{"id":"https://openalex.org/W3153694186","doi":"https://doi.org/10.1145/3442381.3450128","title":"Biomedical Vocabulary Alignment at Scale in\u00a0the\u00a0UMLS\u00a0Metathesaurus","display_name":"Biomedical Vocabulary Alignment at Scale in\u00a0the\u00a0UMLS\u00a0Metathesaurus","publication_year":2021,"publication_date":"2021-04-19","ids":{"openalex":"https://openalex.org/W3153694186","doi":"https://doi.org/10.1145/3442381.3450128","mag":"3153694186","pmid":"https://pubmed.ncbi.nlm.nih.gov/34514472"},"language":"en","primary_location":{"id":"doi:10.1145/3442381.3450128","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3442381.3450128","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Web Conference 2021","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3442381.3450128","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5066629222","display_name":"Vinh Nguyen","orcid":null},"institutions":[{"id":"https://openalex.org/I2800548410","display_name":"United States National Library of Medicine","ror":"https://ror.org/0060t0j89","country_code":"US","type":"archive","lineage":["https://openalex.org/I1299022934","https://openalex.org/I1299303238","https://openalex.org/I2800548410"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Vinh Nguyen","raw_affiliation_strings":["National Library of Medicine, NIH, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Library of Medicine, NIH, USA","institution_ids":["https://openalex.org/I2800548410"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064336316","display_name":"Hong Yung Yip","orcid":"https://orcid.org/0000-0003-1393-7890"},"institutions":[{"id":"https://openalex.org/I155781252","display_name":"University of South Carolina","ror":"https://ror.org/02b6qw903","country_code":"US","type":"education","lineage":["https://openalex.org/I155781252"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hong Yung Yip","raw_affiliation_strings":["University of South Carolina, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of South Carolina, USA","institution_ids":["https://openalex.org/I155781252"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5073807945","display_name":"Olivier Bodenreider","orcid":"https://orcid.org/0000-0003-4769-4217"},"institutions":[{"id":"https://openalex.org/I2800548410","display_name":"United States National Library of Medicine","ror":"https://ror.org/0060t0j89","country_code":"US","type":"archive","lineage":["https://openalex.org/I1299022934","https://openalex.org/I1299303238","https://openalex.org/I2800548410"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Olivier Bodenreider","raw_affiliation_strings":["US National Library of Medicine, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"US National Library of Medicine, USA","institution_ids":["https://openalex.org/I2800548410"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5066629222"],"corresponding_institution_ids":["https://openalex.org/I2800548410"],"apc_list":null,"apc_paid":null,"fwci":1.3015,"has_fulltext":false,"cited_by_count":21,"citation_normalized_percentile":{"value":0.7970061,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"2021","issue":null,"first_page":"2672","last_page":"2683"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9997000098228455,"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":0.9997000098228455,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9983000159263611,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.9933000206947327,"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/unified-medical-language-system","display_name":"Unified Medical Language System","score":0.9592931866645813},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8213129043579102},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.6833332180976868},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6818111538887024},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.6291847229003906},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5998702049255371},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5922505259513855},{"id":"https://openalex.org/keywords/terminology","display_name":"Terminology","score":0.5812100172042847},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4569748640060425},{"id":"https://openalex.org/keywords/controlled-vocabulary","display_name":"Controlled vocabulary","score":0.4459105134010315},{"id":"https://openalex.org/keywords/generalizability-theory","display_name":"Generalizability theory","score":0.44228291511535645},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.4210568070411682},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.13233745098114014},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.09839245676994324}],"concepts":[{"id":"https://openalex.org/C69505689","wikidata":"https://www.wikidata.org/wiki/Q455338","display_name":"Unified Medical Language System","level":2,"score":0.9592931866645813},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8213129043579102},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.6833332180976868},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6818111538887024},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.6291847229003906},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5998702049255371},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5922505259513855},{"id":"https://openalex.org/C547195049","wikidata":"https://www.wikidata.org/wiki/Q1725664","display_name":"Terminology","level":2,"score":0.5812100172042847},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4569748640060425},{"id":"https://openalex.org/C110615152","wikidata":"https://www.wikidata.org/wiki/Q1469824","display_name":"Controlled vocabulary","level":2,"score":0.4459105134010315},{"id":"https://openalex.org/C27158222","wikidata":"https://www.wikidata.org/wiki/Q5532422","display_name":"Generalizability theory","level":2,"score":0.44228291511535645},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.4210568070411682},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.13233745098114014},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.09839245676994324},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3442381.3450128","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3442381.3450128","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Web Conference 2021","raw_type":"proceedings-article"},{"id":"pmid:34514472","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/34514472","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":"Proceedings of the ... International World-Wide Web Conference. International WWW Conference","raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:8434895","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/8434895","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":"Proc Int World Wide Web Conf","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1145/3442381.3450128","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3442381.3450128","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Web Conference 2021","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.8199999928474426,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":48,"referenced_works":["https://openalex.org/W102861580","https://openalex.org/W192652968","https://openalex.org/W1566018662","https://openalex.org/W1689711448","https://openalex.org/W1822004795","https://openalex.org/W1829379010","https://openalex.org/W1832693441","https://openalex.org/W1978394996","https://openalex.org/W1983578042","https://openalex.org/W2010392031","https://openalex.org/W2010866855","https://openalex.org/W2083195256","https://openalex.org/W2087361167","https://openalex.org/W2101026445","https://openalex.org/W2106612368","https://openalex.org/W2118100588","https://openalex.org/W2120699290","https://openalex.org/W2122410182","https://openalex.org/W2131660156","https://openalex.org/W2157364932","https://openalex.org/W2159583324","https://openalex.org/W2165533158","https://openalex.org/W2167312525","https://openalex.org/W2171313960","https://openalex.org/W2250387780","https://openalex.org/W2251427843","https://openalex.org/W2251919380","https://openalex.org/W2345968833","https://openalex.org/W2406695577","https://openalex.org/W2461338233","https://openalex.org/W2508865106","https://openalex.org/W2510940142","https://openalex.org/W2759181158","https://openalex.org/W2887535136","https://openalex.org/W2911489562","https://openalex.org/W2944400536","https://openalex.org/W2950133940","https://openalex.org/W2950577311","https://openalex.org/W2957937874","https://openalex.org/W2963104256","https://openalex.org/W2963341956","https://openalex.org/W2963355447","https://openalex.org/W2970550417","https://openalex.org/W3003173133","https://openalex.org/W3029454371","https://openalex.org/W3090380219","https://openalex.org/W3092008332","https://openalex.org/W3117041486"],"related_works":["https://openalex.org/W2509297716","https://openalex.org/W1508778694","https://openalex.org/W138082899","https://openalex.org/W2114373757","https://openalex.org/W2036729745","https://openalex.org/W2010487328","https://openalex.org/W2340589664","https://openalex.org/W1780032657","https://openalex.org/W2264448939","https://openalex.org/W4323777127"],"abstract_inverted_index":{"With":[0],"214":[1],"source":[2,89],"vocabularies,":[3],"the":[4,10,43,58,72,82,87,105,114,120,132,139,165,185,196],"construction":[5,61,109,188],"and":[6,23,32,41,84,156,173],"maintenance":[7],"process":[8,62,189],"of":[9,38,45,74,86,116,122,125,145,151],"UMLS":[11,46,59,88,107,186,197],"(Unified":[12],"Medical":[13],"Language":[14],"System)":[15],"Metathesaurus":[16,60,108,187],"terminology":[17],"integration":[18],"system":[19],"is":[20,119],"costly,":[21],"time-consuming,":[22],"error-prone":[24],"as":[25],"it":[26],"primarily":[27],"relies":[28],"on":[29],"(1)":[30],"lexical":[31,126],"semantic":[33],"processing":[34],"for":[35,48,70,183],"suggesting":[36,75],"groupings":[37],"synonymous":[39,76],"terms,":[40],"(2)":[42],"expertise":[44],"editors":[47],"curating":[49],"these":[50],"synonymy":[51,193],"predictions.":[52],"This":[53,177],"paper":[54],"aims":[55],"to":[56,81,113,195],"improve":[57],"by":[63,190],"developing":[64],"a":[65,99],"novel":[66,178],"supervised":[67],"learning":[68,95],"approach":[69,97,101,118,148,162,179],"improving":[71,184],"task":[73],"pairs":[77,130],"that":[78,103],"can":[79],"scale":[80],"size":[83],"diversity":[85],"vocabularies.":[90],"We":[91],"evaluate":[92],"this":[93],"deep":[94],"(DL)":[96],"against":[98],"rule-based":[100],"(RBA)":[102],"approximates":[104],"current":[106],"process.":[110,134],"The":[111],"key":[112],"generalizability":[115],"our":[117,146],"use":[121],"various":[123],"degrees":[124],"similarity":[127],"in":[128,149,168],"negative":[129],"during":[131],"training":[133],"Our":[135,160],"initial":[136],"experiments":[137],"demonstrate":[138],"strong":[140],"performance":[141],"across":[142],"multiple":[143],"datasets":[144],"DL":[147,161],"terms":[150],"recall":[152,169],"(91-92%),":[153],"precision":[154,171],"(88-99%),":[155],"F1":[157,174],"score":[158,175],"(89-95%).":[159],"largely":[163],"outperforms":[164],"RBA":[166],"method":[167],"(+23%),":[170],"(+2.4%),":[172],"(+14.1%).":[176],"has":[180],"great":[181],"potential":[182],"providing":[191],"better":[192],"suggestions":[194],"editors.":[198]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":1}],"updated_date":"2026-04-26T08:31:28.666265","created_date":"2025-10-10T00:00:00"}