{"id":"https://openalex.org/W4412887979","doi":"https://doi.org/10.18653/v1/2025.findings-acl.759","title":"RecordTwin: Towards Creating Safe Synthetic Clinical Corpora","display_name":"RecordTwin: Towards Creating Safe Synthetic Clinical Corpora","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412887979","doi":"https://doi.org/10.18653/v1/2025.findings-acl.759"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.findings-acl.759","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.759","pdf_url":"https://aclanthology.org/2025.findings-acl.759.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2025","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.findings-acl.759.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5112673540","display_name":"Seiji Shimizu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Seiji Shimizu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5116337284","display_name":"Ibrahim Baroud","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ibrahim Baroud","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072117104","display_name":"Lisa Raithel","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lisa Raithel","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005540314","display_name":"Shuntaro Yada","orcid":"https://orcid.org/0000-0002-6209-1054"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shuntaro Yada","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046718849","display_name":"Shoko Wakamiya","orcid":"https://orcid.org/0000-0002-9371-1340"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shoko Wakamiya","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5041089475","display_name":"Eiji Aramaki","orcid":"https://orcid.org/0000-0003-0201-3609"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Eiji Aramaki","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"14714","last_page":"14726"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9890000224113464,"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":0.9890000224113464,"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":0.9796000123023987,"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/T10028","display_name":"Topic Modeling","score":0.9667999744415283,"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":0.6492283344268799},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.44753551483154297},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3458460569381714}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6492283344268799},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.44753551483154297},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3458460569381714}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.18653/v1/2025.findings-acl.759","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.759","pdf_url":"https://aclanthology.org/2025.findings-acl.759.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2025","raw_type":"proceedings-article"},{"id":"pmh:oai:irdb.nii.ac.jp:01146:0006961090","is_oa":true,"landing_page_url":"https://naist.repo.nii.ac.jp/records/2001207","pdf_url":null,"source":{"id":"https://openalex.org/S7407056385","display_name":"Institutional Repositories DataBase (IRDB)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I184597095","host_organization_name":"National Institute of Informatics","host_organization_lineage":["https://openalex.org/I184597095"],"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":"Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics","raw_type":"conference paper"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.findings-acl.759","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.759","pdf_url":"https://aclanthology.org/2025.findings-acl.759.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.6000000238418579,"display_name":"Zero hunger","id":"https://metadata.un.org/sdg/2"}],"awards":[{"id":"https://openalex.org/G240039914","display_name":null,"funder_award_id":"JPMJCR22N1","funder_id":"https://openalex.org/F4320338075","funder_display_name":"Core Research for Evolutional Science and Technology"},{"id":"https://openalex.org/G5019646625","display_name":null,"funder_award_id":"JPJ012425","funder_id":"https://openalex.org/F4320338075","funder_display_name":"Core Research for Evolutional Science and Technology"},{"id":"https://openalex.org/G6689335287","display_name":null,"funder_award_id":"BIFOLD24B","funder_id":"https://openalex.org/F4320321114","funder_display_name":"Bundesministerium f\u00fcr Bildung und Forschung"}],"funders":[{"id":"https://openalex.org/F4320321114","display_name":"Bundesministerium f\u00fcr Bildung und Forschung","ror":"https://ror.org/04pz7b180"},{"id":"https://openalex.org/F4320338075","display_name":"Core Research for Evolutional Science and Technology","ror":"https://ror.org/00097mb19"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412887979.pdf","grobid_xml":"https://content.openalex.org/works/W4412887979.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W3204019825"],"abstract_inverted_index":{"The":[0],"scarcity":[1],"of":[2,109,129,184],"publicly":[3,157],"available":[4,158],"clinical":[5,14,38,64,159],"corpora":[6],"hinders":[7],"developing":[8],"and":[9,71,117,125,175],"applying":[10],"NLP":[11],"tools":[12],"in":[13,43,82,132,140],"research.While":[15],"existing":[16],"work":[17],"tackles":[18],"this":[19,46,66],"issue":[20],"by":[21],"utilizing":[22],"generative":[23],"models":[24],"to":[25,58,77,94,113,171],"create":[26],"high-quality":[27],"synthetic":[28,53,60,84,144,165,188],"corpora,":[29],"their":[30,115],"methods":[31],"require":[32],"learning":[33],"from":[34,62,74],"the":[35,79,83,96,110,133,143,164,172,182],"original":[36,111,130,173],"inhospital":[37],"documents,":[39],"turning":[40],"them":[41],"unfeasible":[42],"practice.To":[44,141],"address":[45],"problem,":[47],"we":[48,68,88,103,150],"introduce":[49],"RECORDTWIN,":[50],"a":[51,90,105,126,152,156,168,176],"novel":[52],"corpus":[54,85,145,166,189],"creation":[55,190],"method":[56],"designed":[57],"generate":[59],"documents":[61,76,112,131],"anonymized":[63,99,123],"entities.In":[65],"method,":[67,149],"first":[69],"extract":[70],"anonymize":[72],"entities":[73,124],"in-hospital":[75],"ensure":[78],"information":[80],"contained":[81],"is":[86],"restricted.Then,":[87],"use":[89,104],"large":[91],"language":[92],"model":[93],"fill":[95],"context":[97],"between":[98],"entities.To":[100],"do":[101],"so,":[102],"small,":[106],"privacy-preserving":[107,187],"subset":[108,128],"mimic":[114],"formatting":[116],"writing":[118],"style.This":[119],"approach":[120],"only":[121],"requires":[122],"small":[127],"generation":[134],"process,":[135],"making":[136],"it":[137],"more":[138],"feasible":[139],"evaluate":[142],"created":[146],"with":[147],"our":[148],"conduct":[151],"proof-of-concept":[153],"study":[154],"using":[155],"database.Our":[160],"results":[161],"demonstrate":[162],"that":[163],"has":[167],"utility":[169],"comparable":[170],"data":[174],"safety":[177],"advantage":[178],"over":[179],"baselines,":[180],"highlighting":[181],"potential":[183],"RECORDTWIN":[185],"for":[186],"1":[191],".":[192]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}