{"id":"https://openalex.org/W4385825800","doi":"https://doi.org/10.1145/3583780.3615126","title":"Ontology Enrichment from Texts: A Biomedical Dataset for Concept Discovery and Placement","display_name":"Ontology Enrichment from Texts: A Biomedical Dataset for Concept Discovery and Placement","publication_year":2023,"publication_date":"2023-10-21","ids":{"openalex":"https://openalex.org/W4385825800","doi":"https://doi.org/10.1145/3583780.3615126"},"language":"en","primary_location":{"id":"doi:10.1145/3583780.3615126","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3583780.3615126","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3583780.3615126","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":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3583780.3615126","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":false,"raw_author_name":"Hang Dong","raw_affiliation_strings":["University of Oxford, Oxford, United Kingdom"],"raw_orcid":"https://orcid.org/0000-0001-6828-6891","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"],"raw_orcid":"https://orcid.org/0000-0003-4643-6750","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"],"raw_orcid":"https://orcid.org/0000-0002-4486-1262","affiliations":[{"raw_affiliation_string":"University of Oxford, Oxford, United Kingdom","institution_ids":["https://openalex.org/I40120149"]}]},{"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"],"raw_orcid":"https://orcid.org/0000-0002-2685-7462","affiliations":[{"raw_affiliation_string":"University of Oxford, Oxford, United Kingdom","institution_ids":["https://openalex.org/I40120149"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":9,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5316","last_page":"5320"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9980999827384949,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.9944999814033508,"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/snomed-ct","display_name":"SNOMED CT","score":0.7832608222961426},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7534996271133423},{"id":"https://openalex.org/keywords/ontology","display_name":"Ontology","score":0.6743688583374023},{"id":"https://openalex.org/keywords/open-biomedical-ontologies","display_name":"Open Biomedical Ontologies","score":0.6050638556480408},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.566290020942688},{"id":"https://openalex.org/keywords/taxonomy","display_name":"Taxonomy (biology)","score":0.5570003986358643},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5043748617172241},{"id":"https://openalex.org/keywords/description-logic","display_name":"Description logic","score":0.46527692675590515},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.42814281582832336},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4001519978046417},{"id":"https://openalex.org/keywords/semantic-web","display_name":"Semantic Web","score":0.39926713705062866},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.30779021978378296},{"id":"https://openalex.org/keywords/terminology","display_name":"Terminology","score":0.26222532987594604},{"id":"https://openalex.org/keywords/upper-ontology","display_name":"Upper ontology","score":0.22719711065292358},{"id":"https://openalex.org/keywords/ontology-alignment","display_name":"Ontology alignment","score":0.18838796019554138},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.10591113567352295}],"concepts":[{"id":"https://openalex.org/C206497026","wikidata":"https://www.wikidata.org/wiki/Q1753883","display_name":"SNOMED CT","level":3,"score":0.7832608222961426},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7534996271133423},{"id":"https://openalex.org/C25810664","wikidata":"https://www.wikidata.org/wiki/Q44325","display_name":"Ontology","level":2,"score":0.6743688583374023},{"id":"https://openalex.org/C137982476","wikidata":"https://www.wikidata.org/wiki/Q7072326","display_name":"Open Biomedical Ontologies","level":5,"score":0.6050638556480408},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.566290020942688},{"id":"https://openalex.org/C58642233","wikidata":"https://www.wikidata.org/wiki/Q8269924","display_name":"Taxonomy (biology)","level":2,"score":0.5570003986358643},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5043748617172241},{"id":"https://openalex.org/C102993220","wikidata":"https://www.wikidata.org/wiki/Q387196","display_name":"Description logic","level":2,"score":0.46527692675590515},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.42814281582832336},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4001519978046417},{"id":"https://openalex.org/C2129575","wikidata":"https://www.wikidata.org/wiki/Q54837","display_name":"Semantic Web","level":2,"score":0.39926713705062866},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.30779021978378296},{"id":"https://openalex.org/C547195049","wikidata":"https://www.wikidata.org/wiki/Q1725664","display_name":"Terminology","level":2,"score":0.26222532987594604},{"id":"https://openalex.org/C78726541","wikidata":"https://www.wikidata.org/wiki/Q3882785","display_name":"Upper ontology","level":3,"score":0.22719711065292358},{"id":"https://openalex.org/C98893333","wikidata":"https://www.wikidata.org/wiki/Q4339878","display_name":"Ontology alignment","level":4,"score":0.18838796019554138},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.10591113567352295},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","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/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"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/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3583780.3615126","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3583780.3615126","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3583780.3615126","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:10.1145/3583780.3615126","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3583780.3615126","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3583780.3615126","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/W4385825800.pdf","grobid_xml":"https://content.openalex.org/works/W4385825800.grobid-xml"},"referenced_works_count":25,"referenced_works":["https://openalex.org/W2139315672","https://openalex.org/W2159583324","https://openalex.org/W2473007590","https://openalex.org/W2605369679","https://openalex.org/W2742280187","https://openalex.org/W2745056157","https://openalex.org/W2774343269","https://openalex.org/W3012615229","https://openalex.org/W3091073555","https://openalex.org/W3093526682","https://openalex.org/W3104748221","https://openalex.org/W3105801792","https://openalex.org/W3164540570","https://openalex.org/W3168349005","https://openalex.org/W3173065403","https://openalex.org/W3176459892","https://openalex.org/W4224308858","https://openalex.org/W4224326644","https://openalex.org/W4306316978","https://openalex.org/W4318677432","https://openalex.org/W4360998806","https://openalex.org/W4385572570","https://openalex.org/W4385573309","https://openalex.org/W4385825816","https://openalex.org/W6926259797"],"related_works":["https://openalex.org/W181545316","https://openalex.org/W2787565797","https://openalex.org/W2507623806","https://openalex.org/W2127299687","https://openalex.org/W1597785952","https://openalex.org/W2136803152","https://openalex.org/W1506177826","https://openalex.org/W2532736362","https://openalex.org/W2726617685","https://openalex.org/W4298304116"],"abstract_inverted_index":{"Mentions":[0],"of":[1,64,78,82,119],"new":[2,36,96],"concepts":[3],"appear":[4],"regularly":[5],"in":[6,107],"texts":[7],"and":[8,14,23,40,59,68,109,115,123,141],"require":[9],"automated":[10],"approaches":[11],"to":[12],"harvest":[13],"place":[15],"them":[16],"into":[17],"Knowledge":[18],"Bases":[19],"(KB),":[20],"e.g.,":[21],"ontologies":[22],"taxonomies.":[24],"Existing":[25],"datasets":[26],"suffer":[27],"from":[28],"three":[29],"issues,":[30,92],"(i)":[31],"mostly":[32,70],"assuming":[33],"that":[34],"a":[35,65,76,95],"concept":[37,50,66,73,142],"is":[38],"pre-discovered":[39],"cannot":[41],"support":[42],"out-of-KB":[43,138],"mention":[44,139],"discovery;":[45],"(ii)":[46],"only":[47],"using":[48],"the":[49,53,57,62,112,116,132,135],"label":[51],"as":[52],"input":[54],"along":[55],"with":[56,86,103,134],"KB":[58],"thus":[60],"lacking":[61],"contexts":[63],"label;":[67],"(iii)":[69],"focusing":[71],"on":[72,131],"placement":[74],"w.r.t":[75],"taxonomy":[77],"atomic":[79],"concepts,":[80,84],"instead":[81],"complex":[83],"i.e.,":[85],"logical":[87],"operators.":[88],"To":[89],"address":[90],"these":[91],"we":[93],"propose":[94],"benchmark,":[97],"adapting":[98,144],"MedMentions":[99],"dataset":[100,136],"(PubMed":[101],"abstracts)":[102],"SNOMED":[104],"CT":[105],"versions":[106],"2014":[108],"2017":[110],"under":[111],"Diseases":[113],"sub-category":[114],"broader":[117],"categories":[118],"Clinical":[120],"finding,":[121],"Procedure,":[122],"Pharmaceutical":[124],"/":[125],"biologic":[126],"product.":[127],"We":[128],"provide":[129],"usage":[130],"evaluation":[133],"for":[137],"discovery":[140],"placement,":[143],"recent":[145],"Large":[146],"Language":[147],"Model":[148],"based":[149],"methods.":[150]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":3},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}