{"id":"https://openalex.org/W2912691650","doi":"https://doi.org/10.1145/3308558.3313743","title":"Neural Chinese Named Entity Recognition via CNN-LSTM-CRF and Joint Training with Word Segmentation","display_name":"Neural Chinese Named Entity Recognition via CNN-LSTM-CRF and Joint Training with Word Segmentation","publication_year":2019,"publication_date":"2019-05-13","ids":{"openalex":"https://openalex.org/W2912691650","doi":"https://doi.org/10.1145/3308558.3313743","mag":"2912691650"},"language":"en","primary_location":{"id":"doi:10.1145/3308558.3313743","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3308558.3313743","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/10.1145/3308558.3313743","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Fangzhao Wu","orcid":null},"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":null,"display_name":"Junxin Liu","orcid":null},"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":null,"display_name":"Chuhan Wu","orcid":null},"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":null,"display_name":"Yongfeng Huang","orcid":null},"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":null,"display_name":"Xing Xie","orcid":null},"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":3.827,"has_fulltext":false,"cited_by_count":77,"citation_normalized_percentile":{"value":0.95180372,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"3342","last_page":"3348"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","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/T10028","display_name":"Topic Modeling","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/T10181","display_name":"Natural Language Processing Techniques","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/T11550","display_name":"Text and Document Classification Technologies","score":0.9670000076293945,"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/named-entity-recognition","display_name":"Named-entity recognition","score":0.7408000230789185},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.656000018119812},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5622000098228455},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5289999842643738},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5260000228881836},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4749999940395355},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.45329999923706055},{"id":"https://openalex.org/keywords/text-segmentation","display_name":"Text segmentation","score":0.4465000033378601},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.43959999084472656}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8689000010490417},{"id":"https://openalex.org/C2779135771","wikidata":"https://www.wikidata.org/wiki/Q403574","display_name":"Named-entity recognition","level":3,"score":0.7408000230789185},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6617000102996826},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.656000018119812},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6320000290870667},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5622000098228455},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5289999842643738},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5260000228881836},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4749999940395355},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.45329999923706055},{"id":"https://openalex.org/C98501671","wikidata":"https://www.wikidata.org/wiki/Q1948408","display_name":"Text segmentation","level":3,"score":0.4465000033378601},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.43959999084472656},{"id":"https://openalex.org/C96711827","wikidata":"https://www.wikidata.org/wiki/Q17012245","display_name":"Entity linking","level":3,"score":0.4025999903678894},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.36550000309944153},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.3637999892234802},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.34630000591278076},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3091999888420105},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.3091999888420105},{"id":"https://openalex.org/C2777889803","wikidata":"https://www.wikidata.org/wiki/Q25047676","display_name":"Named entity","level":2,"score":0.3075000047683716},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3059000074863434},{"id":"https://openalex.org/C62354387","wikidata":"https://www.wikidata.org/wiki/Q875399","display_name":"Boundary (topology)","level":2,"score":0.2766000032424927},{"id":"https://openalex.org/C35639132","wikidata":"https://www.wikidata.org/wiki/Q7452468","display_name":"Sequence labeling","level":3,"score":0.2727000117301941},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.2720000147819519},{"id":"https://openalex.org/C22367795","wikidata":"https://www.wikidata.org/wiki/Q7625208","display_name":"Structured prediction","level":2,"score":0.27129998803138733},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.26339998841285706},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2599000036716461}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3308558.3313743","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3308558.3313743","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:1905.01964","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1905.01964","pdf_url":"https://arxiv.org/pdf/1905.01964","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:10.1145/3308558.3313743","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3308558.3313743","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":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W1573052634","https://openalex.org/W1772464306","https://openalex.org/W2064675550","https://openalex.org/W2085337304","https://openalex.org/W2140016149","https://openalex.org/W2147800946","https://openalex.org/W2250709962","https://openalex.org/W2250739653","https://openalex.org/W2251287417","https://openalex.org/W2295030615","https://openalex.org/W2407349924","https://openalex.org/W2474916227","https://openalex.org/W2515462165","https://openalex.org/W2605215742","https://openalex.org/W2756748969","https://openalex.org/W2762995374","https://openalex.org/W2763438644","https://openalex.org/W2884150813","https://openalex.org/W2963682821","https://openalex.org/W2963917673","https://openalex.org/W6683738474","https://openalex.org/W6691587449","https://openalex.org/W6697155078"],"related_works":[],"abstract_inverted_index":{"Chinese":[0,10,21,29,158],"named":[1,159],"entity":[2,22,120,160],"recognition":[3],"(CNER)":[4],"is":[5,17,54,64,166],"an":[6,125],"important":[7],"task":[8],"in":[9,51,109,118],"natural":[11],"language":[12],"processing":[13],"field.":[14],"However,":[15],"CNER":[16,50,63,104,116],"very":[18,65],"challenging":[19],"since":[20],"names":[23],"are":[24],"highly":[25],"context-dependent.":[26],"In":[27,69],"addition,":[28],"texts":[30],"lack":[31],"delimiters":[32],"to":[33,39,86,101,111,128],"separate":[34],"words,":[35],"making":[36],"it":[37],"difficult":[38],"identify":[40],"the":[41,46,113,140,155],"boundary":[42],"of":[43,115,157],"entities.":[44],"Besides,":[45],"training":[47,60,141,164],"data":[48,61,136,165],"for":[49,62,77,93],"many":[52],"domains":[53],"usually":[55],"insufficient,":[56],"and":[57,67,90,105],"annotating":[58],"enough":[59],"expensive":[66],"time-consuming.":[68],"this":[70],"paper,":[71],"we":[72,80,96,123],"propose":[73,97],"a":[74,82,98],"neural":[75,84],"approach":[76,151],"CNER.":[78,94],"First,":[79],"introduce":[81,124],"CNN-LSTM-CRF":[83],"architecture":[85],"capture":[87],"both":[88],"local":[89],"long-distance":[91],"contexts":[92],"Second,":[95],"unified":[99],"framework":[100],"jointly":[102],"train":[103],"word":[106],"segmentation":[107],"models":[108],"order":[110],"enhance":[112],"ability":[114],"model":[117],"identifying":[119],"boundaries.":[121],"Third,":[122],"automatic":[126],"method":[127],"generate":[129],"pseudo":[130],"labeled":[131,135],"samples":[132],"from":[133],"existing":[134],"which":[137],"can":[138,152],"enrich":[139],"data.":[142],"Experiments":[143],"on":[144],"two":[145],"benchmark":[146],"datasets":[147],"show":[148],"that":[149],"our":[150],"effectively":[153],"improve":[154],"performance":[156],"recognition,":[161],"especially":[162],"when":[163],"insufficient.":[167]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":14},{"year":2023,"cited_by_count":18},{"year":2022,"cited_by_count":12},{"year":2021,"cited_by_count":13},{"year":2020,"cited_by_count":8},{"year":2019,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2019-02-21T00:00:00"}