{"id":"https://openalex.org/W2952370363","doi":"https://doi.org/10.1109/taslp.2021.3124365","title":"Pre-Training With Whole Word Masking for Chinese BERT","display_name":"Pre-Training With Whole Word Masking for Chinese BERT","publication_year":2021,"publication_date":"2021-01-01","ids":{"openalex":"https://openalex.org/W2952370363","doi":"https://doi.org/10.1109/taslp.2021.3124365","mag":"2952370363"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2021.3124365","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2021.3124365","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1906.08101","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Yiming Cui","orcid":"https://orcid.org/0000-0002-2452-375X"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yiming Cui","raw_affiliation_strings":["Harbin Institute of Technology, 47822 Harbin, China, (e-mail: ymcui@ir.hit.edu.cn)"],"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology, 47822 Harbin, China, (e-mail: ymcui@ir.hit.edu.cn)","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Wanxiang Che","orcid":"https://orcid.org/0000-0002-3907-0335"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wanxiang Che","raw_affiliation_strings":["Harbin Institute of Technology, 47822 Harbin, China, (e-mail: car@ir.hit.edu.cn)"],"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology, 47822 Harbin, China, (e-mail: car@ir.hit.edu.cn)","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Ting Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ting Liu","raw_affiliation_strings":["Harbin Institute of Technology, 47822 Harbin, China, (e-mail: tliu@hit.edu.cn)"],"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology, 47822 Harbin, China, (e-mail: tliu@hit.edu.cn)","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Bing Qin","orcid":null},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bing Qin","raw_affiliation_strings":["Harbin Institute of Technology, 47822 Harbin, China, (e-mail: qinb@ir.hit.edu.cn)"],"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology, 47822 Harbin, China, (e-mail: qinb@ir.hit.edu.cn)","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"last","author":{"id":null,"display_name":"Ziqing Yang","orcid":"https://orcid.org/0000-0003-0666-4409"},"institutions":[{"id":"https://openalex.org/I4210149494","display_name":"Institute of Animal Sciences","ror":"https://ror.org/04tcthy91","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210127390","https://openalex.org/I4210138501","https://openalex.org/I4210149494","https://openalex.org/I4210151987"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ziqing Yang","raw_affiliation_strings":["iFLYTEK Research, State Key Laboratory of Cognitive Intelligence, Beijing, China, (e-mail: zqyang5@iflytek.com)"],"affiliations":[{"raw_affiliation_string":"iFLYTEK Research, State Key Laboratory of Cognitive Intelligence, Beijing, China, (e-mail: zqyang5@iflytek.com)","institution_ids":["https://openalex.org/I4210149494"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I204983213"],"apc_list":null,"apc_paid":null,"fwci":107.3719,"has_fulltext":false,"cited_by_count":1063,"citation_normalized_percentile":{"value":0.99968535,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":"29","issue":null,"first_page":"3504","last_page":"3514"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.3587000072002411,"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":0.3587000072002411,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.1339000016450882,"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"}},{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.1152999997138977,"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/language-model","display_name":"Language model","score":0.7253999710083008},{"id":"https://openalex.org/keywords/masking","display_name":"Masking (illustration)","score":0.6510000228881836},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5716999769210815},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5349000096321106},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5128999948501587},{"id":"https://openalex.org/keywords/chinese-language","display_name":"Chinese language","score":0.45170000195503235}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7846999764442444},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.7253999710083008},{"id":"https://openalex.org/C2777402240","wikidata":"https://www.wikidata.org/wiki/Q6783436","display_name":"Masking (illustration)","level":2,"score":0.6510000228881836},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5981000065803528},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5716999769210815},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5557000041007996},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5349000096321106},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5128999948501587},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.49239999055862427},{"id":"https://openalex.org/C3018428822","wikidata":"https://www.wikidata.org/wiki/Q7850","display_name":"Chinese language","level":2,"score":0.45170000195503235},{"id":"https://openalex.org/C94922259","wikidata":"https://www.wikidata.org/wiki/Q33215","display_name":"Constructed language","level":2,"score":0.2651999890804291},{"id":"https://openalex.org/C143724316","wikidata":"https://www.wikidata.org/wiki/Q312468","display_name":"Series (stratigraphy)","level":2,"score":0.263700008392334},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.2502000033855438}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/taslp.2021.3124365","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2021.3124365","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:1906.08101","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1906.08101","pdf_url":"https://arxiv.org/pdf/1906.08101","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"pmh:oai:arXiv.org:1906.08101","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1906.08101","pdf_url":"https://arxiv.org/pdf/1906.08101","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1649532842","display_name":null,"funder_award_id":"61976072","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4529408277","display_name":null,"funder_award_id":"2020AAA0106501","funder_id":"https://openalex.org/F4320336026","funder_display_name":"National Key Research and Development Program of China Stem Cell and Translational Research"},{"id":"https://openalex.org/G8903434528","display_name":null,"funder_award_id":"61772153","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/F4320336026","display_name":"National Key Research and Development Program of China Stem Cell and Translational Research","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W2096707493","https://openalex.org/W2251568283","https://openalex.org/W2606964149","https://openalex.org/W2888302696","https://openalex.org/W2889968917","https://openalex.org/W2891555348","https://openalex.org/W2897356710","https://openalex.org/W2912924812","https://openalex.org/W2963748441","https://openalex.org/W2964110616","https://openalex.org/W2964223283","https://openalex.org/W2981133359","https://openalex.org/W2998579922","https://openalex.org/W3011411500","https://openalex.org/W3099911888","https://openalex.org/W3114651185","https://openalex.org/W6631190155","https://openalex.org/W6631435780","https://openalex.org/W6677674009","https://openalex.org/W6682691769","https://openalex.org/W6713134421","https://openalex.org/W6727690538","https://openalex.org/W6739901393","https://openalex.org/W6750535842","https://openalex.org/W6752148829","https://openalex.org/W6753143414","https://openalex.org/W6755207826","https://openalex.org/W6759961675","https://openalex.org/W6760810938","https://openalex.org/W6763701032","https://openalex.org/W6766481131","https://openalex.org/W6766673545","https://openalex.org/W6767852069","https://openalex.org/W6768021236","https://openalex.org/W6768841368","https://openalex.org/W6771917389","https://openalex.org/W6783754597","https://openalex.org/W6802852670"],"related_works":[],"abstract_inverted_index":{"Bidirectional":[0],"Encoder":[1],"Representations":[2],"from":[3],"Transformers":[4],"(BERT)":[5],"has":[6],"shown":[7],"marvelous":[8],"improvements":[9],"across":[10],"various":[11],"NLP":[12,120,147],"tasks,":[13,148],"and":[14,149],"its":[15],"consecutive":[16],"variants":[17],"have":[18],"been":[19],"proposed":[20,134],"to":[21,36,122],"further":[22,169],"improve":[23],"the":[24,27,39,89,124,133],"performance":[25],"of":[26,52,91,98],"pre-trained":[28,54,100,127,165],"language":[29,55,101,128,166],"models.":[30,56],"In":[31],"this":[32],"paper,":[33],"we":[34,58,76,94,150],"aim":[35],"first":[37],"introduce":[38],"whole":[40],"word":[41],"masking":[42,80],"(wwm)":[43],"strategy":[44,81],"for":[45,168],"Chinese":[46,53,99,119,126],"BERT,":[47,107],"along":[48],"with":[49,154],"a":[50,61,78,96],"series":[51,97],"Then":[57],"also":[59,151],"propose":[60,77],"simple":[62],"but":[63],"effective":[64],"model":[65],"called":[66,82],"MacBERT,":[67],"which":[68],"improves":[69],"upon":[70],"RoBERTa":[71],"in":[72],"several":[73,155],"ways.":[74],"Especially,":[75],"new":[79],"MLM":[83],"as":[84,103,130,132],"correction":[85],"(Mac).":[86],"To":[87],"demonstrate":[88],"effectiveness":[90],"these":[92],"models,":[93],"create":[95],"models":[102,129,167],"our":[104,164,171],"baselines,":[105],"including":[106],"RoBERTa,":[108],"ELECTRA,":[109],"RBT,":[110],"etc.":[111],"We":[112,162],"carried":[113],"out":[114],"extensive":[115],"experiments":[116],"on":[117,145],"ten":[118],"tasks":[121],"evaluate":[123],"created":[125],"well":[131],"MacBERT.":[135],"Experimental":[136],"results":[137],"show":[138],"that":[139,157],"MacBERT":[140],"could":[141],"achieve":[142],"state-of-the-art":[143],"performances":[144],"many":[146],"ablate":[152],"details":[153],"findings":[156],"may":[158],"help":[159],"future":[160],"research.":[161],"open-source":[163],"facilitating":[170],"research":[172],"community.":[173]},"counts_by_year":[{"year":2026,"cited_by_count":51},{"year":2025,"cited_by_count":245},{"year":2024,"cited_by_count":311},{"year":2023,"cited_by_count":305},{"year":2022,"cited_by_count":145},{"year":2021,"cited_by_count":6}],"updated_date":"2026-04-13T07:58:08.660418","created_date":"2019-06-27T00:00:00"}