{"id":"https://openalex.org/W7140101662","doi":"https://doi.org/10.18653/v1/2026.eacl-long.103","title":"K-LegalDeID: A Benchmark Dataset and KLUEBERT-CRF for De-identification in Korean Court Judgments","display_name":"K-LegalDeID: A Benchmark Dataset and KLUEBERT-CRF for De-identification in Korean Court Judgments","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7140101662","doi":"https://doi.org/10.18653/v1/2026.eacl-long.103"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.eacl-long.103","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.eacl-long.103","pdf_url":"https://aclanthology.org/2026.eacl-long.103.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":"Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.eacl-long.103.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5130336664","display_name":"Wooseok Choi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wooseok Choi","raw_affiliation_strings":["Department of Computer Science and Engineering , Korea University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering , Korea University","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130326099","display_name":"Hyungbin Kim","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hyungbin Kim","raw_affiliation_strings":["Department of Computer Science and Engineering , Korea University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering , Korea University","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5130327352","display_name":"Yon Dohn Chung","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yon Dohn Chung","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.38992565,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2308","last_page":"2325"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13643","display_name":"Artificial Intelligence in Law","score":0.47029998898506165,"subfield":{"id":"https://openalex.org/subfields/3320","display_name":"Political Science and International Relations"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T13643","display_name":"Artificial Intelligence in Law","score":0.47029998898506165,"subfield":{"id":"https://openalex.org/subfields/3320","display_name":"Political Science and International Relations"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T13910","display_name":"Computational and Text Analysis Methods","score":0.12449999898672104,"subfield":{"id":"https://openalex.org/subfields/3300","display_name":"General Social Sciences"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.023099999874830246,"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/benchmark","display_name":"Benchmark (surveying)","score":0.4830000102519989},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.22779999673366547},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.227400004863739},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.22349999845027924}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5705999732017517},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4862000048160553},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4830000102519989},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.34119999408721924},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.26829999685287476},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.22910000383853912},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.22779999673366547},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.227400004863739},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.22349999845027924},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.21850000321865082}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.eacl-long.103","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.eacl-long.103","pdf_url":"https://aclanthology.org/2026.eacl-long.103.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":"Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.eacl-long.103","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.eacl-long.103","pdf_url":"https://aclanthology.org/2026.eacl-long.103.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":"Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.6415282487869263}],"awards":[{"id":"https://openalex.org/G7542792045","display_name":null,"funder_award_id":"IITP-2025-RS-2020-II201819","funder_id":"https://openalex.org/F4320335489","funder_display_name":"Institute for Information and Communications Technology Promotion"}],"funders":[{"id":"https://openalex.org/F4320320671","display_name":"National Research Foundation","ror":"https://ror.org/05s0g1g46"},{"id":"https://openalex.org/F4320322120","display_name":"National Research Foundation of Korea","ror":"https://ror.org/013aysd81"},{"id":"https://openalex.org/F4320328359","display_name":"Ministry of Science and ICT, South Korea","ror":"https://ror.org/01wpjm123"},{"id":"https://openalex.org/F4320335489","display_name":"Institute for Information and Communications Technology Promotion","ror":"https://ror.org/01g0hqq23"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7140101662.pdf","grobid_xml":"https://content.openalex.org/works/W7140101662.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"The":[0],"Korean":[1,51],"legal":[2,31,64,116],"system":[3],"mandates":[4],"public":[5],"access":[6],"to":[7,10,22],"court":[8,52],"judgments":[9],"ensure":[11],"judicial":[12],"transparency.However,":[13],"this":[14,34],"requirement":[15],"conflicts":[16],"with":[17,66,77,97],"privacy":[18],"protection":[19],"obligations":[20],"due":[21],"the":[23],"prevalence":[24],"of":[25,80,103],"Personally":[26],"Identifiable":[27],"Information":[28],"(PII)":[29],"in":[30],"documents.To":[32],"address":[33],"challenge,":[35],"we":[36],"introduce":[37],"K-LegalDeID,":[38],"a":[39,57,72,85,108],"large-scale":[40,59],"benchmark":[41,60],"dataset":[42,61],"and":[43,110],"an":[44,98],"efficient":[45,112],"KLUEBERT-CRF":[46,87],"model":[47],"for":[48,50,114],"de-identification":[49],"judgments.Our":[53],"primary":[54],"contribution":[55],"is":[56,69],"new":[58],"spanning":[62],"39":[63],"domains,":[65],"its":[67],"quality":[68],"validated":[70],"by":[71],"high":[73],"interannotator":[74],"agreement":[75],"(IAA)":[76],"Fleiss'":[78],"Kappa":[79],"0.7352.Our":[81],"results":[82],"demonstrate":[83],"that":[84],"lightweight":[86],"model,":[88],"when":[89],"trained":[90],"on":[91],"our":[92],"dataset,":[93],"achieves":[94],"state-of-theart":[95],"performance":[96],"entity-level":[99],"micro":[100],"F1":[101],"score":[102],"0.9923.Our":[104],"end-to-end":[105],"framework":[106],"offers":[107],"practical":[109],"computationally":[111],"solution":[113],"real-world":[115],"systems.":[117]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-03-24T00:00:00"}