{"id":"https://openalex.org/W4393523074","doi":"https://doi.org/10.5281/zenodo.8228371","title":"Datasets for Out-of-KB Mention Discovery with Entity Linking","display_name":"Datasets for Out-of-KB Mention Discovery with Entity Linking","publication_year":2023,"publication_date":"2023-08-09","ids":{"openalex":"https://openalex.org/W4393523074","doi":"https://doi.org/10.5281/zenodo.8228371"},"language":"en","primary_location":{"id":"pmh:oai:zenodo.org:8228371","is_oa":true,"landing_page_url":"https://zenodo.org/record/8228371","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"dataset"},"type":"dataset","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://zenodo.org/record/8228371","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"]},{"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":"Chen, Jiaoyan","raw_affiliation_strings":["University of Manchester & University of Oxford"],"raw_orcid":"https://orcid.org/0000-0003-4643-6750","affiliations":[{"raw_affiliation_string":"University of Manchester & University of Oxford","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":"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":"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"],"raw_orcid":"https://orcid.org/0009-0008-4930-428X","affiliations":[{"raw_affiliation_string":"Nankai University","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":"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":2,"institutions_distinct_count":3,"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/T10028","display_name":"Topic Modeling","score":0.9980000257492065,"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":0.9980000257492065,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9979000091552734,"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/T13702","display_name":"Machine Learning in Healthcare","score":0.9412999749183655,"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":0.49788975715637207},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.39622125029563904},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.3762472867965698},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.371089905500412},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3222714066505432},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.2284710705280304}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.49788975715637207},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.39622125029563904},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3762472867965698},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.371089905500412},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3222714066505432},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.2284710705280304}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:zenodo.org:8228371","is_oa":true,"landing_page_url":"https://zenodo.org/record/8228371","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"dataset"},{"id":"doi:10.5281/zenodo.8228371","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.8228371","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":"pmh:oai:zenodo.org:8228371","is_oa":true,"landing_page_url":"https://zenodo.org/record/8228371","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"dataset"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["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","https://openalex.org/W2530322880"],"abstract_inverted_index":{"The":[0],"repository":[1],"contains":[2,34],"datasets":[3],"for":[4,46,50,69,78],"out-of-KB":[5],"mention":[6],"discovery":[7],"from":[8,108,113,121,128,133,139],"texts,":[9],"documented":[10],"in":[11],"the":[12,15,58,70,100],"work,":[13],"<em>Reveal":[14],"Unknown:":[16],"Out-of-Knowledge-Base":[17],"Mention":[18],"Discovery":[19],"with":[20,55],"Entity":[21],"Linking</em>,":[22],"on":[23],"arXiv:":[24],"https://arxiv.org/abs/2302.07189":[25],"(CIKM":[26],"2023).":[27],"Each":[28],"data":[29,48,63,101],"setting":[30,81,87],"(as":[31],"a":[32],"sub-folder)":[33],"train,":[35],"valid,":[36],"and":[37,40],"test":[38],"files":[39,45,74],"also":[41],"100":[42],"random":[43],"sample":[44],"each":[47],"split":[49],"debugging.":[51],"Data":[52,92],"folder":[53],"names":[54],"\u201csyn_full\u201d":[56],"at":[57,96],"end":[59],"are":[60,84,94],"synonym":[61,65],"augmented":[62],"(each":[64],"as":[66,90],"an":[67],"entity)":[68],"setting.":[71],"Ontology":[72],".jsonl":[73],"have":[75],"two":[76],"versions":[77],"each,":[79],"\"syn_attr\"":[80],"treats":[82,88],"synonyms":[83,89],"attributes,":[85],"\"syn_full\"":[86],"entities.":[91],"scripts":[93],"available":[95],"https://github.com/KRR-Oxford/BLINKout#data-scripts":[97],"Acknowledgement":[98],"of":[99],"sources":[102],"below:":[103],"ShARe/CLEF":[104],"2013":[105],"dataset":[106,111,131],"is":[107,112,120,127,132,138],"https://physionet.org/content/shareclefehealth2013/1.0/":[109],"MedMention":[110],"https://github.com/chanzuckerberg/MedMentions":[114],"UMLS":[115],"(versions":[116],"2012AB,":[117],"2014AB,":[118],"2017AA)":[119],"https://www.nlm.nih.gov/research/umls/index.html":[122],"SNOMED":[123],"CT":[124],"(corresponding":[125],"versions)":[126],"https://www.nlm.nih.gov/healthit/snomedct/index.html":[129],"NILK":[130],"https://zenodo.org/record/6607514":[134],"WikiData":[135],"2017":[136],"dump":[137],"https://archive.org/download/enwiki-20170220/enwiki-20170220-pages-articles.xml.bz2":[140]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2025-10-10T00:00:00"}
