{"id":"https://openalex.org/W3168522299","doi":"https://doi.org/10.18653/v1/2021.bionlp-1.2","title":"Triplet-Trained Vector Space and Sieve-Based Search Improve Biomedical Concept Normalization","display_name":"Triplet-Trained Vector Space and Sieve-Based Search Improve Biomedical Concept Normalization","publication_year":2021,"publication_date":"2021-01-01","ids":{"openalex":"https://openalex.org/W3168522299","doi":"https://doi.org/10.18653/v1/2021.bionlp-1.2","mag":"3168522299"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2021.bionlp-1.2","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2021.bionlp-1.2","pdf_url":"https://aclanthology.org/2021.bionlp-1.2.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 20th Workshop on Biomedical Language Processing","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2021.bionlp-1.2.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5064023395","display_name":"Dongfang Xu","orcid":"https://orcid.org/0000-0003-0828-1102"},"institutions":[{"id":"https://openalex.org/I138006243","display_name":"University of Arizona","ror":"https://ror.org/03m2x1q45","country_code":"US","type":"education","lineage":["https://openalex.org/I138006243"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Dongfang Xu","raw_affiliation_strings":["School of Information University of Arizona Tucson, AZ"],"affiliations":[{"raw_affiliation_string":"School of Information University of Arizona Tucson, AZ","institution_ids":["https://openalex.org/I138006243"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5068978543","display_name":"Steven Bethard","orcid":"https://orcid.org/0000-0001-9560-6491"},"institutions":[{"id":"https://openalex.org/I138006243","display_name":"University of Arizona","ror":"https://ror.org/03m2x1q45","country_code":"US","type":"education","lineage":["https://openalex.org/I138006243"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Steven Bethard","raw_affiliation_strings":["School of Information University of Arizona Tucson, AZ"],"affiliations":[{"raw_affiliation_string":"School of Information University of Arizona Tucson, AZ","institution_ids":["https://openalex.org/I138006243"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5064023395"],"corresponding_institution_ids":["https://openalex.org/I138006243"],"apc_list":null,"apc_paid":null,"fwci":0.5694,"has_fulltext":true,"cited_by_count":7,"citation_normalized_percentile":{"value":0.64299128,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"11","last_page":"22"},"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":0.9988999962806702,"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":0.9943000078201294,"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":0.7620779275894165},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.6742562055587769},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6352657079696655},{"id":"https://openalex.org/keywords/retraining","display_name":"Retraining","score":0.624008059501648},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5765703916549683},{"id":"https://openalex.org/keywords/vector-space","display_name":"Vector space","score":0.4978783130645752},{"id":"https://openalex.org/keywords/vector-space-model","display_name":"Vector space model","score":0.49186062812805176},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4758070409297943},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.47082024812698364},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.35274726152420044},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08760201930999756}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7620779275894165},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.6742562055587769},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6352657079696655},{"id":"https://openalex.org/C2778712577","wikidata":"https://www.wikidata.org/wiki/Q3505966","display_name":"Retraining","level":2,"score":0.624008059501648},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5765703916549683},{"id":"https://openalex.org/C13336665","wikidata":"https://www.wikidata.org/wiki/Q125977","display_name":"Vector space","level":2,"score":0.4978783130645752},{"id":"https://openalex.org/C89686163","wikidata":"https://www.wikidata.org/wiki/Q1187982","display_name":"Vector space model","level":2,"score":0.49186062812805176},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4758070409297943},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.47082024812698364},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.35274726152420044},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08760201930999756},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","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/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C155202549","wikidata":"https://www.wikidata.org/wiki/Q178803","display_name":"International trade","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.18653/v1/2021.bionlp-1.2","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2021.bionlp-1.2","pdf_url":"https://aclanthology.org/2021.bionlp-1.2.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 20th Workshop on Biomedical Language Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:repository.arizona.edu:10150/663578","is_oa":true,"landing_page_url":"http://hdl.handle.net/10150/663578","pdf_url":null,"source":{"id":"https://openalex.org/S4306400271","display_name":"UA Campus Repository (The University of Arizona)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I138006243","host_organization_name":"University of Arizona","host_organization_lineage":["https://openalex.org/I138006243"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"Proceedings of the 20th Workshop on Biomedical Language Processing, BioNLP 2021","raw_type":"Proceedings"}],"best_oa_location":{"id":"doi:10.18653/v1/2021.bionlp-1.2","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2021.bionlp-1.2","pdf_url":"https://aclanthology.org/2021.bionlp-1.2.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 20th Workshop on Biomedical Language Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2136782543","display_name":null,"funder_award_id":"R01LM012918","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G3611247453","display_name":null,"funder_award_id":"R01GM","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G4863354295","display_name":null,"funder_award_id":"R01GM114355","funder_id":"https://openalex.org/F4320337354","funder_display_name":"National Institute of General Medical Sciences"},{"id":"https://openalex.org/G6011010749","display_name":null,"funder_award_id":"1228509","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6531036774","display_name":null,"funder_award_id":"R01GM114355","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"},{"id":"https://openalex.org/F4320337354","display_name":"National Institute of General Medical Sciences","ror":"https://ror.org/04q48ey07"},{"id":"https://openalex.org/F4320337372","display_name":"U.S. National Library of Medicine","ror":"https://ror.org/0060t0j89"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3168522299.pdf","grobid_xml":"https://content.openalex.org/works/W3168522299.grobid-xml"},"referenced_works_count":43,"referenced_works":["https://openalex.org/W1530032857","https://openalex.org/W2107890417","https://openalex.org/W2129038679","https://openalex.org/W2142016317","https://openalex.org/W2158743996","https://openalex.org/W2159583324","https://openalex.org/W2169099542","https://openalex.org/W2169491861","https://openalex.org/W2252174377","https://openalex.org/W2259159222","https://openalex.org/W2340690086","https://openalex.org/W2346452181","https://openalex.org/W2412122516","https://openalex.org/W2414378847","https://openalex.org/W2509884321","https://openalex.org/W2510940142","https://openalex.org/W2515403501","https://openalex.org/W2598634450","https://openalex.org/W2754624511","https://openalex.org/W2763990719","https://openalex.org/W2782318039","https://openalex.org/W2798442412","https://openalex.org/W2808598571","https://openalex.org/W2808838104","https://openalex.org/W2911489562","https://openalex.org/W2915128229","https://openalex.org/W2917968119","https://openalex.org/W2963341956","https://openalex.org/W2963775347","https://openalex.org/W2964271799","https://openalex.org/W2967690619","https://openalex.org/W2970641574","https://openalex.org/W2972483465","https://openalex.org/W2980508402","https://openalex.org/W3034229721","https://openalex.org/W3035021780","https://openalex.org/W3035691659","https://openalex.org/W3046375318","https://openalex.org/W3088349482","https://openalex.org/W3098115739","https://openalex.org/W3099206234","https://openalex.org/W3108567500","https://openalex.org/W3117138190"],"related_works":["https://openalex.org/W2096728994","https://openalex.org/W2349139068","https://openalex.org/W1974406477","https://openalex.org/W3161401723","https://openalex.org/W1540114765","https://openalex.org/W105748137","https://openalex.org/W2391634343","https://openalex.org/W2362958218","https://openalex.org/W1883708690","https://openalex.org/W1966027089"],"abstract_inverted_index":{"Concept":[0],"normalization,":[1,30],"the":[2,60,90],"task":[3],"of":[4,8,70,72,85,125],"linking":[5],"textual":[6],"mentions":[7,32],"concepts":[9,11,34,73],"to":[10],"in":[12],"an":[13],"ontology,":[14],"is":[15],"critical":[16],"for":[17,28,87,131,141],"mining":[18,63],"and":[19,33,59],"analyzing":[20],"biomedical":[21],"texts.":[22],"We":[23,81],"propose":[24],"a":[25,44,83],"vector-space":[26,92],"model":[27,105],"concept":[29],"where":[31],"are":[35,41,113,121,129],"encoded":[36],"via":[37,43],"transformer":[38,53],"networks":[39,54],"that":[40,96,112,128],"trained":[42,91,114,140],"triplet":[45,50,62],"objective":[46],"with":[47,68,89,103],"online":[48,61],"hard":[49],"mining.":[51],"The":[52],"refine":[55],"existing":[56],"pre-trained":[57],"models,":[58],"makes":[64],"training":[65,76],"efficient":[66],"even":[67],"hundreds":[69],"thousands":[71],"by":[74],"sampling":[75],"triples":[77],"within":[78,122],"each":[79,132,142],"mini-batch.":[80],"introduce":[82],"variety":[84],"strategies":[86],"searching":[88],"model,":[93],"including":[94],"approaches":[95],"incorporate":[97],"domain-specific":[98],"synonyms":[99],"at":[100],"search":[101],"time":[102],"no":[104],"retraining.":[106],"Across":[107],"five":[108],"datasets,":[109],"our":[110],"models":[111,127,136],"only":[115],"once":[116],"on":[117,147],"their":[118],"corresponding":[119],"ontologies":[120],"3":[123],"points":[124],"state-of-the-art":[126,146],"retrained":[130],"new":[133,145],"domain.":[134],"Our":[135],"can":[137],"also":[138],"be":[139],"domain,":[143],"achieving":[144],"multiple":[148],"datasets.":[149]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":2}],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}