{"id":"https://openalex.org/W4394049666","doi":"https://doi.org/10.5281/zenodo.10432003","title":"Ontology Enrichment from Texts (OET): A Biomedical Dataset for Concept Discovery and Placement","display_name":"Ontology Enrichment from Texts (OET): A Biomedical Dataset for Concept Discovery and Placement","publication_year":2023,"publication_date":"2023-12-26","ids":{"openalex":"https://openalex.org/W4394049666","doi":"https://doi.org/10.5281/zenodo.10432003"},"language":"en","primary_location":{"id":"doi:10.5281/zenodo.10432003","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.10432003","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Dataset"},"type":"dataset","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.5281/zenodo.10432003","any_repository_has_fulltext":true},"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":"Dong, Hang","raw_affiliation_strings":["University of Oxford"],"raw_orcid":"https://orcid.org/0000-0001-6828-6891","affiliations":[{"raw_affiliation_string":"University of Oxford","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"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Chen, Jiaoyan","raw_affiliation_strings":["University of Manchester"],"raw_orcid":"https://orcid.org/0000-0003-4643-6750","affiliations":[{"raw_affiliation_string":"University of Manchester","institution_ids":["https://openalex.org/I28407311"]}]},{"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":"He, Yuan","raw_affiliation_strings":["University of Oxford"],"raw_orcid":"https://orcid.org/0000-0002-4486-1262","affiliations":[{"raw_affiliation_string":"University of Oxford","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":"Horrocks, Ian","raw_affiliation_strings":["University of Oxford"],"raw_orcid":"https://orcid.org/0000-0002-2685-7462","affiliations":[{"raw_affiliation_string":"University of Oxford","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":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9902999997138977,"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":0.9902999997138977,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.9832000136375427,"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":0.9132999777793884,"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/ontology","display_name":"Ontology","score":0.7254218459129333},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5374515652656555},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.45432981848716736},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.44334670901298523},{"id":"https://openalex.org/keywords/epistemology","display_name":"Epistemology","score":0.14064845442771912},{"id":"https://openalex.org/keywords/philosophy","display_name":"Philosophy","score":0.10057809948921204}],"concepts":[{"id":"https://openalex.org/C25810664","wikidata":"https://www.wikidata.org/wiki/Q44325","display_name":"Ontology","level":2,"score":0.7254218459129333},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5374515652656555},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.45432981848716736},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.44334670901298523},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.14064845442771912},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.10057809948921204}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.5281/zenodo.10432003","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.10432003","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Dataset"}],"best_oa_location":{"id":"doi:10.5281/zenodo.10432003","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.10432003","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Dataset"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W2382290278","https://openalex.org/W2478288626","https://openalex.org/W4391913857","https://openalex.org/W2350741829"],"abstract_inverted_index":{"A":[0,58],"biomedical":[1],"dataset":[2,16,48],"supporting":[3],"ontology":[4,226,278],"enrichment":[5],"from":[6,56],"texts,":[7],"by":[8,202],"concept":[9,120,138,282],"discovery":[10,80,118],"and":[11,26,33,41,64,119,148,150,166,175,183,187,221,234,280],"placement,":[12],"adapting":[13],"the":[14,29,34,52,82,92,95,123,135,145,153,159,184,190,199,225],"MedMentions":[15,260],"(PubMed":[17],"abstracts)":[18],"with":[19,100,193,211],"SNOMED":[20,238,258],"CT":[21,228,239],"of":[22,37,84,113,231,263],"versions":[23],"in":[24,51,91,131,152,224],"2014":[25],"2017":[27],"under":[28],"Diseases":[30],"(disorder)":[31],"sub-category":[32],"broader":[35],"categories":[36],"Clinical":[38],"finding,":[39],"Procedure,":[40],"Pharmaceutical":[42],"/":[43],"biologic":[44],"(CPP)":[45],"product.":[46],"The":[47,71],"is":[49,74,87],"documented":[50,90],"work,":[53,93],"Ontology":[54],"Enrichment":[55],"Texts:":[57],"Biomedical":[59],"Dataset":[60],"for":[61,116,168,254,277],"Concept":[62],"Discovery":[63,99],"Placement,":[65],"on":[66,103,274],"arXiv:":[67,104],"https://arxiv.org/abs/2306.14704":[68],"(CIKM":[69,106],"2023).":[70,107],"companion":[72],"code":[73],"available":[75],"at":[76],"https://github.com/KRR-Oxford/OET.":[77],"Out-of-KB":[78],"mention":[79],"(including":[81,214],"settings":[83],"mention-level":[85,114,177,200],"data)":[86],"further":[88],"partly":[89],"Reveal":[94],"Unknown:":[96],"Out-of-Knowledge-Base":[97],"Mention":[98],"Entity":[101],"Linking,":[102],"https://arxiv.org/abs/2302.07189":[105],"ver4:":[108],"we":[109,157,173,197],"made":[110],"a":[111,169],"version":[112],"data":[115,178,201,232],"out-of-KB":[117,126,129,142,205],"placement":[121],"separately:":[122],"former":[124],"(for":[125,137],"discovery)":[127],"has":[128,140],"mentions":[130,143,206],"training":[132,154],"data,":[133],"while":[134],"latter":[136],"placement)":[139],"only":[141,203],"during":[144],"evaluation":[146],"(validation":[147],"test)":[149],"not":[151],"data.":[155],"Also,":[156],"split":[158],"original":[160],"\"test-NIL.jsonl\"":[161,167],"(now":[162],"\"test-NIL-all.jsonl\")":[163],"into":[164],"\"valid-NIL.jsonl\"":[165],"better":[170],"evaluation.":[171],"ver3:":[172],"revised":[174,198],"updated":[176,189],"(syn_full,":[179],"synonym":[180],"augmentation":[181],"setting)":[182],"folder":[185],"structure,":[186],"also":[188],"edge":[191],"catalogues":[192],"complex":[194,281],"edges.":[195],"ver2:":[196],"keeping":[204],"(or":[207],"\"NIL\"":[208],"mentions)":[209],"associated":[210],"one-hop":[212],"edges":[213,223],"leaf":[215],"nodes,":[216],"as":[217],"<leaf":[218],"node,":[219],"NULL>)":[220],"two-hop":[222],"(SNOMED":[227],"20140901).":[229],"Acknowledgement":[230],"sources":[233],"tools":[235],"below:":[236],"*":[237,266],"https://www.nlm.nih.gov/healthit/snomedct/archive.html":[240],"(and":[241,250],"use":[242,252],"snomed-owl-toolkit":[243,269],"to":[244,257],"form":[245],".owl":[246],"files)*":[247],"UMLS":[248,256],"https://www.nlm.nih.gov/research/umls/licensedcontent/umlsarchives04.html":[249],"mainly":[251],"MRCONSO":[253],"mapping":[255],"CT)*":[259],"https://github.com/chanzuckerberg/MedMentions":[261],"(source":[262],"entity":[264],"linking)":[265],"Prot\u00e9g\u00e9":[267],"http://protegeproject.github.io/protege/*":[268],"https://github.com/IHTSDO/snomed-owl-toolkit*":[270],"DeepOnto":[271],"https://github.com/KRR-Oxford/DeepOnto":[272],"(based":[273],"OWLAPI":[275],"https://owlapi.sourceforge.net/)":[276],"processing":[279],"verbalisation":[283]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2025-10-10T00:00:00"}
