{"id":"https://openalex.org/W4226154421","doi":"https://doi.org/10.1109/access.2022.3157854","title":"How Do Your Biomedical Named Entity Recognition Models Generalize to Novel Entities?","display_name":"How Do Your Biomedical Named Entity Recognition Models Generalize to Novel Entities?","publication_year":2022,"publication_date":"2022-01-01","ids":{"openalex":"https://openalex.org/W4226154421","doi":"https://doi.org/10.1109/access.2022.3157854","pmid":"https://pubmed.ncbi.nlm.nih.gov/35582496"},"language":"en","primary_location":{"id":"doi:10.1109/access.2022.3157854","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2022.3157854","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/9668973/09730848.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://ieeexplore.ieee.org/ielx7/6287639/9668973/09730848.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5083644268","display_name":"Hyunjae Kim","orcid":"https://orcid.org/0000-0003-2996-2564"},"institutions":[{"id":"https://openalex.org/I197347611","display_name":"Korea University","ror":"https://ror.org/047dqcg40","country_code":"KR","type":"education","lineage":["https://openalex.org/I197347611"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hyunjae Kim","raw_affiliation_strings":["Department of Computer Science and Engineering, Korea University, Seoul, South Korea"],"raw_orcid":"https://orcid.org/0000-0003-2996-2564","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Korea University, Seoul, South Korea","institution_ids":["https://openalex.org/I197347611"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5076917278","display_name":"Jaewoo Kang","orcid":"https://orcid.org/0000-0001-6798-9106"},"institutions":[{"id":"https://openalex.org/I197347611","display_name":"Korea University","ror":"https://ror.org/047dqcg40","country_code":"KR","type":"education","lineage":["https://openalex.org/I197347611"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jaewoo Kang","raw_affiliation_strings":["Department of Computer Science and Engineering, Korea University, Seoul, South Korea"],"raw_orcid":"https://orcid.org/0000-0001-6798-9106","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Korea University, Seoul, South Korea","institution_ids":["https://openalex.org/I197347611"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I197347611"],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":3.0192,"has_fulltext":true,"cited_by_count":29,"citation_normalized_percentile":{"value":0.92079767,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":"10","issue":null,"first_page":"31513","last_page":"31523"},"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":0.9987999796867371,"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":0.9983999729156494,"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/generalization","display_name":"Generalization","score":0.8302308320999146},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8143537640571594},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6614640951156616},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.6349408626556396},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5218702554702759},{"id":"https://openalex.org/keywords/synonym","display_name":"Synonym (taxonomy)","score":0.4616841673851013},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.45099592208862305},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4390346109867096},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09945836663246155}],"concepts":[{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.8302308320999146},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8143537640571594},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6614640951156616},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.6349408626556396},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5218702554702759},{"id":"https://openalex.org/C173483453","wikidata":"https://www.wikidata.org/wiki/Q1040689","display_name":"Synonym (taxonomy)","level":3,"score":0.4616841673851013},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.45099592208862305},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4390346109867096},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09945836663246155},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"id":"https://openalex.org/C157369684","wikidata":"https://www.wikidata.org/wiki/Q34740","display_name":"Genus","level":2,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/access.2022.3157854","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2022.3157854","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/9668973/09730848.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmid:35582496","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/35582496","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","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":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE access : practical innovations, open solutions","raw_type":null},{"id":"pmh:oai:arXiv.org:2101.00160","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2101.00160","pdf_url":"https://arxiv.org/pdf/2101.00160","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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"},{"id":"pmh:oai:doaj.org/article:67b8b8f7f75b4424aa36d637f8319661","is_oa":false,"landing_page_url":"https://doaj.org/article/67b8b8f7f75b4424aa36d637f8319661","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 10, Pp 31513-31523 (2022)","raw_type":"article"},{"id":"pmh:oai:pubmedcentral.nih.gov:9014470","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/9014470","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1109/access.2022.3157854","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2022.3157854","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/9668973/09730848.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1161642172","display_name":null,"funder_award_id":"IITP-2022-2020-0-01819","funder_id":"https://openalex.org/F4320335489","funder_display_name":"Institute for Information and Communications Technology Promotion"},{"id":"https://openalex.org/G4260205836","display_name":null,"funder_award_id":"2020R1A2C3010638","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"},{"id":"https://openalex.org/G4700831490","display_name":null,"funder_award_id":"2022-","funder_id":"https://openalex.org/F4320335489","funder_display_name":"Institute for Information and Communications Technology Promotion"},{"id":"https://openalex.org/G5282237008","display_name":null,"funder_award_id":"IITP-2022-2020-0-01819","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"},{"id":"https://openalex.org/G6403016105","display_name":null,"funder_award_id":"IITP-2022-2020-0-01819","funder_id":"https://openalex.org/F4320328359","funder_display_name":"Ministry of Science and ICT, South Korea"},{"id":"https://openalex.org/G8018065544","display_name":null,"funder_award_id":"2020-0-01819","funder_id":"https://openalex.org/F4320328359","funder_display_name":"Ministry of Science and ICT, South Korea"},{"id":"https://openalex.org/G8029515747","display_name":null,"funder_award_id":"HR20C0021","funder_id":"https://openalex.org/F4320322107","funder_display_name":"Korea Health Industry Development Institute"},{"id":"https://openalex.org/G835223354","display_name":null,"funder_award_id":"NRF-2020R1A2C3010638","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"}],"funders":[{"id":"https://openalex.org/F4320320671","display_name":"National Research Foundation","ror":"https://ror.org/05s0g1g46"},{"id":"https://openalex.org/F4320322107","display_name":"Korea Health Industry Development Institute","ror":"https://ror.org/00fdzyk40"},{"id":"https://openalex.org/F4320322120","display_name":"National Research Foundation of Korea","ror":"https://ror.org/013aysd81"},{"id":"https://openalex.org/F4320328359","display_name":"Ministry of Science and ICT, South Korea","ror":"https://ror.org/01wpjm123"},{"id":"https://openalex.org/F4320335489","display_name":"Institute for Information and Communications Technology Promotion","ror":"https://ror.org/01g0hqq23"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4226154421.pdf","grobid_xml":"https://content.openalex.org/works/W4226154421.grobid-xml"},"referenced_works_count":55,"referenced_works":["https://openalex.org/W1566289585","https://openalex.org/W1592053870","https://openalex.org/W1623072288","https://openalex.org/W1907024343","https://openalex.org/W2008085355","https://openalex.org/W2023736097","https://openalex.org/W2100627415","https://openalex.org/W2121244856","https://openalex.org/W2144578941","https://openalex.org/W2158743996","https://openalex.org/W2169099542","https://openalex.org/W2264517602","https://openalex.org/W2346452181","https://openalex.org/W2414378847","https://openalex.org/W2479527281","https://openalex.org/W2573492843","https://openalex.org/W2734608416","https://openalex.org/W2743028754","https://openalex.org/W2890830728","https://openalex.org/W2896457183","https://openalex.org/W2911489562","https://openalex.org/W2949176808","https://openalex.org/W2950021574","https://openalex.org/W2951286828","https://openalex.org/W2952984539","https://openalex.org/W2962843521","https://openalex.org/W2963339489","https://openalex.org/W2963442256","https://openalex.org/W2963558486","https://openalex.org/W2963644680","https://openalex.org/W2970019270","https://openalex.org/W2970813009","https://openalex.org/W2971258845","https://openalex.org/W2984256198","https://openalex.org/W2997448699","https://openalex.org/W3012358066","https://openalex.org/W3034229721","https://openalex.org/W3034831508","https://openalex.org/W3035139434","https://openalex.org/W3037063616","https://openalex.org/W3046375318","https://openalex.org/W3098886914","https://openalex.org/W3103621845","https://openalex.org/W3104502698","https://openalex.org/W3105491236","https://openalex.org/W3134983687","https://openalex.org/W3183195595","https://openalex.org/W3186056917","https://openalex.org/W6635275303","https://openalex.org/W6682082992","https://openalex.org/W6739651123","https://openalex.org/W6739901393","https://openalex.org/W6759960650","https://openalex.org/W6775715944","https://openalex.org/W6776225533"],"related_works":["https://openalex.org/W17155033","https://openalex.org/W3207760230","https://openalex.org/W1496222301","https://openalex.org/W1590307681","https://openalex.org/W2536018345","https://openalex.org/W4312814274","https://openalex.org/W4285370786","https://openalex.org/W2296488620","https://openalex.org/W2358353312","https://openalex.org/W2353836703"],"abstract_inverted_index":{"The":[0],"number":[1],"of":[2,49,52,93,102,190,200],"biomedical":[3,7,16,85,113,134],"literature":[4,114],"on":[5,71,74],"new":[6,24,84],"concepts":[8],"is":[9,31,199],"rapidly":[10],"increasing,":[11],"which":[12,124],"necessitates":[13],"a":[14,152,160,194],"reliable":[15],"named":[17],"entity":[18,27],"recognition":[19,50],"(BioNER)":[20],"model":[21],"for":[22],"identifying":[23,81],"and":[25,58,83,104,131,144,163,177],"unseen":[26,110,170],"mentions.":[28,171],"However,":[29],"it":[30],"questionable":[32],"whether":[33],"existing":[34],"models":[35,67,103,118,145,192],"can":[36],"effectively":[37],"handle":[38],"them.":[39,149],"In":[40],"this":[41],"work,":[42],"we":[43],"systematically":[44],"analyze":[45],"the":[46,126,165,187],"three":[47],"types":[48],"abilities":[51,128],"BioNER":[53],"models:":[54],"memorization,":[55],"synonym":[56],"generalization,":[57],"concept":[59],"generalization.":[60],"We":[61,97,150,172],"find":[62],"that":[63,174],"although":[64],"current":[65],"best":[66],"achieve":[68],"state-of-the-art":[69],"performance":[70],"benchmarks":[72],"based":[73],"overall":[75],"performance,":[76],"they":[77,88],"have":[78,136],"limitations":[79],"in":[80,91,108,112,167,193],"synonyms":[82],"concepts,":[86],"indicating":[87],"are":[89],"overestimated":[90],"terms":[92],"their":[94,197],"generalization":[95,168,188],"abilities.":[96],"also":[98],"investigate":[99],"failure":[100],"cases":[101],"identify":[105],"several":[106,133],"difficulties":[107],"recognizing":[109],"mentions":[111],"as":[115,159],"follows:":[116],"(1)":[117],"tend":[119],"to":[120,129,147,156,169,182],"exploit":[121],"dataset":[122],"biases,":[123],"hinders":[125],"models'":[127],"generalize,":[130],"(2)":[132],"names":[135],"novel":[137],"morphological":[138],"patterns":[139],"with":[140],"weak":[141],"name":[142],"regularity,":[143],"fail":[146],"recognize":[148],"apply":[151],"statistics-based":[153],"debiasing":[154],"method":[155],"our":[157,175],"problem":[158],"simple":[161],"remedy":[162],"show":[164],"improvement":[166],"hope":[173],"analyses":[176],"findings":[178],"would":[179],"be":[180],"able":[181],"facilitate":[183],"further":[184],"research":[185],"into":[186],"capabilities":[189],"NER":[191],"domain":[195],"where":[196],"reliability":[198],"utmost":[201],"importance.":[202]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":9},{"year":2022,"cited_by_count":5}],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2022-05-05T00:00:00"}