{"id":"https://openalex.org/W4306176992","doi":"https://doi.org/10.18653/v1/2022.emnlp-main.805","title":"MedJEx: A Medical Jargon Extraction Model with Wiki\u2019s Hyperlink Span and Contextualized Masked Language Model Score","display_name":"MedJEx: A Medical Jargon Extraction Model with Wiki\u2019s Hyperlink Span and Contextualized Masked Language Model Score","publication_year":2022,"publication_date":"2022-01-01","ids":{"openalex":"https://openalex.org/W4306176992","doi":"https://doi.org/10.18653/v1/2022.emnlp-main.805"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2022.emnlp-main.805","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2022.emnlp-main.805","pdf_url":"https://aclanthology.org/2022.emnlp-main.805.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 2022 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2022.emnlp-main.805.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5051373234","display_name":"Sunjae Kwon","orcid":"https://orcid.org/0000-0002-5425-6779"},"institutions":[{"id":"https://openalex.org/I24603500","display_name":"University of Massachusetts Amherst","ror":"https://ror.org/0072zz521","country_code":"US","type":"education","lineage":["https://openalex.org/I24603500"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Sunjae Kwon","raw_affiliation_strings":["UMass Amherst"],"affiliations":[{"raw_affiliation_string":"UMass Amherst","institution_ids":["https://openalex.org/I24603500"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012790041","display_name":"Zonghai Yao","orcid":"https://orcid.org/0000-0002-5707-8410"},"institutions":[{"id":"https://openalex.org/I24603500","display_name":"University of Massachusetts Amherst","ror":"https://ror.org/0072zz521","country_code":"US","type":"education","lineage":["https://openalex.org/I24603500"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zonghai Yao","raw_affiliation_strings":["UMass Amherst"],"affiliations":[{"raw_affiliation_string":"UMass Amherst","institution_ids":["https://openalex.org/I24603500"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029760496","display_name":"H Jordan","orcid":"https://orcid.org/0009-0004-4824-1919"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Harmon Jordan","raw_affiliation_strings":["Health Research Consultant"],"affiliations":[{"raw_affiliation_string":"Health Research Consultant","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110393171","display_name":"David A. Levy","orcid":"https://orcid.org/0009-0000-1530-2309"},"institutions":[{"id":"https://openalex.org/I133738476","display_name":"University of Massachusetts Lowell","ror":"https://ror.org/03hamhx47","country_code":"US","type":"education","lineage":["https://openalex.org/I133738476"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David Levy","raw_affiliation_strings":["UMass Lowell"],"affiliations":[{"raw_affiliation_string":"UMass Lowell","institution_ids":["https://openalex.org/I133738476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005591168","display_name":"Brian D. Corner","orcid":null},"institutions":[{"id":"https://openalex.org/I4210162397","display_name":"UMass Memorial Medical Center","ror":"https://ror.org/053v00853","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1303243448","https://openalex.org/I4210162397"]},{"id":"https://openalex.org/I166722992","display_name":"University of Massachusetts Chan Medical School","ror":"https://ror.org/0464eyp60","country_code":"US","type":"education","lineage":["https://openalex.org/I166722992"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Brian Corner","raw_affiliation_strings":["UMass Medical School"],"affiliations":[{"raw_affiliation_string":"UMass Medical School","institution_ids":["https://openalex.org/I4210162397","https://openalex.org/I166722992"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5017601806","display_name":"Hong Yu","orcid":"https://orcid.org/0000-0001-9263-5035"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hong Yu","raw_affiliation_strings":["U.S. Department of Veterans Affairs.; UMass Amherst.; UMass Lowell.; UMass Medical School"],"affiliations":[{"raw_affiliation_string":"U.S. Department of Veterans Affairs.; UMass Amherst.; UMass Lowell.; UMass Medical School","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5051373234"],"corresponding_institution_ids":["https://openalex.org/I24603500"],"apc_list":null,"apc_paid":null,"fwci":0.9552,"has_fulltext":true,"cited_by_count":11,"citation_normalized_percentile":{"value":0.73581861,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"11733","last_page":"11751"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9991000294685364,"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":0.9991000294685364,"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":0.9986000061035156,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9916999936103821,"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/jargon","display_name":"Jargon","score":0.9588145017623901},{"id":"https://openalex.org/keywords/hyperlink","display_name":"Hyperlink","score":0.9020127058029175},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8250447511672974},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6608299612998962},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.578521192073822},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5222166776657104},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5216941237449646},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.49540746212005615},{"id":"https://openalex.org/keywords/named-entity-recognition","display_name":"Named-entity recognition","score":0.47014859318733215},{"id":"https://openalex.org/keywords/unified-medical-language-system","display_name":"Unified Medical Language System","score":0.4405383765697479},{"id":"https://openalex.org/keywords/span","display_name":"Span (engineering)","score":0.42844730615615845},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.29448139667510986},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.16391441226005554},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.1386030614376068}],"concepts":[{"id":"https://openalex.org/C2777611551","wikidata":"https://www.wikidata.org/wiki/Q17951","display_name":"Jargon","level":2,"score":0.9588145017623901},{"id":"https://openalex.org/C30088001","wikidata":"https://www.wikidata.org/wiki/Q102014","display_name":"Hyperlink","level":3,"score":0.9020127058029175},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8250447511672974},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6608299612998962},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.578521192073822},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5222166776657104},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5216941237449646},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.49540746212005615},{"id":"https://openalex.org/C2779135771","wikidata":"https://www.wikidata.org/wiki/Q403574","display_name":"Named-entity recognition","level":3,"score":0.47014859318733215},{"id":"https://openalex.org/C69505689","wikidata":"https://www.wikidata.org/wiki/Q455338","display_name":"Unified Medical Language System","level":2,"score":0.4405383765697479},{"id":"https://openalex.org/C2778753569","wikidata":"https://www.wikidata.org/wiki/Q1960395","display_name":"Span (engineering)","level":2,"score":0.42844730615615845},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.29448139667510986},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.16391441226005554},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.1386030614376068},{"id":"https://openalex.org/C147176958","wikidata":"https://www.wikidata.org/wiki/Q77590","display_name":"Civil engineering","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"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/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","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}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.18653/v1/2022.emnlp-main.805","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2022.emnlp-main.805","pdf_url":"https://aclanthology.org/2022.emnlp-main.805.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 2022 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2210.05875","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2210.05875","pdf_url":"https://arxiv.org/pdf/2210.05875","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"pmh:oai:pubmedcentral.nih.gov:10129059","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/10129059","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC10129059/pdf/nihms-1843448.pdf","source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Proc Conf Empir Methods Nat Lang Process","raw_type":"Text"},{"id":"doi:10.48550/arxiv.2210.05875","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2210.05875","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.18653/v1/2022.emnlp-main.805","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2022.emnlp-main.805","pdf_url":"https://aclanthology.org/2022.emnlp-main.805.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 2022 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.8399999737739563,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4306176992.pdf"},"referenced_works_count":61,"referenced_works":["https://openalex.org/W112847953","https://openalex.org/W274221391","https://openalex.org/W1525595230","https://openalex.org/W1550258693","https://openalex.org/W1550291595","https://openalex.org/W1841433433","https://openalex.org/W1986211833","https://openalex.org/W1991133427","https://openalex.org/W2004311568","https://openalex.org/W2047782770","https://openalex.org/W2064418625","https://openalex.org/W2071879021","https://openalex.org/W2100627415","https://openalex.org/W2114668172","https://openalex.org/W2129958862","https://openalex.org/W2141086962","https://openalex.org/W2141936101","https://openalex.org/W2145561180","https://openalex.org/W2147880316","https://openalex.org/W2149369282","https://openalex.org/W2154142897","https://openalex.org/W2159583324","https://openalex.org/W2164861117","https://openalex.org/W2178441628","https://openalex.org/W2335791510","https://openalex.org/W2396881363","https://openalex.org/W2398669368","https://openalex.org/W2582146834","https://openalex.org/W2592420893","https://openalex.org/W2604748391","https://openalex.org/W2765441486","https://openalex.org/W2770304476","https://openalex.org/W2776226510","https://openalex.org/W2784948075","https://openalex.org/W2808393080","https://openalex.org/W2885588848","https://openalex.org/W2887280559","https://openalex.org/W2891311366","https://openalex.org/W2896457183","https://openalex.org/W2902446432","https://openalex.org/W2908840510","https://openalex.org/W2911489562","https://openalex.org/W2925863688","https://openalex.org/W2963716420","https://openalex.org/W2965373594","https://openalex.org/W2970476646","https://openalex.org/W2979736514","https://openalex.org/W2982906145","https://openalex.org/W2994782398","https://openalex.org/W3004015233","https://openalex.org/W3034238904","https://openalex.org/W3100452049","https://openalex.org/W3108819963","https://openalex.org/W3150670579","https://openalex.org/W3158665049","https://openalex.org/W3158890082","https://openalex.org/W3166986030","https://openalex.org/W3172427031","https://openalex.org/W4221006722","https://openalex.org/W4285209661","https://openalex.org/W4287746114"],"related_works":["https://openalex.org/W3040422808","https://openalex.org/W4317528635","https://openalex.org/W2499956125","https://openalex.org/W2553927761","https://openalex.org/W2501778858","https://openalex.org/W2485612408","https://openalex.org/W3128124465","https://openalex.org/W235416042","https://openalex.org/W3214311004","https://openalex.org/W4387517132"],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"a":[3,30,50,109],"new":[4],"natural":[5],"language":[6,112],"processing":[7],"(NLP)":[8],"application":[9],"for":[10,17,117],"identifying":[11],"medical":[12,38,52],"jargon":[13,39,53,121],"terms":[14,40],"potentially":[15],"difficult":[16],"patients":[18],"to":[19,61,91],"comprehend":[20],"from":[21,41],"electronic":[22],"health":[23],"record":[24],"(EHR)":[25],"notes.":[26],"We":[27],"first":[28],"present":[29],"novel":[31,51],"and":[32,97,149],"publicly":[33,152],"available":[34],"dataset":[35],"with":[36],"expert-annotated":[37],"18K+":[42],"EHR":[43],"note":[44],"sentences":[45],"($MedJ$).":[46],"Then,":[47],"we":[48,106],"introduce":[49],"extraction":[54],"($MedJEx$)":[55],"model":[56,113],"which":[57],"has":[58],"been":[59],"shown":[60],"outperform":[62],"existing":[63],"state-of-the-art":[64],"NLP":[65],"models.":[66],"First,":[67],"MedJEx":[68,150],"improved":[69,136],"the":[70,93,101,130],"overall":[71],"performance":[72],"when":[73],"it":[74],"was":[75,115],"trained":[76],"on":[77,100,129],"an":[78],"auxiliary":[79,131],"Wikipedia":[80,89,132],"hyperlink":[81,85,133],"span":[82,134],"dataset,":[83],"where":[84],"spans":[86,94],"provide":[87],"additional":[88],"articles":[90],"explain":[92],"(or":[95],"terms),":[96],"then":[98],"fine-tuned":[99],"annotated":[102],"MedJ":[103,148],"data.":[104],"Secondly,":[105],"found":[107],"that":[108,127],"contextualized":[110],"masked":[111],"score":[114],"beneficial":[116],"detecting":[118],"domain-specific":[119],"unfamiliar":[120],"terms.":[122],"Moreover,":[123],"our":[124],"results":[125],"show":[126],"training":[128],"datasets":[135],"six":[137],"out":[138],"of":[139],"eight":[140],"biomedical":[141],"named":[142],"entity":[143],"recognition":[144],"benchmark":[145],"datasets.":[146],"Both":[147],"are":[151],"available.":[153]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":1}],"updated_date":"2026-03-11T14:59:36.786465","created_date":"2022-10-14T00:00:00"}