{"id":"https://openalex.org/W3046375318","doi":"https://doi.org/10.1145/3458754","title":"Domain-Specific Language Model Pretraining for Biomedical Natural Language Processing","display_name":"Domain-Specific Language Model Pretraining for Biomedical Natural Language Processing","publication_year":2021,"publication_date":"2021-10-15","ids":{"openalex":"https://openalex.org/W3046375318","doi":"https://doi.org/10.1145/3458754","mag":"3046375318"},"language":"en","primary_location":{"id":"doi:10.1145/3458754","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3458754","pdf_url":null,"source":{"id":"https://openalex.org/S4210174653","display_name":"ACM Transactions on Computing for Healthcare","issn_l":"2637-8051","issn":["2637-8051","2691-1957"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Computing for Healthcare","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2007.15779","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5087377548","display_name":"\u88d5\u4e8c \u6c60\u8c37","orcid":"https://orcid.org/0000-0002-1704-1744"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yu Gu","raw_affiliation_strings":["Microsoft Research, Redmond, WA"],"affiliations":[{"raw_affiliation_string":"Microsoft Research, Redmond, WA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073496354","display_name":"Robert Tinn","orcid":"https://orcid.org/0000-0003-0182-7280"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Robert Tinn","raw_affiliation_strings":["Microsoft Research, Redmond, WA"],"affiliations":[{"raw_affiliation_string":"Microsoft Research, Redmond, WA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101511712","display_name":"Hao Cheng","orcid":"https://orcid.org/0000-0003-4823-0908"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hao Cheng","raw_affiliation_strings":["Microsoft Research, Redmond, WA"],"affiliations":[{"raw_affiliation_string":"Microsoft Research, Redmond, WA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041818444","display_name":"Michael Lucas","orcid":"https://orcid.org/0009-0000-9745-4241"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael Lucas","raw_affiliation_strings":["Microsoft Research, Redmond, WA"],"affiliations":[{"raw_affiliation_string":"Microsoft Research, Redmond, WA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010756260","display_name":"Naoto Usuyama","orcid":"https://orcid.org/0000-0003-0888-929X"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Naoto Usuyama","raw_affiliation_strings":["Microsoft Research, Redmond, WA"],"affiliations":[{"raw_affiliation_string":"Microsoft Research, Redmond, WA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100374810","display_name":"Xiaodong Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiaodong Liu","raw_affiliation_strings":["Microsoft Research, Redmond, WA"],"affiliations":[{"raw_affiliation_string":"Microsoft Research, Redmond, WA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023123863","display_name":"Tristan Naumann","orcid":"https://orcid.org/0000-0003-2150-1747"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tristan Naumann","raw_affiliation_strings":["Microsoft Research, Redmond, WA"],"affiliations":[{"raw_affiliation_string":"Microsoft Research, Redmond, WA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114910293","display_name":"Jianfeng Gao","orcid":"https://orcid.org/0000-0002-5702-6143"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jianfeng Gao","raw_affiliation_strings":["Microsoft Research, Redmond, WA"],"affiliations":[{"raw_affiliation_string":"Microsoft Research, Redmond, WA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019494985","display_name":"Hoifung Poon","orcid":"https://orcid.org/0000-0002-9067-0918"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hoifung Poon","raw_affiliation_strings":["Microsoft Research, Redmond, WA"],"affiliations":[{"raw_affiliation_string":"Microsoft Research, Redmond, WA","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5087377548"],"corresponding_institution_ids":["https://openalex.org/I1290206253"],"apc_list":null,"apc_paid":null,"fwci":183.6661,"has_fulltext":false,"cited_by_count":1914,"citation_normalized_percentile":{"value":0.99988113,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"3","issue":"1","first_page":"1","last_page":"23"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","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/T10028","display_name":"Topic Modeling","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/T10181","display_name":"Natural Language Processing Techniques","score":0.9937000274658203,"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/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9901000261306763,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8130438327789307},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.7901056408882141},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6947801113128662},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.6720025539398193},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6708896160125732},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.6629963517189026},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5744728446006775},{"id":"https://openalex.org/keywords/biomedicine","display_name":"Biomedicine","score":0.5419282913208008},{"id":"https://openalex.org/keywords/aka","display_name":"AKA","score":0.5066412091255188},{"id":"https://openalex.org/keywords/language-understanding","display_name":"Language understanding","score":0.4924331605434418},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.4302677512168884},{"id":"https://openalex.org/keywords/named-entity-recognition","display_name":"Named-entity recognition","score":0.41865095496177673},{"id":"https://openalex.org/keywords/bioinformatics","display_name":"Bioinformatics","score":0.06705847382545471}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8130438327789307},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7901056408882141},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6947801113128662},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.6720025539398193},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6708896160125732},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.6629963517189026},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5744728446006775},{"id":"https://openalex.org/C66782513","wikidata":"https://www.wikidata.org/wiki/Q864601","display_name":"Biomedicine","level":2,"score":0.5419282913208008},{"id":"https://openalex.org/C121158502","wikidata":"https://www.wikidata.org/wiki/Q4652161","display_name":"AKA","level":2,"score":0.5066412091255188},{"id":"https://openalex.org/C2983448237","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Language understanding","level":2,"score":0.4924331605434418},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.4302677512168884},{"id":"https://openalex.org/C2779135771","wikidata":"https://www.wikidata.org/wiki/Q403574","display_name":"Named-entity recognition","level":3,"score":0.41865095496177673},{"id":"https://openalex.org/C60644358","wikidata":"https://www.wikidata.org/wiki/Q128570","display_name":"Bioinformatics","level":1,"score":0.06705847382545471},{"id":"https://openalex.org/C161191863","wikidata":"https://www.wikidata.org/wiki/Q199655","display_name":"Library science","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","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/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3458754","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3458754","pdf_url":null,"source":{"id":"https://openalex.org/S4210174653","display_name":"ACM Transactions on Computing for Healthcare","issn_l":"2637-8051","issn":["2637-8051","2691-1957"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Computing for Healthcare","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2007.15779","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2007.15779","pdf_url":"https://arxiv.org/pdf/2007.15779","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:2007.15779","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2007.15779","pdf_url":"https://arxiv.org/pdf/2007.15779","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":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.6399999856948853}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":68,"referenced_works":["https://openalex.org/W154351976","https://openalex.org/W1522301498","https://openalex.org/W1566289585","https://openalex.org/W1614298861","https://openalex.org/W1905522558","https://openalex.org/W2034269086","https://openalex.org/W2047782770","https://openalex.org/W2064675550","https://openalex.org/W2075201173","https://openalex.org/W2112227057","https://openalex.org/W2114315281","https://openalex.org/W2121227244","https://openalex.org/W2136437513","https://openalex.org/W2145383760","https://openalex.org/W2147880316","https://openalex.org/W2154142897","https://openalex.org/W2158049734","https://openalex.org/W2169099542","https://openalex.org/W2170189740","https://openalex.org/W2174775663","https://openalex.org/W2250539671","https://openalex.org/W2295072214","https://openalex.org/W2346452181","https://openalex.org/W2396881363","https://openalex.org/W2735784619","https://openalex.org/W2736047977","https://openalex.org/W2743028754","https://openalex.org/W2765742249","https://openalex.org/W2793862696","https://openalex.org/W2888041867","https://openalex.org/W2896457183","https://openalex.org/W2900758626","https://openalex.org/W2911489562","https://openalex.org/W2913340405","https://openalex.org/W2923014074","https://openalex.org/W2943552823","https://openalex.org/W2949460468","https://openalex.org/W2950577311","https://openalex.org/W2951036431","https://openalex.org/W2955483668","https://openalex.org/W2962739339","https://openalex.org/W2962784628","https://openalex.org/W2962859618","https://openalex.org/W2963026768","https://openalex.org/W2963250244","https://openalex.org/W2963403868","https://openalex.org/W2963716420","https://openalex.org/W2964022985","https://openalex.org/W2964121744","https://openalex.org/W2964179635","https://openalex.org/W2965373594","https://openalex.org/W2970482702","https://openalex.org/W2970771982","https://openalex.org/W2971258845","https://openalex.org/W2981852735","https://openalex.org/W2990704537","https://openalex.org/W3017003177","https://openalex.org/W3035763680","https://openalex.org/W3039677769","https://openalex.org/W3082274269","https://openalex.org/W4234482043","https://openalex.org/W4237040408","https://openalex.org/W4238634189","https://openalex.org/W4287813862","https://openalex.org/W4288089799","https://openalex.org/W4301409532","https://openalex.org/W4385245566","https://openalex.org/W6676573207"],"related_works":["https://openalex.org/W4387517132","https://openalex.org/W4387929264","https://openalex.org/W3105220303","https://openalex.org/W4287903637","https://openalex.org/W2999168658","https://openalex.org/W69308499","https://openalex.org/W4288365749","https://openalex.org/W2936497627","https://openalex.org/W2918609062","https://openalex.org/W2901701848"],"abstract_inverted_index":{"Pretraining":[0],"large":[1],"neural":[2],"language":[3,16,48,70,83],"models,":[4,152],"such":[5,29,66,153],"as":[6,30,67,107,154],"BERT,":[7],"has":[8],"led":[9],"to":[10,120],"impressive":[11],"gains":[12,77],"on":[13,25],"many":[14],"natural":[15],"processing":[17],"(NLP)":[18],"tasks.":[19],"However,":[20],"most":[21],"pretraining":[22,41,69,80,105,138],"efforts":[23],"focus":[24],"general":[26],"domain":[27],"corpora,":[28],"newswire":[31],"and":[32,139,176,182],"Web.":[33],"A":[34],"prevailing":[35],"assumption":[36,56],"is":[37],"that":[38,59,103,144],"even":[39],"domain-specific":[40,104],"can":[42],"benefit":[43],"by":[44,57],"starting":[45],"from":[46,72,96],"general-domain":[47,82],"models.":[49,84],"In":[50],"this":[51,55,87],"article,":[52],"we":[53,89,142,170],"challenge":[54],"showing":[58],"for":[60,111,137,179,191],"domains":[61],"with":[62,150],"abundant":[63],"unlabeled":[64],"text,":[65],"biomedicine,":[68],"models":[71,178],"scratch":[73],"results":[74,123],"in":[75,128,159,167],"substantial":[76],"over":[78],"continual":[79],"of":[81,115,133],"To":[85,163],"facilitate":[86],"investigation,":[88],"compile":[90],"a":[91,108,112,130,184],"comprehensive":[92],"biomedical":[93,116,168],"NLP":[94,117],"benchmark":[95,189],"publicly":[97],"available":[98],"datasets.":[99],"Our":[100],"experiments":[101],"show":[102],"serves":[106],"solid":[109],"foundation":[110],"wide":[113],"range":[114],"tasks,":[118],"leading":[119],"new":[121],"state-of-the-art":[122,174],"across":[124],"the":[125,180],"board.":[126],"Further,":[127],"conducting":[129],"thorough":[131],"evaluation":[132],"modeling":[134],"choices,":[135],"both":[136],"task-specific":[140,177],"fine-tuning,":[141],"discover":[143],"some":[145],"common":[146],"practices":[147],"are":[148],"unnecessary":[149],"BERT":[151],"using":[155],"complex":[156],"tagging":[157],"schemes":[158],"named":[160],"entity":[161],"recognition.":[162],"help":[164],"accelerate":[165],"research":[166],"NLP,":[169],"have":[171],"released":[172],"our":[173,187],"pretrained":[175],"community,":[181],"created":[183],"leaderboard":[185],"featuring":[186],"BLURB":[188],"(short":[190],"Biomedical":[192],"Language":[193],"Understanding":[194],"&":[195],"Reasoning":[196],"Benchmark)":[197],"at":[198],"https://aka.ms/BLURB":[199],".":[200]},"counts_by_year":[{"year":2026,"cited_by_count":84},{"year":2025,"cited_by_count":501},{"year":2024,"cited_by_count":478},{"year":2023,"cited_by_count":435},{"year":2022,"cited_by_count":254},{"year":2021,"cited_by_count":138},{"year":2020,"cited_by_count":23}],"updated_date":"2026-04-13T07:58:08.660418","created_date":"2020-08-07T00:00:00"}