{"id":"https://openalex.org/W4412393339","doi":"https://doi.org/10.1145/3748325","title":"A Bilingual Legal NER Dataset and Semantics-Aware Cross-Lingual Label Transfer Method for Low-Resource Languages","display_name":"A Bilingual Legal NER Dataset and Semantics-Aware Cross-Lingual Label Transfer Method for Low-Resource Languages","publication_year":2025,"publication_date":"2025-07-14","ids":{"openalex":"https://openalex.org/W4412393339","doi":"https://doi.org/10.1145/3748325"},"language":"en","primary_location":{"id":"doi:10.1145/3748325","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3748325","pdf_url":null,"source":{"id":"https://openalex.org/S4306421405","display_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","issn_l":"2375-4699","issn":["2375-4699","2375-4702"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5099844244","display_name":"Paerhati Tulajiang","orcid":null},"institutions":[{"id":"https://openalex.org/I1334729051","display_name":"Xinjiang Normal University","ror":"https://ror.org/00ndrvk93","country_code":"CN","type":"education","lineage":["https://openalex.org/I1334729051"]},{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]},{"id":"https://openalex.org/I4210092944","display_name":"Dalian University","ror":"https://ror.org/00g2ypp58","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210092944"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Paerhati Tulajiang","raw_affiliation_strings":["College of computer science and technology, Xinjiang Normal University","School of computer science and technology, Dalian University of Technology","School of computer science and technology, Dalian University of Technology, Dalian, China and College of computer science and technology, Xinjiang Normal University, Urumqi, China"],"raw_orcid":"https://orcid.org/0009-0000-0432-692X","affiliations":[{"raw_affiliation_string":"College of computer science and technology, Xinjiang Normal University","institution_ids":["https://openalex.org/I1334729051"]},{"raw_affiliation_string":"School of computer science and technology, Dalian University of Technology","institution_ids":["https://openalex.org/I27357992"]},{"raw_affiliation_string":"School of computer science and technology, Dalian University of Technology, Dalian, China and College of computer science and technology, Xinjiang Normal University, Urumqi, China","institution_ids":["https://openalex.org/I27357992","https://openalex.org/I4210092944"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086010608","display_name":"Yuanyuan Sun","orcid":"https://orcid.org/0000-0002-6515-134X"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuanyuan Sun","raw_affiliation_strings":["School of computer science and technology, Dalian University of Technology","School of computer science and technology, Dalian University of Technology, Dalian, China"],"raw_orcid":"https://orcid.org/0000-0002-6515-134X","affiliations":[{"raw_affiliation_string":"School of computer science and technology, Dalian University of Technology","institution_ids":["https://openalex.org/I27357992"]},{"raw_affiliation_string":"School of computer science and technology, Dalian University of Technology, Dalian, China","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047808515","display_name":"Yuanyu Zhang","orcid":"https://orcid.org/0000-0002-6740-1701"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuanyu Zhang","raw_affiliation_strings":["School of computer science and technology, Dalian University of Technology","School of computer science and technology, Dalian University of Technology, Dalian, China"],"raw_orcid":"https://orcid.org/0000-0002-6740-1701","affiliations":[{"raw_affiliation_string":"School of computer science and technology, Dalian University of Technology","institution_ids":["https://openalex.org/I27357992"]},{"raw_affiliation_string":"School of computer science and technology, Dalian University of Technology, Dalian, China","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058727059","display_name":"Yingying Le","orcid":"https://orcid.org/0000-0002-7990-3899"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yingying Le","raw_affiliation_strings":["School of computer science and technology, Dalian University of Technology","School of computer science and technology, Dalian University of Technology, Dalian, China"],"raw_orcid":"https://orcid.org/0009-0007-0606-4098","affiliations":[{"raw_affiliation_string":"School of computer science and technology, Dalian University of Technology","institution_ids":["https://openalex.org/I27357992"]},{"raw_affiliation_string":"School of computer science and technology, Dalian University of Technology, Dalian, China","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009293091","display_name":"Kelaiti Xiao","orcid":null},"institutions":[{"id":"https://openalex.org/I1334729051","display_name":"Xinjiang Normal University","ror":"https://ror.org/00ndrvk93","country_code":"CN","type":"education","lineage":["https://openalex.org/I1334729051"]},{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]},{"id":"https://openalex.org/I4210092944","display_name":"Dalian University","ror":"https://ror.org/00g2ypp58","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210092944"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kelaiti Xiao","raw_affiliation_strings":["College of computer science and technology, Xinjiang Normal University","School of computer science and technology, Dalian University of Technology","School of computer science and technology, Dalian University of Technology, Dalian, China and College of computer science and technology, Xinjiang Normal University, Urumqi, China"],"raw_orcid":"https://orcid.org/0009-0007-6223-3642","affiliations":[{"raw_affiliation_string":"College of computer science and technology, Xinjiang Normal University","institution_ids":["https://openalex.org/I1334729051"]},{"raw_affiliation_string":"School of computer science and technology, Dalian University of Technology","institution_ids":["https://openalex.org/I27357992"]},{"raw_affiliation_string":"School of computer science and technology, Dalian University of Technology, Dalian, China and College of computer science and technology, Xinjiang Normal University, Urumqi, China","institution_ids":["https://openalex.org/I27357992","https://openalex.org/I4210092944"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5023931221","display_name":"Hongfei Lin","orcid":"https://orcid.org/0000-0003-0872-7688"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongfei Lin","raw_affiliation_strings":["School of computer science and technology, Dalian University of Technology","School of computer science and technology, Dalian University of Technology, Dalian, China"],"raw_orcid":"https://orcid.org/0000-0003-0872-7688","affiliations":[{"raw_affiliation_string":"School of computer science and technology, Dalian University of Technology","institution_ids":["https://openalex.org/I27357992"]},{"raw_affiliation_string":"School of computer science and technology, Dalian University of Technology, Dalian, China","institution_ids":["https://openalex.org/I27357992"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.396,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.84672913,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"24","issue":"9","first_page":"1","last_page":"21"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9983999729156494,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9983999729156494,"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":0.9950000047683716,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9909999966621399,"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":0.6901264190673828},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6170352101325989},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.5324505567550659},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4952940046787262},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.477994829416275},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.4410804510116577},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.14560404419898987}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6901264190673828},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6170352101325989},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.5324505567550659},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4952940046787262},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.477994829416275},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.4410804510116577},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.14560404419898987},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3748325","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3748325","pdf_url":null,"source":{"id":"https://openalex.org/S4306421405","display_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","issn_l":"2375-4699","issn":["2375-4699","2375-4702"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W128638292","https://openalex.org/W2896457183","https://openalex.org/W2939455697","https://openalex.org/W2952053761","https://openalex.org/W2962902328","https://openalex.org/W2971863715","https://openalex.org/W2995118574","https://openalex.org/W3021663125","https://openalex.org/W3034708897","https://openalex.org/W3042711927","https://openalex.org/W3094300367","https://openalex.org/W3094590257","https://openalex.org/W3174571625","https://openalex.org/W3184324824","https://openalex.org/W3212216364","https://openalex.org/W4221143270","https://openalex.org/W4285069614","https://openalex.org/W4288331126","https://openalex.org/W4300628203","https://openalex.org/W4385569952","https://openalex.org/W4386246396","https://openalex.org/W4390393222","https://openalex.org/W4392199349","https://openalex.org/W4393042705","https://openalex.org/W4400123644","https://openalex.org/W6769263558","https://openalex.org/W6948272289"],"related_works":["https://openalex.org/W3188962172","https://openalex.org/W2772917594","https://openalex.org/W4312825515","https://openalex.org/W4306742369","https://openalex.org/W4303457083","https://openalex.org/W2131146434","https://openalex.org/W2951359407","https://openalex.org/W4376623224","https://openalex.org/W3204019825","https://openalex.org/W2053618139"],"abstract_inverted_index":{"Named":[0],"Entity":[1],"Recognition":[2],"(NER)":[3],"in":[4,152,177],"specialized":[5],"domains":[6],"for":[7,165,174],"low-resource":[8,178],"languages":[9],"remains":[10],"a":[11,55,64,89,162,171],"significant":[12],"challenge":[13],"due":[14],"to":[15,75,147],"data":[16,122],"scarcity":[17],"and":[18,28,35,97,123,135,169],"the":[19,46,129],"complexity":[20],"of":[21,79,116],"domain-specific":[22],"terminology.":[23],"Existing":[24],"cross-lingual":[25,65,142,175],"approaches\u2014spanning":[26],"model-transfer":[27],"data-transfer":[29],"paradigms\u2014often":[30],"suffer":[31],"from":[32],"semantic":[33],"drift":[34],"inadequate":[36],"domain":[37],"adaptation.":[38],"To":[39],"address":[40],"these":[41],"limitations,":[42],"we":[43,86],"introduce":[44],"BiLegalNERD,":[45],"first":[47],"bilingual":[48,98],"Chinese\u2013Uyghur":[49],"legal":[50,105,167],"NER":[51,92,168,176],"dataset,":[52],"constructed":[53],"via":[54],"semantics-aware":[56],"label":[57,157],"transfer":[58,143],"strategy.":[59],"We":[60],"further":[61],"propose":[62],"CUTLM,":[63],"annotation":[66],"method":[67],"that":[68,109],"combines":[69],"dual":[70],"translation":[71],"with":[72,114],"Levenshtein-based":[73],"alignment":[74],"ensure":[76],"high-fidelity":[77],"preservation":[78],"entity":[80,154],"boundaries":[81],"across":[82],"languages.":[83],"In":[84],"addition,":[85],"present":[87],"BiLegalNER,":[88],"domain-adapted":[90],"multilingual":[91,131],"model":[93],"incorporating":[94],"vocabulary":[95],"expansion":[96],"fine-tuning,":[99],"significantly":[100],"enhancing":[101],"performance":[102],"on":[103,118,125],"Uyghur":[104,166],"texts.":[106],"Experiments":[107],"demonstrate":[108],"BiLegalNER":[110],"achieves":[111],"state-of-the-art":[112],"results,":[113],"F1-scores":[115],"86.65%":[117],"automatically":[119],"generated":[120],"training":[121],"89.11%":[124],"fully":[126],"human-annotated":[127],"data\u2014outperforming":[128],"strongest":[130],"baseline":[132],"by":[133,145],"4.18%":[134],"4.64%,":[136],"respectively.":[137],"Moreover,":[138],"CUTLM":[139],"surpasses":[140],"prior":[141],"methods":[144],"up":[146],"9.89%,":[148],"confirming":[149],"its":[150],"effectiveness":[151],"preserving":[153],"integrity":[155],"during":[156],"projection.":[158],"These":[159],"findings":[160],"establish":[161],"new":[163],"benchmark":[164],"provide":[170],"scalable":[172],"framework":[173],"settings.":[179]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}