","publication_year":2019,"publication_date":"2019-05-13","ids":{"openalex":"https://openalex.org/W2911295364","doi":"https://doi.org/10.1145/3308558.3313437","mag":"2911295364"},"language":"en","primary_location":{"id":"doi:10.1145/3308558.3313437","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3308558.3313437","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The World Wide Web Conference","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3308558.3313437","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5068189045","display_name":"Junxin Liu","orcid":"https://orcid.org/0009-0000-6634-4031"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junxin Liu","raw_affiliation_strings":["Tsinghua University Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076423724","display_name":"Fangzhao Wu","orcid":"https://orcid.org/0000-0001-9138-1272"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fangzhao Wu","raw_affiliation_strings":["Microsoft Research Asia Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001967239","display_name":"Chuhan Wu","orcid":"https://orcid.org/0000-0001-5730-8792"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chuhan Wu","raw_affiliation_strings":["Tsinghua University Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100768896","display_name":"Yongfeng Huang","orcid":"https://orcid.org/0000-0003-3825-2230"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yongfeng Huang","raw_affiliation_strings":["Tsinghua University Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044651577","display_name":"Xing Xie","orcid":"https://orcid.org/0000-0002-8608-8482"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xing Xie","raw_affiliation_strings":["Microsoft Research Asia Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.7654,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.7677123,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"3013","last_page":"3019"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9991999864578247,"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9911999702453613,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/lexicon","display_name":"Lexicon","score":0.7220248579978943},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7178082466125488},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6992413997650146},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5731210708618164},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.5469423532485962},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5216113328933716},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4995903968811035},{"id":"https://openalex.org/keywords/text-segmentation","display_name":"Text segmentation","score":0.439423143863678},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.4119647145271301},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3240678310394287}],"concepts":[{"id":"https://openalex.org/C2778121359","wikidata":"https://www.wikidata.org/wiki/Q8096","display_name":"Lexicon","level":2,"score":0.7220248579978943},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7178082466125488},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6992413997650146},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5731210708618164},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.5469423532485962},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5216113328933716},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4995903968811035},{"id":"https://openalex.org/C98501671","wikidata":"https://www.wikidata.org/wiki/Q1948408","display_name":"Text segmentation","level":3,"score":0.439423143863678},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.4119647145271301},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3240678310394287}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3308558.3313437","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3308558.3313437","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The World Wide Web Conference","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1905.01963","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1905.01963","pdf_url":"https://arxiv.org/pdf/1905.01963","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"doi:10.1145/3308558.3313437","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3308558.3313437","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The World Wide Web Conference","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.5600000023841858}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W1772464306","https://openalex.org/W2010576059","https://openalex.org/W2064675550","https://openalex.org/W2100259670","https://openalex.org/W2126504272","https://openalex.org/W2137281231","https://openalex.org/W2140016149","https://openalex.org/W2147880316","https://openalex.org/W2154368244","https://openalex.org/W2163377725","https://openalex.org/W2233994034","https://openalex.org/W2250542158","https://openalex.org/W2250739653","https://openalex.org/W2251811146","https://openalex.org/W2252066972","https://openalex.org/W2252225757","https://openalex.org/W2252264945","https://openalex.org/W2474916227","https://openalex.org/W2516334389","https://openalex.org/W2557387915","https://openalex.org/W2609232568","https://openalex.org/W2740603853","https://openalex.org/W2785522575","https://openalex.org/W2788824299","https://openalex.org/W2808482853","https://openalex.org/W2884150813","https://openalex.org/W2895520828","https://openalex.org/W2950577311","https://openalex.org/W2951037516","https://openalex.org/W2962860930","https://openalex.org/W2963077975","https://openalex.org/W2963355640","https://openalex.org/W2963593215","https://openalex.org/W2963917673","https://openalex.org/W2964093505","https://openalex.org/W2964352165","https://openalex.org/W3010865323","https://openalex.org/W3145501851","https://openalex.org/W6683955732","https://openalex.org/W6736544834","https://openalex.org/W6736812215"],"related_works":["https://openalex.org/W3136209078","https://openalex.org/W4392255232","https://openalex.org/W1522196789","https://openalex.org/W2978383222","https://openalex.org/W2172629291","https://openalex.org/W2380773642","https://openalex.org/W2384559435","https://openalex.org/W2337707338","https://openalex.org/W2785359773","https://openalex.org/W2058548953"],"abstract_inverted_index":{"Chinese":[0,8,48,70],"word":[1,26,71],"segmentation":[2,27,72],"(CWS)":[3],"is":[4,40,83],"very":[5],"important":[6],"for":[7,13,59,69],"text":[9],"processing.":[10],"Existing":[11],"methods":[12],"CWS":[14,112],"usually":[15,41],"rely":[16],"on":[17,85,116],"a":[18,66,86],"large":[19],"number":[20],"of":[21,53,88,111,129],"labeled":[22],"sentences":[23],"to":[24,34,43],"train":[25],"models,":[28],"which":[29,54,73],"are":[30,50,98],"expensive":[31],"and":[32,45,78,92,96,123],"time-consuming":[33],"annotate.":[35],"Luckily,":[36],"the":[37,93,108,127],"unlabeled":[38,79,94],"data":[39,95],"easy":[42],"collect":[44],"many":[46],"high-quality":[47],"lexicons":[49],"off-the-shelf,":[51],"both":[52,76,121],"can":[55,74],"provide":[56],"useful":[57],"information":[58],"CWS.":[60],"In":[61],"this":[62],"paper,":[63],"we":[64],"propose":[65],"neural":[67],"approach":[68,82],"exploit":[75],"lexicon":[77,97],"data.":[80],"Our":[81],"based":[84],"variant":[87],"posterior":[89],"regularization":[90],"algorithm,":[91],"incorporated":[99],"into":[100],"model":[101],"training":[102],"as":[103],"indirect":[104],"supervision":[105],"by":[106],"regularizing":[107],"prediction":[109],"space":[110],"models.":[113],"Extensive":[114],"experiments":[115],"multiple":[117],"benchmark":[118],"datasets":[119],"in":[120],"in-domain":[122],"cross-domain":[124],"scenarios":[125],"validate":[126],"effectiveness":[128],"our":[130],"approach.":[131]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2019-02-21T00:00:00"}