{"id":"https://openalex.org/W2250565570","doi":"https://doi.org/10.3115/v1/w14-1103","title":"The impact of near domain transfer on biomedical named entity recognition","display_name":"The impact of near domain transfer on biomedical named entity recognition","publication_year":2014,"publication_date":"2014-01-01","ids":{"openalex":"https://openalex.org/W2250565570","doi":"https://doi.org/10.3115/v1/w14-1103","mag":"2250565570"},"language":"en","primary_location":{"id":"doi:10.3115/v1/w14-1103","is_oa":true,"landing_page_url":"https://doi.org/10.3115/v1/w14-1103","pdf_url":"https://aclanthology.org/W14-1103.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 5th International Workshop on Health Text Mining and Information Analysis (Louhi)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/W14-1103.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5073413742","display_name":"Nigel Collier","orcid":"https://orcid.org/0000-0002-7230-4164"},"institutions":[{"id":"https://openalex.org/I1303153112","display_name":"European Bioinformatics Institute","ror":"https://ror.org/02catss52","country_code":"GB","type":"facility","lineage":["https://openalex.org/I1303153112","https://openalex.org/I4210138560"]},{"id":"https://openalex.org/I4210136249","display_name":"University of Applied Sciences Upper Austria","ror":"https://ror.org/03jqp6d56","country_code":"AT","type":"education","lineage":["https://openalex.org/I4210136249"]},{"id":"https://openalex.org/I67868205","display_name":"VNU University of Science","ror":"https://ror.org/05w54hk79","country_code":"VN","type":"education","lineage":["https://openalex.org/I177233841","https://openalex.org/I67868205"]},{"id":"https://openalex.org/I184597095","display_name":"National Institute of Informatics","ror":"https://ror.org/04ksd4g47","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1319490839","https://openalex.org/I184597095","https://openalex.org/I4210158934"]}],"countries":["AT","GB","JP","VN"],"is_corresponding":true,"raw_author_name":"Nigel Collier","raw_affiliation_strings":["European Bioinformatics Institute Hinxton, Cambridge, UK, and National Institute of Informatics, Tokyo, Japan","University of Engineering and Technology -VNU Hanoi, Vietnam","University of Applied Sciences Upper Austria Hagenberg Campus, Austria"],"affiliations":[{"raw_affiliation_string":"European Bioinformatics Institute Hinxton, Cambridge, UK, and National Institute of Informatics, Tokyo, Japan","institution_ids":["https://openalex.org/I1303153112","https://openalex.org/I184597095"]},{"raw_affiliation_string":"University of Engineering and Technology -VNU Hanoi, Vietnam","institution_ids":["https://openalex.org/I67868205"]},{"raw_affiliation_string":"University of Applied Sciences Upper Austria Hagenberg Campus, Austria","institution_ids":["https://openalex.org/I4210136249"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036041371","display_name":"Mai-Vu Tran","orcid":"https://orcid.org/0000-0003-1602-5424"},"institutions":[{"id":"https://openalex.org/I4210136249","display_name":"University of Applied Sciences Upper Austria","ror":"https://ror.org/03jqp6d56","country_code":"AT","type":"education","lineage":["https://openalex.org/I4210136249"]},{"id":"https://openalex.org/I1303153112","display_name":"European Bioinformatics Institute","ror":"https://ror.org/02catss52","country_code":"GB","type":"facility","lineage":["https://openalex.org/I1303153112","https://openalex.org/I4210138560"]},{"id":"https://openalex.org/I184597095","display_name":"National Institute of Informatics","ror":"https://ror.org/04ksd4g47","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1319490839","https://openalex.org/I184597095","https://openalex.org/I4210158934"]},{"id":"https://openalex.org/I67868205","display_name":"VNU University of Science","ror":"https://ror.org/05w54hk79","country_code":"VN","type":"education","lineage":["https://openalex.org/I177233841","https://openalex.org/I67868205"]}],"countries":["AT","GB","JP","VN"],"is_corresponding":false,"raw_author_name":"Mai-vu Tran","raw_affiliation_strings":["European Bioinformatics Institute Hinxton, Cambridge, UK, and National Institute of Informatics, Tokyo, Japan","University of Engineering and Technology -VNU Hanoi, Vietnam","University of Applied Sciences Upper Austria Hagenberg Campus, Austria"],"affiliations":[{"raw_affiliation_string":"European Bioinformatics Institute Hinxton, Cambridge, UK, and National Institute of Informatics, Tokyo, Japan","institution_ids":["https://openalex.org/I1303153112","https://openalex.org/I184597095"]},{"raw_affiliation_string":"University of Engineering and Technology -VNU Hanoi, Vietnam","institution_ids":["https://openalex.org/I67868205"]},{"raw_affiliation_string":"University of Applied Sciences Upper Austria Hagenberg Campus, Austria","institution_ids":["https://openalex.org/I4210136249"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5023827407","display_name":"Ferdinand Paster","orcid":null},"institutions":[{"id":"https://openalex.org/I4210136249","display_name":"University of Applied Sciences Upper Austria","ror":"https://ror.org/03jqp6d56","country_code":"AT","type":"education","lineage":["https://openalex.org/I4210136249"]},{"id":"https://openalex.org/I67868205","display_name":"VNU University of Science","ror":"https://ror.org/05w54hk79","country_code":"VN","type":"education","lineage":["https://openalex.org/I177233841","https://openalex.org/I67868205"]},{"id":"https://openalex.org/I1303153112","display_name":"European Bioinformatics Institute","ror":"https://ror.org/02catss52","country_code":"GB","type":"facility","lineage":["https://openalex.org/I1303153112","https://openalex.org/I4210138560"]},{"id":"https://openalex.org/I184597095","display_name":"National Institute of Informatics","ror":"https://ror.org/04ksd4g47","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1319490839","https://openalex.org/I184597095","https://openalex.org/I4210158934"]}],"countries":["AT","GB","JP","VN"],"is_corresponding":false,"raw_author_name":"Ferdinand Paster","raw_affiliation_strings":["University of Engineering and Technology -VNU Hanoi, Vietnam","European Bioinformatics Institute Hinxton, Cambridge, UK, and National Institute of Informatics, Tokyo, Japan","University of Applied Sciences Upper Austria Hagenberg Campus, Austria"],"affiliations":[{"raw_affiliation_string":"University of Engineering and Technology -VNU Hanoi, Vietnam","institution_ids":["https://openalex.org/I67868205"]},{"raw_affiliation_string":"European Bioinformatics Institute Hinxton, Cambridge, UK, and National Institute of Informatics, Tokyo, Japan","institution_ids":["https://openalex.org/I1303153112","https://openalex.org/I184597095"]},{"raw_affiliation_string":"University of Applied Sciences Upper Austria Hagenberg Campus, Austria","institution_ids":["https://openalex.org/I4210136249"]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5073413742"],"corresponding_institution_ids":["https://openalex.org/I1303153112","https://openalex.org/I184597095","https://openalex.org/I4210136249","https://openalex.org/I67868205"],"apc_list":null,"apc_paid":null,"fwci":1.2685,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.86086097,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"11","last_page":"20"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9990000128746033,"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":0.9990000128746033,"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":0.9987999796867371,"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":0.9961000084877014,"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":0.5972867608070374},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5703775882720947},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.32720649242401123},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1494767963886261}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5972867608070374},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5703775882720947},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32720649242401123},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1494767963886261},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.3115/v1/w14-1103","is_oa":true,"landing_page_url":"https://doi.org/10.3115/v1/w14-1103","pdf_url":"https://aclanthology.org/W14-1103.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 5th International Workshop on Health Text Mining and Information Analysis (Louhi)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.681.5846","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.681.5846","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.aclweb.org/anthology/W/W14/W14-1103.pdf","raw_type":"text"}],"best_oa_location":{"id":"doi:10.3115/v1/w14-1103","is_oa":true,"landing_page_url":"https://doi.org/10.3115/v1/w14-1103","pdf_url":"https://aclanthology.org/W14-1103.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 5th International Workshop on Health Text Mining and Information Analysis (Louhi)","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.550000011920929,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G2689612763","display_name":null,"funder_award_id":"Marie","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G3444298493","display_name":null,"funder_award_id":"Marie Curie International Incoming","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G4681381370","display_name":null,"funder_award_id":"Marie Curie","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G8606174952","display_name":"Semantic mining of phenotype associations from the biomedical literature","funder_award_id":"301806","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2250565570.pdf","grobid_xml":"https://content.openalex.org/works/W2250565570.grobid-xml"},"referenced_works_count":41,"referenced_works":["https://openalex.org/W98423455","https://openalex.org/W1555643513","https://openalex.org/W1747861911","https://openalex.org/W1848260265","https://openalex.org/W1850865022","https://openalex.org/W2004763266","https://openalex.org/W2010450719","https://openalex.org/W2018874418","https://openalex.org/W2033377040","https://openalex.org/W2047782770","https://openalex.org/W2048140075","https://openalex.org/W2052525903","https://openalex.org/W2061231608","https://openalex.org/W2088212442","https://openalex.org/W2103017472","https://openalex.org/W2104254426","https://openalex.org/W2104936489","https://openalex.org/W2110298216","https://openalex.org/W2111362445","https://openalex.org/W2119412782","https://openalex.org/W2119759918","https://openalex.org/W2120354757","https://openalex.org/W2121244856","https://openalex.org/W2124772738","https://openalex.org/W2124991490","https://openalex.org/W2125055259","https://openalex.org/W2126434293","https://openalex.org/W2128386749","https://openalex.org/W2131887446","https://openalex.org/W2135352205","https://openalex.org/W2136410628","https://openalex.org/W2141099517","https://openalex.org/W2142678031","https://openalex.org/W2147880316","https://openalex.org/W2154333659","https://openalex.org/W2163107094","https://openalex.org/W2163685645","https://openalex.org/W2165698076","https://openalex.org/W2604748391","https://openalex.org/W3146885639","https://openalex.org/W4248234957"],"related_works":["https://openalex.org/W3107474891","https://openalex.org/W2623347760","https://openalex.org/W3034138874","https://openalex.org/W2743342830","https://openalex.org/W1864954421","https://openalex.org/W2362192218","https://openalex.org/W1991466308","https://openalex.org/W2801011252","https://openalex.org/W4313681550","https://openalex.org/W1571048958"],"abstract_inverted_index":{"Current":[0],"research":[1],"in":[2,13,101,116],"fully":[3],"supervised":[4],"biomedical":[5],"named":[6],"entity":[7],"recognition":[8],"(bioNER)":[9],"is":[10],"often":[11],"conducted":[12],"a":[14,56],"setting":[15],"of":[16,78,125,159],"low":[17],"sample":[18],"sizes.":[19],"Whilst":[20],"experimental":[21],"results":[22],"show":[23],"strong":[24],"performance":[25,98,118,144],"in-domain":[26],"it":[27],"has":[28],"been":[29,49],"recognised":[30],"that":[31,139],"quality":[32],"suffers":[33],"when":[34],"models":[35],"are":[36,72],"applied":[37],"to":[38,130],"heterogeneous":[39],"text":[40],"collections.":[41],"However":[42],"the":[43,76,156],"causal":[44],"factors":[45],"have":[46],"until":[47],"now":[48],"uncertain.":[50],"In":[51],"this":[52],"paper":[53],"we":[54,140,150],"describe":[55],"controlled":[57],"experiment":[58],"into":[59],"near":[60,79],"domain":[61,80,102],"bias":[62],"for":[63,74,120,134,155],"two":[64],"Medline":[65],"corpora":[66],"on":[67,96],"hereditary":[68],"diseases.":[69],"Five":[70],"strategies":[71],"employed":[73],"mitigating":[75],"impact":[77],"transference":[81],"including":[82],"simple":[83],"transference,":[84],"pooling,":[85],"stacking,":[86],"class":[87],"re-labeling":[88],"and":[89,105,145],"feature":[90,106],"augmentation.":[91],"We":[92,137],"measure":[93],"their":[94],"effect":[95],"f-score":[97,109],"against":[99],"an":[100],"baseline.":[103],"Stacking":[104],"augmentation":[107],"mitigate":[108],"loss":[110],"but":[111],"do":[112,151],"not":[113,152],"necessarily":[114],"result":[115],"superior":[117],"except":[119],"selected":[121],"classes.":[122,136],"Simple":[123],"pooling":[124],"data":[126],"across":[127],"domains":[128,160],"failed":[129],"exploit":[131],"size":[132],"effects":[133],"most":[135],"conclude":[138],"can":[141],"expect":[142],"lower":[143],"higher":[146],"annotation":[147],"costs":[148],"if":[149],"adequately":[153],"compensate":[154],"distributional":[157],"dissimilarities":[158],"during":[161],"learning.":[162]},"counts_by_year":[{"year":2017,"cited_by_count":1},{"year":2015,"cited_by_count":2}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}