{"id":"https://openalex.org/W4200196700","doi":"https://doi.org/10.1186/s12859-021-04260-y","title":"Deep learning with language models improves named entity recognition for PharmaCoNER","display_name":"Deep learning with language models improves named entity recognition for PharmaCoNER","publication_year":2021,"publication_date":"2021-12-17","ids":{"openalex":"https://openalex.org/W4200196700","doi":"https://doi.org/10.1186/s12859-021-04260-y","pmid":"https://pubmed.ncbi.nlm.nih.gov/34920700"},"language":"en","primary_location":{"id":"doi:10.1186/s12859-021-04260-y","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12859-021-04260-y","pdf_url":"https://bmcbioinformatics.biomedcentral.com/track/pdf/10.1186/s12859-021-04260-y","source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"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 Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://bmcbioinformatics.biomedcentral.com/track/pdf/10.1186/s12859-021-04260-y","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102828553","display_name":"Cong Sun","orcid":"https://orcid.org/0000-0003-0240-1070"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Cong Sun","raw_affiliation_strings":["School of Computer Science and Technology, Dalian University of Technology, Dalian, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Dalian University of Technology, Dalian, China","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051597671","display_name":"Zhihao Yang","orcid":"https://orcid.org/0000-0001-6186-2024"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]},{"id":"https://openalex.org/I4210092944","display_name":"Dalian University","ror":"https://ror.org/00g2ypp58","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210092944"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhihao Yang","raw_affiliation_strings":["School of Computer Science and Technology, Dalian University of Technology, Dalian, China. yangzh@dlut.edu.cn","School of Computer Science and Technology, Dalian University of Technology, Dalian, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Dalian University of Technology, Dalian, China. yangzh@dlut.edu.cn","institution_ids":["https://openalex.org/I27357992","https://openalex.org/I4210092944"]},{"raw_affiliation_string":"School of Computer Science and Technology, Dalian University of Technology, Dalian, China","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100736263","display_name":"Lei Wang","orcid":"https://orcid.org/0000-0002-8420-6860"},"institutions":[{"id":"https://openalex.org/I4210119119","display_name":"Beijing Administration Institute","ror":"https://ror.org/02mf18m55","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210110145","https://openalex.org/I4210119119"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Lei Wang","raw_affiliation_strings":["Beijing Institute of Health Administration and Medical Information, Beijing, China. wanglei.wlbihami@gmail.com","Beijing Institute of Health Administration and Medical Information, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Institute of Health Administration and Medical Information, Beijing, China. wanglei.wlbihami@gmail.com","institution_ids":["https://openalex.org/I4210119119"]},{"raw_affiliation_string":"Beijing Institute of Health Administration and Medical Information, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100343737","display_name":"Yin Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yin Zhang","raw_affiliation_strings":["Beijing Institute of Health Administration and Medical Information, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Institute of Health Administration and Medical Information, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023931221","display_name":"Hongfei Lin","orcid":"https://orcid.org/0000-0003-0872-7688"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongfei Lin","raw_affiliation_strings":["School of Computer Science and Technology, Dalian University of Technology, Dalian, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Dalian University of Technology, Dalian, China","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100370452","display_name":"Jian Wang","orcid":"https://orcid.org/0000-0002-4656-7446"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jian Wang","raw_affiliation_strings":["School of Computer Science and Technology, Dalian University of Technology, Dalian, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Dalian University of Technology, Dalian, China","institution_ids":["https://openalex.org/I27357992"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5051597671","https://openalex.org/A5100736263"],"corresponding_institution_ids":["https://openalex.org/I27357992","https://openalex.org/I4210092944","https://openalex.org/I4210119119"],"apc_list":{"value":2790,"currency":"USD","value_usd":2790},"apc_paid":{"value":2790,"currency":"USD","value_usd":2790},"fwci":0.5181,"has_fulltext":true,"cited_by_count":12,"citation_normalized_percentile":{"value":0.62119572,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":"22","issue":"S1","first_page":"602","last_page":"602"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.8859000205993652,"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"}},"topics":[{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.8859000205993652,"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"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.039000000804662704,"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/T10211","display_name":"Computational Drug Discovery Methods","score":0.023800000548362732,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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":0.8123407363891602},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.7006944417953491},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6798136234283447},{"id":"https://openalex.org/keywords/named-entity-recognition","display_name":"Named-entity recognition","score":0.6772547364234924},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.6480679512023926},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6436353325843811},{"id":"https://openalex.org/keywords/relationship-extraction","display_name":"Relationship extraction","score":0.5919452905654907},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5863986611366272},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5742294788360596},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.5269066691398621},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.49486225843429565},{"id":"https://openalex.org/keywords/biomedical-text-mining","display_name":"Biomedical text mining","score":0.491803914308548},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.40338414907455444},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.33992648124694824},{"id":"https://openalex.org/keywords/text-mining","display_name":"Text mining","score":0.2558419406414032},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.12608060240745544}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8123407363891602},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.7006944417953491},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6798136234283447},{"id":"https://openalex.org/C2779135771","wikidata":"https://www.wikidata.org/wiki/Q403574","display_name":"Named-entity recognition","level":3,"score":0.6772547364234924},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.6480679512023926},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6436353325843811},{"id":"https://openalex.org/C153604712","wikidata":"https://www.wikidata.org/wiki/Q7310755","display_name":"Relationship extraction","level":3,"score":0.5919452905654907},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5863986611366272},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5742294788360596},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.5269066691398621},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.49486225843429565},{"id":"https://openalex.org/C165141518","wikidata":"https://www.wikidata.org/wiki/Q4915126","display_name":"Biomedical text mining","level":3,"score":0.491803914308548},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.40338414907455444},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.33992648124694824},{"id":"https://openalex.org/C71472368","wikidata":"https://www.wikidata.org/wiki/Q676880","display_name":"Text mining","level":2,"score":0.2558419406414032},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.12608060240745544},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[{"descriptor_ui":"D000077321","descriptor_name":"Deep Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000077321","descriptor_name":"Deep Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000077321","descriptor_name":"Deep Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000077321","descriptor_name":"Deep Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":4,"locations":[{"id":"doi:10.1186/s12859-021-04260-y","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12859-021-04260-y","pdf_url":"https://bmcbioinformatics.biomedcentral.com/track/pdf/10.1186/s12859-021-04260-y","source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"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 Bioinformatics","raw_type":"journal-article"},{"id":"pmid:34920700","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/34920700","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 bioinformatics","raw_type":null},{"id":"pmh:oai:doaj.org/article:3276f25b7a404fe5a39e46425fc733ef","is_oa":true,"landing_page_url":"https://doaj.org/article/3276f25b7a404fe5a39e46425fc733ef","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":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"BMC Bioinformatics, Vol 22, Iss S1, Pp 1-16 (2021)","raw_type":"article"},{"id":"pmh:oai:pubmedcentral.nih.gov:8684061","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/8684061","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 Bioinformatics","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1186/s12859-021-04260-y","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12859-021-04260-y","pdf_url":"https://bmcbioinformatics.biomedcentral.com/track/pdf/10.1186/s12859-021-04260-y","source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"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 Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.7699999809265137,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4200196700.pdf","grobid_xml":"https://content.openalex.org/works/W4200196700.grobid-xml"},"referenced_works_count":34,"referenced_works":["https://openalex.org/W1566289585","https://openalex.org/W2101553882","https://openalex.org/W2145870108","https://openalex.org/W2153579005","https://openalex.org/W2168041406","https://openalex.org/W2168990503","https://openalex.org/W2205981794","https://openalex.org/W2250539671","https://openalex.org/W2296283641","https://openalex.org/W2610394652","https://openalex.org/W2896457183","https://openalex.org/W2911489562","https://openalex.org/W2946558277","https://openalex.org/W2949445525","https://openalex.org/W2962739339","https://openalex.org/W2963428321","https://openalex.org/W2963997788","https://openalex.org/W2970771982","https://openalex.org/W2971258845","https://openalex.org/W2983842045","https://openalex.org/W2985294119","https://openalex.org/W2986178925","https://openalex.org/W2989464093","https://openalex.org/W4213016248","https://openalex.org/W4234762960","https://openalex.org/W4385681388","https://openalex.org/W6600654476","https://openalex.org/W6681542663","https://openalex.org/W6684484140","https://openalex.org/W6691431627","https://openalex.org/W6697155078","https://openalex.org/W6739901393","https://openalex.org/W6748634344","https://openalex.org/W6769577755"],"related_works":["https://openalex.org/W173870552","https://openalex.org/W2167202928","https://openalex.org/W2604144356","https://openalex.org/W2134429551","https://openalex.org/W2548624545","https://openalex.org/W2916255597","https://openalex.org/W3095980030","https://openalex.org/W3004288456","https://openalex.org/W4379379356","https://openalex.org/W2572241437"],"abstract_inverted_index":{"BACKGROUND:":[0],"The":[1,124,183,200],"recognition":[2,61],"of":[3,79,101,119,156,197],"pharmacological":[4,65],"substances,":[5],"compounds":[6],"and":[7,109],"proteins":[8],"is":[9,57,92],"essential":[10],"for":[11],"biomedical":[12,34,51,167],"relation":[13],"extraction,":[14],"knowledge":[15,169],"graph":[16],"construction,":[17],"drug":[18],"discovery,":[19],"as":[20,22],"well":[21],"medical":[23],"question":[24],"answering.":[25],"Although":[26],"considerable":[27],"efforts":[28],"have":[29],"been":[30],"made":[31,46],"to":[32,39,47,63,84,88,115,193],"recognize":[33,48,64],"entities":[35,66],"in":[36,53,76],"English":[37],"texts,":[38],"date,":[40],"only":[41],"few":[42],"limited":[43],"attempts":[44],"were":[45],"them":[49],"from":[50,67],"texts":[52],"other":[54],"languages.":[55],"PharmaCoNER":[56,90,121,141,150,165],"a":[58,93,153,171,212,225],"named":[59],"entity":[60],"challenge":[62,91],"Spanish":[68],"texts.":[69],"Because":[70],"there":[71],"are":[72],"currently":[73],"abundant":[74],"resources":[75,87],"the":[77,89,99,117,120,140,149,160,164,178,195,203,220],"field":[78],"natural":[80],"language":[81,105,132,180],"processing,":[82],"how":[83],"leverage":[85],"these":[86],"meaningful":[94],"study.":[95],"METHODS:":[96],"Inspired":[97],"by":[98,190,210],"success":[100],"deep":[102,129],"learning":[103,130],"with":[104,131,152],"models,":[106],"we":[107],"compare":[108],"explore":[110],"various":[111],"representative":[112],"BERT":[113,161,184,204],"models":[114,133,162,185],"promote":[116],"development":[118],"task.":[122],"RESULTS:":[123],"experimental":[125],"results":[126],"show":[127],"that":[128],"can":[134,186,206],"effectively":[135],"improve":[136],"model":[137,175,205,229],"performance":[138,147,176,189,201],"on":[139,148,163,174,202,216,228],"dataset.":[142],"Our":[143],"method":[144],"achieves":[145],"state-of-the-art":[146],"dataset,":[151,166],"max":[154],"F1-score":[155],"92.01%.":[157],"CONCLUSION:":[158],"For":[159],"domain":[168,217],"has":[170,224],"greater":[172],"impact":[173,227],"than":[177],"native":[179],"(i.e.,":[181],"Spanish).":[182],"obtain":[187],"competitive":[188],"using":[191],"WordPiece":[192],"alleviate":[194],"out":[196],"vocabulary":[198,214],"limitation.":[199],"be":[207],"further":[208],"improved":[209],"constructing":[211],"specific":[213],"based":[215],"knowledge.":[218],"Moreover,":[219],"character":[221],"case":[222],"also":[223],"certain":[226],"performance.":[230]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":2}],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2025-10-10T00:00:00"}