{"id":"https://openalex.org/W2972313266","doi":"https://doi.org/10.18653/v1/w19-3204","title":"MedNorm: A Corpus and Embeddings for Cross-terminology Medical Concept Normalisation","display_name":"MedNorm: A Corpus and Embeddings for Cross-terminology Medical Concept Normalisation","publication_year":2019,"publication_date":"2019-01-01","ids":{"openalex":"https://openalex.org/W2972313266","doi":"https://doi.org/10.18653/v1/w19-3204","mag":"2972313266"},"language":"en","primary_location":{"id":"doi:10.18653/v1/w19-3204","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w19-3204","pdf_url":"https://www.aclweb.org/anthology/W19-3204.pdf","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 Fourth Social Media Mining for Health Applications (#SMM4H) Workshop & Shared Task","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/W19-3204.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5058088514","display_name":"Maksim Belousov","orcid":"https://orcid.org/0000-0001-8574-5439"},"institutions":[{"id":"https://openalex.org/I28407311","display_name":"University of Manchester","ror":"https://ror.org/027m9bs27","country_code":"GB","type":"education","lineage":["https://openalex.org/I28407311"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Maksim Belousov","raw_affiliation_strings":["School of Computer Science The University of Manchester United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science The University of Manchester United Kingdom","institution_ids":["https://openalex.org/I28407311"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075860605","display_name":"William G Dixon","orcid":"https://orcid.org/0000-0001-5881-4857"},"institutions":[{"id":"https://openalex.org/I28407311","display_name":"University of Manchester","ror":"https://ror.org/027m9bs27","country_code":"GB","type":"education","lineage":["https://openalex.org/I28407311"]},{"id":"https://openalex.org/I4210117448","display_name":"Arthritis UK","ror":"https://ror.org/02jkpm469","country_code":"GB","type":"nonprofit","lineage":["https://openalex.org/I4210117448"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"William G. Dixon","raw_affiliation_strings":["Centre for Epidemiology Versus Arthritis The University of Manchester United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Epidemiology Versus Arthritis The University of Manchester United Kingdom","institution_ids":["https://openalex.org/I4210117448","https://openalex.org/I28407311"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005912060","display_name":"Goran Nenadi\u0107","orcid":"https://orcid.org/0000-0003-0795-5363"},"institutions":[{"id":"https://openalex.org/I28407311","display_name":"University of Manchester","ror":"https://ror.org/027m9bs27","country_code":"GB","type":"education","lineage":["https://openalex.org/I28407311"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Goran Nenadic","raw_affiliation_strings":["School of Computer Science The University of Manchester United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science The University of Manchester United Kingdom","institution_ids":["https://openalex.org/I28407311"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3419,"has_fulltext":true,"cited_by_count":7,"citation_normalized_percentile":{"value":0.59835054,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"31","last_page":"39"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9995999932289124,"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":0.9983999729156494,"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/computer-science","display_name":"Computer science","score":0.8405762910842896},{"id":"https://openalex.org/keywords/terminology","display_name":"Terminology","score":0.731105625629425},{"id":"https://openalex.org/keywords/snomed-ct","display_name":"SNOMED CT","score":0.6866639256477356},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.593349039554596},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.55758136510849},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5558792948722839},{"id":"https://openalex.org/keywords/controlled-vocabulary","display_name":"Controlled vocabulary","score":0.4935511350631714},{"id":"https://openalex.org/keywords/unified-medical-language-system","display_name":"Unified Medical Language System","score":0.4843083918094635},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4633519947528839},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.4332748353481293},{"id":"https://openalex.org/keywords/medical-terminology","display_name":"Medical terminology","score":0.4297822415828705},{"id":"https://openalex.org/keywords/open-biomedical-ontologies","display_name":"Open Biomedical Ontologies","score":0.41902631521224976},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.4170053005218506},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.4165078401565552},{"id":"https://openalex.org/keywords/semantic-web","display_name":"Semantic Web","score":0.196384996175766},{"id":"https://openalex.org/keywords/ontology-alignment","display_name":"Ontology alignment","score":0.14854994416236877},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.09583505988121033}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8405762910842896},{"id":"https://openalex.org/C547195049","wikidata":"https://www.wikidata.org/wiki/Q1725664","display_name":"Terminology","level":2,"score":0.731105625629425},{"id":"https://openalex.org/C206497026","wikidata":"https://www.wikidata.org/wiki/Q1753883","display_name":"SNOMED CT","level":3,"score":0.6866639256477356},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.593349039554596},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.55758136510849},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5558792948722839},{"id":"https://openalex.org/C110615152","wikidata":"https://www.wikidata.org/wiki/Q1469824","display_name":"Controlled vocabulary","level":2,"score":0.4935511350631714},{"id":"https://openalex.org/C69505689","wikidata":"https://www.wikidata.org/wiki/Q455338","display_name":"Unified Medical Language System","level":2,"score":0.4843083918094635},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4633519947528839},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.4332748353481293},{"id":"https://openalex.org/C511227900","wikidata":"https://www.wikidata.org/wiki/Q1192539","display_name":"Medical terminology","level":2,"score":0.4297822415828705},{"id":"https://openalex.org/C137982476","wikidata":"https://www.wikidata.org/wiki/Q7072326","display_name":"Open Biomedical Ontologies","level":5,"score":0.41902631521224976},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.4170053005218506},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4165078401565552},{"id":"https://openalex.org/C2129575","wikidata":"https://www.wikidata.org/wiki/Q54837","display_name":"Semantic Web","level":2,"score":0.196384996175766},{"id":"https://openalex.org/C98893333","wikidata":"https://www.wikidata.org/wiki/Q4339878","display_name":"Ontology alignment","level":4,"score":0.14854994416236877},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.09583505988121033},{"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},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C22550185","wikidata":"https://www.wikidata.org/wiki/Q7095047","display_name":"Ontology-based data integration","level":3,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/w19-3204","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w19-3204","pdf_url":"https://www.aclweb.org/anthology/W19-3204.pdf","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 Fourth Social Media Mining for Health Applications (#SMM4H) Workshop & Shared Task","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/w19-3204","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w19-3204","pdf_url":"https://www.aclweb.org/anthology/W19-3204.pdf","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 Fourth Social Media Mining for Health Applications (#SMM4H) Workshop & Shared Task","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2972313266.pdf","grobid_xml":"https://content.openalex.org/works/W2972313266.grobid-xml"},"referenced_works_count":22,"referenced_works":["https://openalex.org/W138612281","https://openalex.org/W1483357098","https://openalex.org/W1614298861","https://openalex.org/W1809130274","https://openalex.org/W2059975159","https://openalex.org/W2085752173","https://openalex.org/W2131546905","https://openalex.org/W2154851992","https://openalex.org/W2187089797","https://openalex.org/W2366141641","https://openalex.org/W2509884321","https://openalex.org/W2610937402","https://openalex.org/W2743104969","https://openalex.org/W2794085611","https://openalex.org/W2887535136","https://openalex.org/W2895296143","https://openalex.org/W2950577311","https://openalex.org/W2962756421","https://openalex.org/W2963460103","https://openalex.org/W3104097132","https://openalex.org/W4293651439","https://openalex.org/W4297571622"],"related_works":["https://openalex.org/W1902843062","https://openalex.org/W2010248145","https://openalex.org/W4206342372","https://openalex.org/W4388685083","https://openalex.org/W2490782389","https://openalex.org/W2036729745","https://openalex.org/W2064177607","https://openalex.org/W2157272674","https://openalex.org/W2068800403","https://openalex.org/W2345577426"],"abstract_inverted_index":{"The":[0,80],"medical":[1,172],"concept":[2,41,117,173],"normalisation":[3,42,174],"task":[4],"aims":[5],"to":[6,10,63,88,110,176,182],"map":[7],"textual":[8,59],"descriptions":[9,60],"standard":[11],"terminologies":[12,25,113],"such":[13],"as":[14],"SNOMED-CT":[15],"or":[16],"MedDRA.":[17],"Existing":[18],"publicly":[19,71],"available":[20,72,175],"datasets":[21,73,91],"annotated":[22],"using":[23],"different":[24,112,160],"cannot":[26],"be":[27,83,98],"simply":[28],"merged":[29],"and":[30,32,53,66,76,95,122,140,143,168],"utilised,":[31],"therefore":[33],"become":[34],"less":[35],"valuable":[36],"when":[37],"developing":[38],"machine":[39],"learningbased":[40],"systems.":[43],"To":[44],"address":[45],"that,":[46],"we":[47],"designed":[48],"a":[49,55,108,115,133,152,166,183],"data":[50,102],"harmonisation":[51],"pipeline":[52,81],"engineered":[54],"corpus":[56,94,167],"of":[57,186],"27,979":[58],"simultaneously":[61],"mapped":[62],"both":[64,138],"MedDRA":[65],"SNOMED-CT,":[67],"sourced":[68],"from":[69,159],"five":[70],"across":[74],"biomedical":[75],"social":[77],"media":[78],"domains.":[79],"can":[82,135],"used":[84],"in":[85,100],"the":[86,93,177,187],"future":[87],"integrate":[89],"new":[90],"into":[92,114],"also":[96,106,156],"could":[97],"applied":[99],"relevant":[101],"curation":[103],"tasks.":[104],"We":[105,162],"described":[107],"method":[109],"merge":[111],"single":[116],"graph":[118,134],"preserving":[119],"their":[120],"relations":[121,142],"demonstrated":[123],"that":[124,164],"representation":[125],"learning":[126],"approach":[127],"based":[128],"on":[129,132],"random":[130],"walks":[131],"efficiently":[136],"encode":[137],"hierarchical":[139],"equivalent":[141],"capture":[144],"semantic":[145],"similarities":[146],"not":[147],"only":[148],"between":[149,157],"concepts":[150,158],"inside":[151],"given":[153],"terminology":[154],"but":[155],"terminologies.":[161],"believe":[163],"making":[165],"embeddings":[169],"for":[170],"cross-terminology":[171],"research":[178],"community":[179],"would":[180],"contribute":[181],"better":[184],"understanding":[185],"task.":[188]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":4}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}