{"id":"https://openalex.org/W4385825816","doi":"https://doi.org/10.1145/3583780.3615036","title":"Reveal the Unknown: Out-of-Knowledge-Base Mention Discovery with Entity Linking","display_name":"Reveal the Unknown: Out-of-Knowledge-Base Mention Discovery with Entity Linking","publication_year":2023,"publication_date":"2023-10-21","ids":{"openalex":"https://openalex.org/W4385825816","doi":"https://doi.org/10.1145/3583780.3615036"},"language":"en","primary_location":{"id":"doi:10.1145/3583780.3615036","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3583780.3615036","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3583780.3615036","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 32nd ACM International Conference on Information and Knowledge Management","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3583780.3615036","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5035163413","display_name":"Hang Dong","orcid":"https://orcid.org/0000-0001-6828-6891"},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Hang Dong","raw_affiliation_strings":["University of Oxford, Oxford, United Kingdom"],"affiliations":[{"raw_affiliation_string":"University of Oxford, Oxford, United Kingdom","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085691361","display_name":"Jiaoyan Chen","orcid":"https://orcid.org/0000-0003-4643-6750"},"institutions":[{"id":"https://openalex.org/I28407311","display_name":"University of Manchester","ror":"https://ror.org/027m9bs27","country_code":"GB","type":"education","lineage":["https://openalex.org/I28407311"]},{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jiaoyan Chen","raw_affiliation_strings":["The University of Manchester & University of Oxford, Manchester, United Kingdom"],"affiliations":[{"raw_affiliation_string":"The University of Manchester & University of Oxford, Manchester, United Kingdom","institution_ids":["https://openalex.org/I28407311","https://openalex.org/I40120149"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100461968","display_name":"Yuan He","orcid":"https://orcid.org/0000-0002-4486-1262"},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Yuan He","raw_affiliation_strings":["University of Oxford, Oxford, United Kingdom"],"affiliations":[{"raw_affiliation_string":"University of Oxford, Oxford, United Kingdom","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007783625","display_name":"Yi-nan Liu","orcid":"https://orcid.org/0009-0008-4930-428X"},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yinan Liu","raw_affiliation_strings":["Nankai University, Tianjing, China"],"affiliations":[{"raw_affiliation_string":"Nankai University, Tianjing, China","institution_ids":["https://openalex.org/I205237279"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5060350556","display_name":"Ian Horrocks","orcid":"https://orcid.org/0000-0002-2685-7462"},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Ian Horrocks","raw_affiliation_strings":["University of Oxford, Oxford, United Kingdom"],"affiliations":[{"raw_affiliation_string":"University of Oxford, Oxford, United Kingdom","institution_ids":["https://openalex.org/I40120149"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5035163413"],"corresponding_institution_ids":["https://openalex.org/I40120149"],"apc_list":null,"apc_paid":null,"fwci":1.5555,"has_fulltext":true,"cited_by_count":9,"citation_normalized_percentile":{"value":0.86333988,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"452","last_page":"462"},"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":0.9994999766349792,"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":0.9987000226974487,"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":0.8307450413703918},{"id":"https://openalex.org/keywords/unified-medical-language-system","display_name":"Unified Medical Language System","score":0.6657279133796692},{"id":"https://openalex.org/keywords/entity-linking","display_name":"Entity linking","score":0.6295350790023804},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6101665496826172},{"id":"https://openalex.org/keywords/snomed-ct","display_name":"SNOMED CT","score":0.6049020290374756},{"id":"https://openalex.org/keywords/knowledge-base","display_name":"Knowledge base","score":0.5982111096382141},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.5735582709312439},{"id":"https://openalex.org/keywords/systematized-nomenclature-of-medicine","display_name":"Systematized Nomenclature of Medicine","score":0.5628775358200073},{"id":"https://openalex.org/keywords/synonym","display_name":"Synonym (taxonomy)","score":0.5291735529899597},{"id":"https://openalex.org/keywords/pruning","display_name":"Pruning","score":0.5006024837493896},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.46608680486679077},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4509621560573578},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.431723415851593},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41434425115585327},{"id":"https://openalex.org/keywords/terminology","display_name":"Terminology","score":0.35854604840278625},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.08753147721290588},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.0850832462310791}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8307450413703918},{"id":"https://openalex.org/C69505689","wikidata":"https://www.wikidata.org/wiki/Q455338","display_name":"Unified Medical Language System","level":2,"score":0.6657279133796692},{"id":"https://openalex.org/C96711827","wikidata":"https://www.wikidata.org/wiki/Q17012245","display_name":"Entity linking","level":3,"score":0.6295350790023804},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6101665496826172},{"id":"https://openalex.org/C206497026","wikidata":"https://www.wikidata.org/wiki/Q1753883","display_name":"SNOMED CT","level":3,"score":0.6049020290374756},{"id":"https://openalex.org/C4554734","wikidata":"https://www.wikidata.org/wiki/Q593744","display_name":"Knowledge base","level":2,"score":0.5982111096382141},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.5735582709312439},{"id":"https://openalex.org/C44681071","wikidata":"https://www.wikidata.org/wiki/Q4048820","display_name":"Systematized Nomenclature of Medicine","level":4,"score":0.5628775358200073},{"id":"https://openalex.org/C173483453","wikidata":"https://www.wikidata.org/wiki/Q1040689","display_name":"Synonym (taxonomy)","level":3,"score":0.5291735529899597},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.5006024837493896},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.46608680486679077},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4509621560573578},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.431723415851593},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41434425115585327},{"id":"https://openalex.org/C547195049","wikidata":"https://www.wikidata.org/wiki/Q1725664","display_name":"Terminology","level":2,"score":0.35854604840278625},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.08753147721290588},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0850832462310791},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3583780.3615036","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3583780.3615036","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3583780.3615036","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 32nd ACM International Conference on Information and Knowledge Management","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3583780.3615036","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3583780.3615036","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3583780.3615036","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 32nd ACM International Conference on Information and Knowledge Management","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3253514882","display_name":"ConCur: Knowledge Base Construction and Curation","funder_award_id":"EP/V050869/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G5652537686","display_name":"UK FIRES: Locating Resource Efficiency at the heart of Future Industrial Strategy in the UK","funder_award_id":"EP/S019111/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G667038190","display_name":"OASIS: Ontology Reasoning over Frequently-changing and Streaming Data","funder_award_id":"EP/S032347/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G7513764588","display_name":null,"funder_award_id":"EP/V050869/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G8795553652","display_name":null,"funder_award_id":"EP/V050869/1, EP/S032347/1, EP/S019111/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320320022","display_name":"Sight Research UK","ror":"https://ror.org/03z2py885"},{"id":"https://openalex.org/F4320332195","display_name":"Samsung","ror":"https://ror.org/04w3jy968"},{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4385825816.pdf","grobid_xml":"https://content.openalex.org/works/W4385825816.grobid-xml"},"referenced_works_count":36,"referenced_works":["https://openalex.org/W1172683740","https://openalex.org/W1964189668","https://openalex.org/W2080133951","https://openalex.org/W2091950909","https://openalex.org/W2133109597","https://openalex.org/W2159583324","https://openalex.org/W2184570030","https://openalex.org/W2337312443","https://openalex.org/W2402639588","https://openalex.org/W2605369679","https://openalex.org/W2774343269","https://openalex.org/W2892181857","https://openalex.org/W2892737606","https://openalex.org/W2967690619","https://openalex.org/W3004185181","https://openalex.org/W3032553678","https://openalex.org/W3046375318","https://openalex.org/W3102559088","https://openalex.org/W3104748221","https://openalex.org/W3105801792","https://openalex.org/W3112302290","https://openalex.org/W3156636935","https://openalex.org/W3164540570","https://openalex.org/W3173423412","https://openalex.org/W3202062685","https://openalex.org/W3204085121","https://openalex.org/W3212714602","https://openalex.org/W3217300598","https://openalex.org/W4224311069","https://openalex.org/W4239019441","https://openalex.org/W4280604898","https://openalex.org/W4287887705","https://openalex.org/W4306316978","https://openalex.org/W4385573309","https://openalex.org/W6766960179","https://openalex.org/W6926259797"],"related_works":["https://openalex.org/W2181479088","https://openalex.org/W2010248145","https://openalex.org/W2037829818","https://openalex.org/W1485513899","https://openalex.org/W1682743535","https://openalex.org/W2044298438","https://openalex.org/W4282583959","https://openalex.org/W3026755508","https://openalex.org/W4206342372","https://openalex.org/W31701444"],"abstract_inverted_index":{"Discovering":[0],"entity":[1,88],"mentions":[2,62,139],"that":[3,63],"are":[4,30,46],"out":[5],"of":[6,117,131],"a":[7,14,52,74],"Knowledge":[8],"Base":[9],"(KB)":[10],"from":[11,108],"texts":[12],"plays":[13],"critical":[15],"role":[16],"in":[17,125],"KB":[18,68,98],"maintenance,":[19],"but":[20],"has":[21],"not":[22,65],"yet":[23],"been":[24],"fully":[25],"explored.":[26],"The":[27],"current":[28],"methods":[29,135],"mostly":[31],"limited":[32],"to":[33,73,103,136],"the":[34,42,129,141,148],"simple":[35],"threshold-based":[36],"approach":[37],"and":[38,41,90,100,122,147],"feature-based":[39],"classification,":[40,91],"datasets":[43,107,116],"for":[44,140],"evaluation":[45],"relatively":[47],"rare.":[48],"We":[49,95],"propose":[50,83],"BLINKout,":[51],"new":[53,84],"BERT-based":[54],"Entity":[55],"Linking":[56],"(EL)":[57],"method":[58],"which":[59],"can":[60],"identify":[61,137],"do":[64],"have":[66],"corresponding":[67],"entities":[69],"by":[70],"matching":[71],"them":[72],"special":[75],"NIL":[76,87],"entity.":[77],"To":[78],"better":[79],"utilize":[80],"BERT,":[81],"we":[82],"techniques":[85],"including":[86],"representation":[89],"with":[92],"synonym":[93],"enhancement.":[94],"also":[96],"apply":[97],"Pruning":[99],"Versioning":[101],"strategies":[102],"automatically":[104],"construct":[105],"out-of-KB":[106,138],"common":[109],"in-KB":[110],"EL":[111],"datasets.":[112],"Results":[113],"on":[114],"five":[115],"clinical":[118],"notes,":[119],"biomedical":[120],"publications,":[121],"Wikipedia":[123],"articles":[124],"various":[126],"domains":[127],"show":[128],"advantages":[130],"BLINKout":[132],"over":[133],"existing":[134],"medical":[142],"ontologies,":[143],"UMLS,":[144],"SNOMED":[145],"CT,":[146],"general":[149],"KB,":[150],"WikiData.":[151]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":1}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}