{"id":"https://openalex.org/W4388579598","doi":"https://doi.org/10.1109/taslp.2023.3331096","title":"Gradual Syntactic Label Replacement for Language Model Pre-Training","display_name":"Gradual Syntactic Label Replacement for Language Model Pre-Training","publication_year":2023,"publication_date":"2023-11-10","ids":{"openalex":"https://openalex.org/W4388579598","doi":"https://doi.org/10.1109/taslp.2023.3331096"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2023.3331096","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/taslp.2023.3331096","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":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5044326908","display_name":"Yile Wang","orcid":"https://orcid.org/0000-0001-8705-9598"},"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":true,"raw_author_name":"Yile Wang","raw_affiliation_strings":["Institute for AI Industry Research, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institute for AI Industry Research, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100333729","display_name":"Yue Zhang","orcid":"https://orcid.org/0000-0002-5214-2268"},"institutions":[{"id":"https://openalex.org/I3133055985","display_name":"Westlake University","ror":"https://ror.org/05hfa4n20","country_code":"CN","type":"education","lineage":["https://openalex.org/I3133055985"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yue Zhang","raw_affiliation_strings":["School of Engineering, Westlake University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"School of Engineering, Westlake University, Hangzhou, China","institution_ids":["https://openalex.org/I3133055985"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100726757","display_name":"Peng Li","orcid":"https://orcid.org/0000-0003-1374-5979"},"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":"Peng Li","raw_affiliation_strings":["Institute for AI Industry Research, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institute for AI Industry Research, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5086000078","display_name":"Yang Liu","orcid":"https://orcid.org/0000-0002-3087-242X"},"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":"Yang Liu","raw_affiliation_strings":["Department of Computer Science and Technology, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5044326908"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.15137272,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"32","issue":null,"first_page":"486","last_page":"496"},"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":0.9998000264167786,"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/T10201","display_name":"Speech Recognition and Synthesis","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":0.5925912857055664},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5686345100402832},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.421700656414032},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4214697480201721},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41710036993026733},{"id":"https://openalex.org/keywords/philosophy","display_name":"Philosophy","score":0.05378720164299011}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5925912857055664},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5686345100402832},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.421700656414032},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4214697480201721},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41710036993026733},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.05378720164299011}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2023.3331096","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/taslp.2023.3331096","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"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.5799999833106995,"display_name":"Reduced inequalities"}],"awards":[{"id":"https://openalex.org/G1111291411","display_name":null,"funder_award_id":"62276152","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7879634455","display_name":null,"funder_award_id":"61925601","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8869030430","display_name":null,"funder_award_id":"61976180","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"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":89,"referenced_works":["https://openalex.org/W1566289585","https://openalex.org/W1632114991","https://openalex.org/W2110485445","https://openalex.org/W2110764733","https://openalex.org/W2144578941","https://openalex.org/W2250539671","https://openalex.org/W2256388387","https://openalex.org/W2296073425","https://openalex.org/W2321470647","https://openalex.org/W2518186251","https://openalex.org/W2525778437","https://openalex.org/W2548122763","https://openalex.org/W2739351760","https://openalex.org/W2896457183","https://openalex.org/W2923014074","https://openalex.org/W2946359678","https://openalex.org/W2962739339","https://openalex.org/W2962784628","https://openalex.org/W2963015836","https://openalex.org/W2963084773","https://openalex.org/W2963159690","https://openalex.org/W2963323070","https://openalex.org/W2963748441","https://openalex.org/W2963846996","https://openalex.org/W2964204621","https://openalex.org/W2964303116","https://openalex.org/W2965373594","https://openalex.org/W2971296908","https://openalex.org/W2978670439","https://openalex.org/W2983725648","https://openalex.org/W2988217457","https://openalex.org/W2998554035","https://openalex.org/W3034999214","https://openalex.org/W3035153870","https://openalex.org/W3098383912","https://openalex.org/W3104033643","https://openalex.org/W3115729981","https://openalex.org/W3142849873","https://openalex.org/W3153427360","https://openalex.org/W3153543512","https://openalex.org/W3157546558","https://openalex.org/W3168386607","https://openalex.org/W3173777717","https://openalex.org/W3173854146","https://openalex.org/W3174401451","https://openalex.org/W3175049034","https://openalex.org/W3177765786","https://openalex.org/W3191350816","https://openalex.org/W3198757395","https://openalex.org/W3212733079","https://openalex.org/W3212940836","https://openalex.org/W4205411913","https://openalex.org/W4206136559","https://openalex.org/W4226003933","https://openalex.org/W4281384181","https://openalex.org/W4283383808","https://openalex.org/W4285202171","https://openalex.org/W4286909689","https://openalex.org/W4288089799","https://openalex.org/W4294170691","https://openalex.org/W4308828465","https://openalex.org/W4385574386","https://openalex.org/W4386566638","https://openalex.org/W6605323724","https://openalex.org/W6679390333","https://openalex.org/W6691459498","https://openalex.org/W6727099177","https://openalex.org/W6727690538","https://openalex.org/W6734040793","https://openalex.org/W6749505818","https://openalex.org/W6754723338","https://openalex.org/W6757423643","https://openalex.org/W6757635932","https://openalex.org/W6757817989","https://openalex.org/W6766673545","https://openalex.org/W6768021236","https://openalex.org/W6769627184","https://openalex.org/W6771594884","https://openalex.org/W6778883912","https://openalex.org/W6789642857","https://openalex.org/W6798840752","https://openalex.org/W6800875267","https://openalex.org/W6802269623","https://openalex.org/W6802669662","https://openalex.org/W6804221474","https://openalex.org/W6838964481","https://openalex.org/W6846585288","https://openalex.org/W6893640197","https://openalex.org/W6894216603"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Pre-training":[0],"serves":[1],"as":[2,27,86],"a":[3,28,65,87,134,155],"foundation":[4],"of":[5,56,137,161],"recent":[6,39],"NLP":[7],"models,":[8],"where":[9,119],"language":[10,36,58,167],"modeling":[11],"tasks":[12],"are":[13],"performed":[14],"over":[15],"large":[16,135],"texts.":[17],"Typical":[18],"models":[19,168],"like":[20],"BERT":[21],"and":[22,30,92,127,144,164,171],"GPT":[23],"take":[24],"the":[25,43,49,54,57,72,77,83,96,120,123,145,159],"corpus":[26,51],"whole":[29],"treat":[31],"each":[32],"word":[33],"equally":[34],"for":[35,89,107],"modeling.":[37],"However,":[38],"works":[40],"show":[41,152],"that":[42,69,153],"naturally":[44],"existing":[45],"frequency":[46],"bias":[47],"in":[48,113],"raw":[50],"may":[52],"limit":[53],"power":[55],"model.":[59],"In":[60],"this":[61],"article,":[62],"we":[63,81,101],"propose":[64],"multi-stage":[66],"training":[67,73,78],"strategy":[68,111],"gradually":[70],"increases":[71],"vocabulary":[74],"by":[75],"modifying":[76],"data.":[79],"Specifically,":[80],"leverage":[82],"syntactic":[84,98],"structure":[85],"bridge":[88],"infrequent":[90],"words":[91,126,139],"replace":[93],"them":[94],"with":[95],"corresponding":[97],"labels,":[99],"then":[100],"recover":[102],"their":[103,141],"original":[104],"lexical":[105],"surface":[106],"further":[108],"training.":[109],"Such":[110],"results":[112,151],"an":[114],"easy-to-hard":[115],"curriculum":[116],"learning":[117],"process,":[118],"model":[121],"learns":[122],"most":[124],"common":[125],"some":[128],"basic":[129],"syntax":[130],"concepts,":[131],"before":[132],"recognizing":[133],"number":[136],"uncommon":[138],"via":[140],"specific":[142],"usages":[143],"previously":[146],"learned":[147],"category":[148],"knowledge.":[149],"Experimental":[150],"such":[154],"method":[156],"can":[157],"improve":[158],"performance":[160],"both":[162],"discriminative":[163],"generative":[165],"pre-trained":[166],"on":[169],"benchmarks":[170],"various":[172],"downstream":[173],"tasks.":[174]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}