{"id":"https://openalex.org/W4225545910","doi":"https://doi.org/10.1186/s12911-022-01829-2","title":"When BERT meets Bilbo: a learning curve analysis of pretrained language model on disease classification","display_name":"When BERT meets Bilbo: a learning curve analysis of pretrained language model on disease classification","publication_year":2021,"publication_date":"2021-11-01","ids":{"openalex":"https://openalex.org/W4225545910","doi":"https://doi.org/10.1186/s12911-022-01829-2","pmid":"https://pubmed.ncbi.nlm.nih.gov/35382811"},"language":"en","primary_location":{"id":"doi:10.1186/s12911-022-01829-2","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12911-022-01829-2","pdf_url":"https://bmcmedinformdecismak.biomedcentral.com/track/pdf/10.1186/s12911-022-01829-2","source":{"id":"https://openalex.org/S107516304","display_name":"BMC Medical Informatics and Decision Making","issn_l":"1472-6947","issn":["1472-6947"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Medical Informatics and Decision Making","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://bmcmedinformdecismak.biomedcentral.com/track/pdf/10.1186/s12911-022-01829-2","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100708345","display_name":"Xuedong Li","orcid":"https://orcid.org/0009-0005-3900-4484"},"institutions":[{"id":"https://openalex.org/I24185976","display_name":"Sichuan University","ror":"https://ror.org/011ashp19","country_code":"CN","type":"education","lineage":["https://openalex.org/I24185976"]},{"id":"https://openalex.org/I4210125143","display_name":"Chengdu University","ror":"https://ror.org/034z67559","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210125143"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuedong Li","raw_affiliation_strings":["College of Computer Science, Sichuan University, Chengdu, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science, Sichuan University, Chengdu, China","institution_ids":["https://openalex.org/I24185976","https://openalex.org/I4210125143"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003788131","display_name":"Walter Yuan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Walter Yuan","raw_affiliation_strings":["MobLab Inc., Pasadena, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MobLab Inc., Pasadena, CA, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027770821","display_name":"Dezhong Peng","orcid":"https://orcid.org/0000-0002-0987-8472"},"institutions":[{"id":"https://openalex.org/I24185976","display_name":"Sichuan University","ror":"https://ror.org/011ashp19","country_code":"CN","type":"education","lineage":["https://openalex.org/I24185976"]},{"id":"https://openalex.org/I4210125143","display_name":"Chengdu University","ror":"https://ror.org/034z67559","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210125143"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dezhong Peng","raw_affiliation_strings":["College of Computer Science, Sichuan University, Chengdu, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science, Sichuan University, Chengdu, China","institution_ids":["https://openalex.org/I24185976","https://openalex.org/I4210125143"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048955398","display_name":"Qiaozhu Mei","orcid":"https://orcid.org/0000-0002-8640-1942"},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Qiaozhu Mei","raw_affiliation_strings":["School of Information, University of Michigan, Ann Arbor, MI, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information, University of Michigan, Ann Arbor, MI, USA","institution_ids":["https://openalex.org/I27837315"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100371984","display_name":"Yue Wang","orcid":"https://orcid.org/0000-0002-0278-2347"},"institutions":[{"id":"https://openalex.org/I114027177","display_name":"University of North Carolina at Chapel Hill","ror":"https://ror.org/0130frc33","country_code":"US","type":"education","lineage":["https://openalex.org/I114027177"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yue Wang","raw_affiliation_strings":["School of Information and Library Science, University of North Carolina at Chapel Hill, Chapel Hill, NC, USA. wangyue@email.unc.edu","School of Information and Library Science, University of North Carolina at Chapel Hill, Chapel Hill, NC, USA"],"raw_orcid":"https://orcid.org/0000-0002-0278-2347","affiliations":[{"raw_affiliation_string":"School of Information and Library Science, University of North Carolina at Chapel Hill, Chapel Hill, NC, USA. wangyue@email.unc.edu","institution_ids":["https://openalex.org/I114027177"]},{"raw_affiliation_string":"School of Information and Library Science, University of North Carolina at Chapel Hill, Chapel Hill, NC, USA","institution_ids":["https://openalex.org/I114027177"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100371984"],"corresponding_institution_ids":["https://openalex.org/I114027177"],"apc_list":{"value":2690,"currency":"USD","value_usd":2690},"apc_paid":{"value":2690,"currency":"USD","value_usd":2690},"fwci":1.0419,"has_fulltext":true,"cited_by_count":8,"citation_normalized_percentile":{"value":0.8187411,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"21","issue":"S9","first_page":"377","last_page":"377"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13702","display_name":"Machine Learning in Healthcare","score":0.24879999458789825,"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/T13702","display_name":"Machine Learning in Healthcare","score":0.24879999458789825,"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":0.11180000007152557,"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/T11636","display_name":"Artificial Intelligence in Healthcare and Education","score":0.10580000281333923,"subfield":{"id":"https://openalex.org/subfields/2718","display_name":"Health Informatics"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.781074047088623},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.6803885698318481},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6453121900558472},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.6127668619155884},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5952299237251282},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5903613567352295},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5381190776824951},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.4661228656768799},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.4585352838039398},{"id":"https://openalex.org/keywords/domain-knowledge","display_name":"Domain knowledge","score":0.4280930757522583},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.425425261259079}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.781074047088623},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6803885698318481},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6453121900558472},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6127668619155884},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5952299237251282},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5903613567352295},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5381190776824951},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4661228656768799},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.4585352838039398},{"id":"https://openalex.org/C207685749","wikidata":"https://www.wikidata.org/wiki/Q2088941","display_name":"Domain knowledge","level":2,"score":0.4280930757522583},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.425425261259079},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0}],"mesh":[{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D007802","descriptor_name":"Language","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D007802","descriptor_name":"Language","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D007802","descriptor_name":"Language","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D007802","descriptor_name":"Language","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D059032","descriptor_name":"Learning Curve","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D059032","descriptor_name":"Learning Curve","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D059032","descriptor_name":"Learning Curve","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D059032","descriptor_name":"Learning Curve","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":5,"locations":[{"id":"doi:10.1186/s12911-022-01829-2","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12911-022-01829-2","pdf_url":"https://bmcmedinformdecismak.biomedcentral.com/track/pdf/10.1186/s12911-022-01829-2","source":{"id":"https://openalex.org/S107516304","display_name":"BMC Medical Informatics and Decision Making","issn_l":"1472-6947","issn":["1472-6947"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Medical Informatics and Decision Making","raw_type":"journal-article"},{"id":"pmid:35382811","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/35382811","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC medical informatics and decision making","raw_type":"Journal Article"},{"id":"pmh:oai:deepblue.lib.umich.edu:2027.42/173609","is_oa":true,"landing_page_url":"https://hdl.handle.net/2027.42/173609","pdf_url":"http://deepblue.lib.umich.edu/bitstream/2027.42/173609/1/12911_2022_Article_1829.pdf","source":{"id":"https://openalex.org/S4306400393","display_name":"Deep Blue (University of Michigan)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I27837315","host_organization_name":"University of Michigan","host_organization_lineage":["https://openalex.org/I27837315"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Journal Article"},{"id":"pmh:oai:doaj.org/article:d5e35767f28841efa7c23a7fbfc057ee","is_oa":false,"landing_page_url":"https://doaj.org/article/d5e35767f28841efa7c23a7fbfc057ee","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"BMC Medical Informatics and Decision Making, Vol 21, Iss S9, Pp 1-11 (2022)","raw_type":"article"},{"id":"pmh:oai:pubmedcentral.nih.gov:8981604","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/8981604","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"BMC Med Inform Decis Mak","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1186/s12911-022-01829-2","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12911-022-01829-2","pdf_url":"https://bmcmedinformdecismak.biomedcentral.com/track/pdf/10.1186/s12911-022-01829-2","source":{"id":"https://openalex.org/S107516304","display_name":"BMC Medical Informatics and Decision Making","issn_l":"1472-6947","issn":["1472-6947"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Medical Informatics and Decision Making","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.7900000214576721}],"awards":[{"id":"https://openalex.org/G4617372556","display_name":null,"funder_award_id":"1633370","funder_id":"https://openalex.org/F4320337389","funder_display_name":"Division of Information and Intelligent Systems"},{"id":"https://openalex.org/G4664183492","display_name":null,"funder_award_id":"R01LM010681","funder_id":"https://openalex.org/F4320337372","funder_display_name":"U.S. National Library of Medicine"},{"id":"https://openalex.org/G5943365711","display_name":"BIGDATA: Collaborative Research: F: Efficient and Exact Methods for Big Data Reduction","funder_award_id":"1633370","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8984988633","display_name":null,"funder_award_id":"2R01LM010681-05","funder_id":"https://openalex.org/F4320337372","funder_display_name":"U.S. National Library of Medicine"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320309652","display_name":"University of Michigan","ror":"https://ror.org/00jmfr291"},{"id":"https://openalex.org/F4320322725","display_name":"China Scholarship Council","ror":"https://ror.org/04atp4p48"},{"id":"https://openalex.org/F4320337372","display_name":"U.S. National Library of Medicine","ror":"https://ror.org/0060t0j89"},{"id":"https://openalex.org/F4320337389","display_name":"Division of Information and Intelligent Systems","ror":"https://ror.org/053a2cp42"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4225545910.pdf","grobid_xml":"https://content.openalex.org/works/W4225545910.grobid-xml"},"referenced_works_count":40,"referenced_works":["https://openalex.org/W96276655","https://openalex.org/W1560851690","https://openalex.org/W1888005072","https://openalex.org/W1994929347","https://openalex.org/W2025428542","https://openalex.org/W2093157872","https://openalex.org/W2100676408","https://openalex.org/W2109206523","https://openalex.org/W2112950297","https://openalex.org/W2132724073","https://openalex.org/W2153064780","https://openalex.org/W2157549840","https://openalex.org/W2157807817","https://openalex.org/W2190333735","https://openalex.org/W2467995757","https://openalex.org/W2557074642","https://openalex.org/W2620787630","https://openalex.org/W2743028754","https://openalex.org/W2902516827","https://openalex.org/W2911489562","https://openalex.org/W2923014074","https://openalex.org/W2927032858","https://openalex.org/W2953356739","https://openalex.org/W2956394034","https://openalex.org/W2963716420","https://openalex.org/W2971258845","https://openalex.org/W2976476443","https://openalex.org/W2979920993","https://openalex.org/W2991755410","https://openalex.org/W2993873509","https://openalex.org/W3011762034","https://openalex.org/W3013605954","https://openalex.org/W3023618320","https://openalex.org/W3025400983","https://openalex.org/W3034238904","https://openalex.org/W3047797631","https://openalex.org/W6601454296","https://openalex.org/W6702248584","https://openalex.org/W6739901393","https://openalex.org/W6763692313"],"related_works":["https://openalex.org/W4390516098","https://openalex.org/W2181948922","https://openalex.org/W2384362569","https://openalex.org/W3201126466","https://openalex.org/W4205302943","https://openalex.org/W2119949815","https://openalex.org/W2561132942","https://openalex.org/W2142795561","https://openalex.org/W3155418658","https://openalex.org/W4243199227"],"abstract_inverted_index":{"BACKGROUND:":[0],"Natural":[1],"language":[2,54],"processing":[3],"(NLP)":[4],"tasks":[5,92,124,323],"in":[6,107,131,237,328],"the":[7,30,58,108,132,146,160,221,234,245,251,265,301],"health":[8,35,109,135,321],"domain":[9],"often":[10,38,93],"deal":[11],"with":[12,292],"limited":[13,181],"amount":[14,222,302],"of":[15,32,73,134,148,163,187,223,247,254,267,303],"labeled":[16],"data":[17,96,127,155,170,269],"due":[18],"to":[19,40,46,68,86,105,116,144,230,320],"high":[20],"annotation":[21],"costs":[22],"and":[23,43,82,150,178,200,208,232,341],"naturally":[24,176],"rare":[25,177],"observations.":[26],"To":[27,215],"compensate":[28],"for":[29],"lack":[31],"training":[33,95,126,154,224,268,280,304,339],"data,":[34],"NLP":[36,322],"researchers":[37],"have":[39,65,179],"leverage":[41],"knowledge":[42,77,85],"resources":[44],"external":[45,213],"a":[47,70,99,140,311,316],"task":[48,246],"at":[49,97],"hand.":[50],"Recently,":[51],"pretrained":[52,312],"large-scale":[53],"models":[55,152,165,196,349],"such":[56,98,197],"as":[57,153,198,300],"Bidirectional":[59],"Encoder":[60],"Representations":[61],"from":[62,78,228],"Transformers":[63],"(BERT)":[64],"been":[66],"proven":[67],"be":[69,345,354],"powerful":[71],"way":[72],"learning":[74,141,217,252],"rich":[75],"linguistic":[76],"massive":[79],"unlabeled":[80],"text":[81,194],"transferring":[83],"that":[84,102,211],"downstream":[87,91,123],"tasks.":[88],"However,":[89,327],"previous":[90],"used":[94,193],"large":[100],"scale":[101],"is":[103,306,315],"unlikely":[104],"obtain":[106,216],"domain.":[110],"In":[111],"this":[112],"work,":[113],"we":[114,219],"aim":[115],"study":[117,145],"whether":[118],"BERT":[119,149,255,286,313],"can":[120],"still":[121],"benefit":[122],"when":[125],"are":[128,175],"relatively":[129],"small":[130,229],"context":[133],"NLP.":[136],"METHOD:":[137],"We":[138,158],"conducted":[139],"curve":[142],"analysis":[143],"behavior":[147],"baseline":[151],"size":[156],"increases.":[157],"observed":[159],"classification":[161,195,235],"performance":[162,236],"these":[164],"on":[166],"two":[167,279,338],"disease":[168,227,283,325],"diagnosis":[169],"sets,":[171],"where":[172,275,331],"some":[173],"diseases":[174],"very":[180],"observations":[182],"(fewer":[183],"than":[184],"2":[185],"out":[186],"10,000).":[188],"The":[189],"baselines":[190],"included":[191],"commonly":[192],"sparse":[199],"dense":[201],"bag-of-words":[202,295,351],"models,":[203],"long":[204,299],"short-term":[205],"memory":[206],"networks,":[207],"their":[209],"variants":[210],"leveraged":[212],"knowledge.":[214],"curves,":[218],"incremented":[220],"examples":[225],"per":[226,282],"large,":[231],"measured":[233],"macro-averaged":[238],"[Formula:":[239],"see":[240],"text]":[241],"score.":[242],"RESULTS:":[243],"On":[244],"classifying":[248],"all":[249,259],"diseases,":[250],"curves":[253],"were":[256,284],"consistently":[257],"above":[258],"baselines,":[260],"significantly":[261],"outperforming":[262],"them":[263],"across":[264],"spectrum":[266],"sizes.":[270],"But":[271],"under":[272],"extreme":[273,329],"situations":[274],"only":[276,335],"one":[277,336],"or":[278,337],"documents":[281,305,340],"available,":[285,346],"was":[287],"outperformed":[288],"by":[289],"linear":[290,348],"classifiers":[291],"carefully":[293],"engineered":[294],"features.":[296],"CONCLUSION:":[297],"As":[298],"not":[307],"extremely":[308],"few,":[309],"fine-tuning":[310],"model":[314],"highly":[317],"effective":[318],"approach":[319],"like":[324],"classification.":[326],"cases":[330],"each":[332],"class":[333],"has":[334],"no":[342],"more":[343],"will":[344],"simple":[347],"using":[350],"features":[352],"shall":[353],"considered.":[355]},"counts_by_year":[{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":1}],"updated_date":"2026-08-01T09:00:35.917206","created_date":"2025-10-10T00:00:00"}