{"id":"https://openalex.org/W3175533348","doi":"https://doi.org/10.1162/dint_a_00105","title":"Medical Named Entity Recognition from Un-labelled Medical Records based on Pre-trained Language Models and Domain Dictionary","display_name":"Medical Named Entity Recognition from Un-labelled Medical Records based on Pre-trained Language Models and Domain Dictionary","publication_year":2021,"publication_date":"2021-01-01","ids":{"openalex":"https://openalex.org/W3175533348","doi":"https://doi.org/10.1162/dint_a_00105","mag":"3175533348"},"language":"en","primary_location":{"id":"doi:10.1162/dint_a_00105","is_oa":true,"landing_page_url":"https://doi.org/10.1162/dint_a_00105","pdf_url":"https://direct.mit.edu/dint/article-pdf/3/3/402/1969110/dint_a_00105.pdf","source":{"id":"https://openalex.org/S4210186383","display_name":"Data Intelligence","issn_l":"2096-7004","issn":["2096-7004","2641-435X"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310315718","host_organization_name":"The MIT Press","host_organization_lineage":["https://openalex.org/P4310315718"],"host_organization_lineage_names":["The MIT Press"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Data Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://direct.mit.edu/dint/article-pdf/3/3/402/1969110/dint_a_00105.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5034661323","display_name":"Chaojie Wen","orcid":"https://orcid.org/0000-0002-9325-9147"},"institutions":[{"id":"https://openalex.org/I4210151615","display_name":"Wuyi University","ror":"https://ror.org/0488wz367","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210151615"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chaojie Wen","raw_affiliation_strings":["Faculty of Intelligent Manufacturing, Wuyi University, Jiangmen 529020, China","Faculty of Intelligent Manufacturing, Wuyi University, Jiangmen 529020,\n China"],"affiliations":[{"raw_affiliation_string":"Faculty of Intelligent Manufacturing, Wuyi University, Jiangmen 529020, China","institution_ids":["https://openalex.org/I4210151615"]},{"raw_affiliation_string":"Faculty of Intelligent Manufacturing, Wuyi University, Jiangmen 529020,\n China","institution_ids":["https://openalex.org/I4210151615"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100357784","display_name":"Tao Chen","orcid":"https://orcid.org/0000-0003-0190-3853"},"institutions":[{"id":"https://openalex.org/I4210151615","display_name":"Wuyi University","ror":"https://ror.org/0488wz367","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210151615"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Tao Chen","raw_affiliation_strings":["Faculty of Intelligent Manufacturing, Wuyi University, Jiangmen 529020, China","Faculty of Intelligent Manufacturing, Wuyi University, Jiangmen 529020,\n China"],"affiliations":[{"raw_affiliation_string":"Faculty of Intelligent Manufacturing, Wuyi University, Jiangmen 529020, China","institution_ids":["https://openalex.org/I4210151615"]},{"raw_affiliation_string":"Faculty of Intelligent Manufacturing, Wuyi University, Jiangmen 529020,\n China","institution_ids":["https://openalex.org/I4210151615"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021123104","display_name":"Xudong Jia","orcid":"https://orcid.org/0000-0001-7911-8869"},"institutions":[{"id":"https://openalex.org/I4210151615","display_name":"Wuyi University","ror":"https://ror.org/0488wz367","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210151615"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xudong Jia","raw_affiliation_strings":["Faculty of Intelligent Manufacturing, Wuyi University, Jiangmen 529020, China","Faculty of Intelligent Manufacturing, Wuyi University, Jiangmen 529020,\n China"],"affiliations":[{"raw_affiliation_string":"Faculty of Intelligent Manufacturing, Wuyi University, Jiangmen 529020, China","institution_ids":["https://openalex.org/I4210151615"]},{"raw_affiliation_string":"Faculty of Intelligent Manufacturing, Wuyi University, Jiangmen 529020,\n China","institution_ids":["https://openalex.org/I4210151615"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101751242","display_name":"Jiang Zhu","orcid":"https://orcid.org/0000-0001-9683-0030"},"institutions":[{"id":"https://openalex.org/I4210151615","display_name":"Wuyi University","ror":"https://ror.org/0488wz367","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210151615"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiang Zhu","raw_affiliation_strings":["Faculty of Intelligent Manufacturing, Wuyi University, Jiangmen 529020, China","Faculty of Intelligent Manufacturing, Wuyi University, Jiangmen 529020,\n China"],"affiliations":[{"raw_affiliation_string":"Faculty of Intelligent Manufacturing, Wuyi University, Jiangmen 529020, China","institution_ids":["https://openalex.org/I4210151615"]},{"raw_affiliation_string":"Faculty of Intelligent Manufacturing, Wuyi University, Jiangmen 529020,\n China","institution_ids":["https://openalex.org/I4210151615"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100357784"],"corresponding_institution_ids":["https://openalex.org/I4210151615"],"apc_list":null,"apc_paid":null,"fwci":2.8162,"has_fulltext":false,"cited_by_count":29,"citation_normalized_percentile":{"value":0.92037653,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":"3","issue":"3","first_page":"402","last_page":"417"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9994000196456909,"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":0.9994000196456909,"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":0.9972000122070312,"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":0.9954000115394592,"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/named-entity-recognition","display_name":"Named-entity recognition","score":0.7674354314804077},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7637567520141602},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.7181037068367004},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.634042501449585},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5750868320465088},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5483289361000061},{"id":"https://openalex.org/keywords/medical-record","display_name":"Medical record","score":0.4759092926979065},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4545728862285614},{"id":"https://openalex.org/keywords/sequence-labeling","display_name":"Sequence labeling","score":0.4420493245124817},{"id":"https://openalex.org/keywords/unified-medical-language-system","display_name":"Unified Medical Language System","score":0.41346535086631775},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.136874258518219},{"id":"https://openalex.org/keywords/medicine","display_name":"Medicine","score":0.13213074207305908},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.07581740617752075},{"id":"https://openalex.org/keywords/radiology","display_name":"Radiology","score":0.07271334528923035}],"concepts":[{"id":"https://openalex.org/C2779135771","wikidata":"https://www.wikidata.org/wiki/Q403574","display_name":"Named-entity recognition","level":3,"score":0.7674354314804077},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7637567520141602},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7181037068367004},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.634042501449585},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5750868320465088},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5483289361000061},{"id":"https://openalex.org/C195910791","wikidata":"https://www.wikidata.org/wiki/Q1324077","display_name":"Medical record","level":2,"score":0.4759092926979065},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4545728862285614},{"id":"https://openalex.org/C35639132","wikidata":"https://www.wikidata.org/wiki/Q7452468","display_name":"Sequence labeling","level":3,"score":0.4420493245124817},{"id":"https://openalex.org/C69505689","wikidata":"https://www.wikidata.org/wiki/Q455338","display_name":"Unified Medical Language System","level":2,"score":0.41346535086631775},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.136874258518219},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.13213074207305908},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.07581740617752075},{"id":"https://openalex.org/C126838900","wikidata":"https://www.wikidata.org/wiki/Q77604","display_name":"Radiology","level":1,"score":0.07271334528923035},{"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1162/dint_a_00105","is_oa":true,"landing_page_url":"https://doi.org/10.1162/dint_a_00105","pdf_url":"https://direct.mit.edu/dint/article-pdf/3/3/402/1969110/dint_a_00105.pdf","source":{"id":"https://openalex.org/S4210186383","display_name":"Data Intelligence","issn_l":"2096-7004","issn":["2096-7004","2641-435X"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310315718","host_organization_name":"The MIT Press","host_organization_lineage":["https://openalex.org/P4310315718"],"host_organization_lineage_names":["The MIT Press"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Data Intelligence","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:61015c5102a743ac916420052a222e5e","is_oa":true,"landing_page_url":"https://doaj.org/article/61015c5102a743ac916420052a222e5e","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Data Intelligence, Vol 3, Iss 3 (2021)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1162/dint_a_00105","is_oa":true,"landing_page_url":"https://doi.org/10.1162/dint_a_00105","pdf_url":"https://direct.mit.edu/dint/article-pdf/3/3/402/1969110/dint_a_00105.pdf","source":{"id":"https://openalex.org/S4210186383","display_name":"Data Intelligence","issn_l":"2096-7004","issn":["2096-7004","2641-435X"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310315718","host_organization_name":"The MIT Press","host_organization_lineage":["https://openalex.org/P4310315718"],"host_organization_lineage_names":["The MIT Press"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Data Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.8299999833106995}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3175533348.pdf","grobid_xml":"https://content.openalex.org/works/W3175533348.grobid-xml"},"referenced_works_count":12,"referenced_works":["https://openalex.org/W2120718680","https://openalex.org/W2190421341","https://openalex.org/W2353198173","https://openalex.org/W2398489001","https://openalex.org/W2525778437","https://openalex.org/W2906351693","https://openalex.org/W2965373594","https://openalex.org/W2967649271","https://openalex.org/W3034238904","https://openalex.org/W3210120707","https://openalex.org/W6681746349","https://openalex.org/W6712207982"],"related_works":["https://openalex.org/W857360071","https://openalex.org/W2773616286","https://openalex.org/W3035097673","https://openalex.org/W3198957374","https://openalex.org/W3022333975","https://openalex.org/W4287800519","https://openalex.org/W4308949089","https://openalex.org/W4226048468","https://openalex.org/W4287636191","https://openalex.org/W3093553144"],"abstract_inverted_index":{"Medical":[0],"named":[1,11],"entity":[2,70],"recognition":[3],"(NER)":[4],"is":[5],"an":[6],"area":[7],"in":[8,43,115],"which":[9,148],"medical":[10,16,30,40,44,53,69,74,78,82,106,117,146,154],"entities":[12,75,83],"are":[13],"recognized":[14],"from":[15,76,84,151],"texts,":[17,147],"such":[18,87],"as":[19,88],"diseases,":[20],"drugs,":[21],"surgery":[22],"reports,":[23],"anatomical":[24],"parts,":[25],"and":[26,61,80,123,165,172],"examination":[27],"documents.":[28,45],"Conventional":[29],"NER":[31,54,160],"methods":[32],"do":[33],"not":[34],"make":[35],"full":[36],"use":[37],"of":[38],"un-labelled":[39,105,116,145],"texts":[41,79,118,122],"embedded":[42],"To":[46],"address":[47],"this":[48,96],"issue,":[49],"we":[50,66,94,109],"proposed":[51,159],"a":[52,62,68,111],"approach":[55,161],"based":[56],"on":[57,143],"pre-trained":[58,101,138],"language":[59,102,139],"models":[60,103],"domain":[63],"dictionary.":[64],"First,":[65],"constructed":[67],"dictionary":[71,97],"by":[72],"extracting":[73],"labelled":[77],"collecting":[81],"other":[85],"resources,":[86],"the":[89,128,137,144,158,163],"Yidu-N4K":[90],"data":[91],"set.":[92],"Second,":[93],"employed":[95,110],"to":[98,119,135,169],"train":[99],"domain-specific":[100],"using":[104],"texts.":[107],"Third,":[108],"pseudo":[112,125],"labelling":[113],"mechanism":[114],"automatically":[120],"annotate":[121],"create":[124],"labels.":[126],"Fourth,":[127],"BiLSTM-CRF":[129],"sequence":[130],"tagging":[131],"model":[132],"was":[133],"used":[134],"fine-tune":[136],"models.":[140],"Our":[141],"experiments":[142],"were":[149],"extracted":[150],"Chinese":[152],"electronic":[153],"records,":[155],"show":[156],"that":[157],"enables":[162],"strict":[164],"relaxed":[166],"F1":[167],"scores":[168],"be":[170],"88.7%":[171],"95.3%,":[173],"respectively.":[174]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":10},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":3}],"updated_date":"2026-04-02T15:55:50.835912","created_date":"2025-10-10T00:00:00"}