{"id":"https://openalex.org/W2896016608","doi":"https://doi.org/10.1109/ichi.2019.8904728","title":"BioSentVec: creating sentence embeddings for biomedical texts","display_name":"BioSentVec: creating sentence embeddings for biomedical texts","publication_year":2019,"publication_date":"2019-06-01","ids":{"openalex":"https://openalex.org/W2896016608","doi":"https://doi.org/10.1109/ichi.2019.8904728","mag":"2896016608"},"language":"en","primary_location":{"id":"doi:10.1109/ichi.2019.8904728","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ichi.2019.8904728","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE International Conference on Healthcare Informatics (ICHI)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1810.09302","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Qingyu Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I4210109390","display_name":"National Center for Biotechnology Information","ror":"https://ror.org/02meqm098","country_code":"US","type":"facility","lineage":["https://openalex.org/I1299022934","https://openalex.org/I1299303238","https://openalex.org/I2800548410","https://openalex.org/I4210109390"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Qingyu Chen","raw_affiliation_strings":["National Institutes of Health (NIH),National Center for Biotechnology Information (NCBI), National Library of Medicine (NLM),Bethesda,MD,USA,20894"],"affiliations":[{"raw_affiliation_string":"National Institutes of Health (NIH),National Center for Biotechnology Information (NCBI), National Library of Medicine (NLM),Bethesda,MD,USA,20894","institution_ids":["https://openalex.org/I4210109390"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yifan Peng","orcid":null},"institutions":[{"id":"https://openalex.org/I4210109390","display_name":"National Center for Biotechnology Information","ror":"https://ror.org/02meqm098","country_code":"US","type":"facility","lineage":["https://openalex.org/I1299022934","https://openalex.org/I1299303238","https://openalex.org/I2800548410","https://openalex.org/I4210109390"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yifan Peng","raw_affiliation_strings":["National Institutes of Health (NIH),National Center for Biotechnology Information (NCBI), National Library of Medicine (NLM),Bethesda,MD,USA,20894"],"affiliations":[{"raw_affiliation_string":"National Institutes of Health (NIH),National Center for Biotechnology Information (NCBI), National Library of Medicine (NLM),Bethesda,MD,USA,20894","institution_ids":["https://openalex.org/I4210109390"]}]},{"author_position":"last","author":{"id":null,"display_name":"Zhiyong Lu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210109390","display_name":"National Center for Biotechnology Information","ror":"https://ror.org/02meqm098","country_code":"US","type":"facility","lineage":["https://openalex.org/I1299022934","https://openalex.org/I1299303238","https://openalex.org/I2800548410","https://openalex.org/I4210109390"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhiyong Lu","raw_affiliation_strings":["National Institutes of Health (NIH),National Center for Biotechnology Information (NCBI), National Library of Medicine (NLM),Bethesda,MD,USA,20894"],"affiliations":[{"raw_affiliation_string":"National Institutes of Health (NIH),National Center for Biotechnology Information (NCBI), National Library of Medicine (NLM),Bethesda,MD,USA,20894","institution_ids":["https://openalex.org/I4210109390"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210109390"],"apc_list":null,"apc_paid":null,"fwci":8.969,"has_fulltext":false,"cited_by_count":111,"citation_normalized_percentile":{"value":0.98170543,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9983000159263611,"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":0.9962000250816345,"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/sentence","display_name":"Sentence","score":0.8371000289916992},{"id":"https://openalex.org/keywords/complement","display_name":"Complement (music)","score":0.728600025177002},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5479999780654907},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5148000121116638},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.4869999885559082},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.46790000796318054},{"id":"https://openalex.org/keywords/biomedical-text-mining","display_name":"Biomedical text mining","score":0.4440999925136566}],"concepts":[{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.8371000289916992},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7468000054359436},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7426000237464905},{"id":"https://openalex.org/C112313634","wikidata":"https://www.wikidata.org/wiki/Q7886648","display_name":"Complement (music)","level":5,"score":0.728600025177002},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.661300003528595},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5479999780654907},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5148000121116638},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.4869999885559082},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.46790000796318054},{"id":"https://openalex.org/C165141518","wikidata":"https://www.wikidata.org/wiki/Q4915126","display_name":"Biomedical text mining","level":3,"score":0.4440999925136566},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.4368000030517578},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.36959999799728394},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.3231000006198883},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.31700000166893005},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.30329999327659607},{"id":"https://openalex.org/C60048249","wikidata":"https://www.wikidata.org/wiki/Q37437","display_name":"Syntax","level":2,"score":0.26980000734329224},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.26660001277923584},{"id":"https://openalex.org/C67277372","wikidata":"https://www.wikidata.org/wiki/Q7449085","display_name":"Semantic role labeling","level":3,"score":0.2572999894618988},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.25220000743865967}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/ichi.2019.8904728","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ichi.2019.8904728","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE International Conference on Healthcare Informatics (ICHI)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1810.09302","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1810.09302","pdf_url":"https://arxiv.org/pdf/1810.09302","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":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1810.09302","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1810.09302","pdf_url":"https://arxiv.org/pdf/1810.09302","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":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W2114315281","https://openalex.org/W2117692326","https://openalex.org/W2163922914","https://openalex.org/W2174775663","https://openalex.org/W2396881363","https://openalex.org/W2605035112","https://openalex.org/W2735784619","https://openalex.org/W2781827132","https://openalex.org/W2889272240","https://openalex.org/W2940542551","https://openalex.org/W2951934944","https://openalex.org/W2963923670","https://openalex.org/W2964279163","https://openalex.org/W2964348125","https://openalex.org/W6749879876"],"related_works":[],"abstract_inverted_index":{"Sentence":[0],"embeddings":[1,49,73,92,135],"have":[2],"become":[3],"an":[4],"essential":[5],"part":[6],"of":[7,47],"today's":[8],"natural":[9],"language":[10],"processing":[11],"(NLP)":[12],"systems,":[13],"especially":[14],"together":[15],"advanced":[16],"deep":[17],"learning":[18],"methods.":[19],"Although":[20],"pre-trained":[21],"sentence":[22,48,76,96],"encoders":[23],"are":[24,136],"available":[25,138],"in":[26,60,65,74,80,108,120,130],"the":[27,43,66,90,100,116,127],"general":[28],"domain,":[29],"none":[30],"exists":[31],"for":[32],"biomedical":[33,82,121,131],"texts":[34],"to":[35,99,114,125],"date.":[36],"In":[37],"this":[38],"work,":[39],"we":[40],"introduce":[41],"BioSentVec:":[42],"first":[44],"open":[45],"set":[46],"trained":[50],"with":[51],"over":[52],"30":[53],"million":[54],"documents":[55],"from":[56],"both":[57,109],"scholarly":[58],"articles":[59],"PubMed":[61],"and":[62,104,118,124],"clinical":[63],"notes":[64],"MIMICIII":[67],"Clinical":[68],"Database.":[69],"We":[70,111],"evaluate":[71],"BioSentVec":[72,91,113],"two":[75],"pair":[77],"similarity":[78],"tasks":[79],"different":[81],"text":[83,122],"genres.":[84],"Our":[85],"benchmarking":[86],"results":[87],"demonstrate":[88],"that":[89],"can":[93],"better":[94],"capture":[95],"semantics":[97],"compared":[98],"other":[101],"competitive":[102],"alternatives":[103],"achieve":[105],"state-of-the-art":[106],"performance":[107],"tasks.":[110],"expect":[112],"facilitate":[115],"research":[117],"development":[119],"mining":[123],"complement":[126],"existing":[128],"resources":[129],"word":[132],"embeddings.":[133],"The":[134],"publicly":[137],"at":[139],"https://github.com/ncbi-nlp/BioSentVec.":[140]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":21},{"year":2024,"cited_by_count":13},{"year":2023,"cited_by_count":14},{"year":2022,"cited_by_count":24},{"year":2021,"cited_by_count":20},{"year":2020,"cited_by_count":13},{"year":2019,"cited_by_count":5}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2018-10-26T00:00:00"}