{"id":"https://openalex.org/W7166883568","doi":"https://doi.org/10.18653/v1/2026.findings-acl.2059","title":"Context-Driven and Reference-Guided Data Augmentation for Subtitle Translation","display_name":"Context-Driven and Reference-Guided Data Augmentation for Subtitle Translation","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166883568","doi":"https://doi.org/10.18653/v1/2026.findings-acl.2059"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.findings-acl.2059","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.2059","pdf_url":"https://aclanthology.org/2026.findings-acl.2059.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 2026","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.findings-acl.2059.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5139789503","display_name":"Hitoshi Ito","orcid":null},"institutions":[{"id":"https://openalex.org/I4210107548","display_name":"Japan Broadcasting Corporation (Japan)","ror":"https://ror.org/01s8tz949","country_code":"JP","type":"company","lineage":["https://openalex.org/I4210107548"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hitoshi Ito","raw_affiliation_strings":["Japan Broadcasting Corp. , Tokyo , Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Japan Broadcasting Corp. , Tokyo , Japan","institution_ids":["https://openalex.org/I4210107548"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061328998","display_name":"N. Shirai","orcid":null},"institutions":[{"id":"https://openalex.org/I4210107548","display_name":"Japan Broadcasting Corporation (Japan)","ror":"https://ror.org/01s8tz949","country_code":"JP","type":"company","lineage":["https://openalex.org/I4210107548"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Naoto Shirai","raw_affiliation_strings":["Japan Broadcasting Corp. , Tokyo , Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Japan Broadcasting Corp. , Tokyo , Japan","institution_ids":["https://openalex.org/I4210107548"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054287040","display_name":"Kazutaka Kinugawa","orcid":null},"institutions":[{"id":"https://openalex.org/I4210107548","display_name":"Japan Broadcasting Corporation (Japan)","ror":"https://ror.org/01s8tz949","country_code":"JP","type":"company","lineage":["https://openalex.org/I4210107548"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kazutaka Kinugawa","raw_affiliation_strings":["Japan Broadcasting Corp. , Tokyo , Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Japan Broadcasting Corp. , Tokyo , Japan","institution_ids":["https://openalex.org/I4210107548"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035575030","display_name":"Hideya Mino","orcid":"https://orcid.org/0009-0000-7257-8045"},"institutions":[{"id":"https://openalex.org/I4210107548","display_name":"Japan Broadcasting Corporation (Japan)","ror":"https://ror.org/01s8tz949","country_code":"JP","type":"company","lineage":["https://openalex.org/I4210107548"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hideya Mino","raw_affiliation_strings":["Japan Broadcasting Corp. , Tokyo , Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Japan Broadcasting Corp. , Tokyo , Japan","institution_ids":["https://openalex.org/I4210107548"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129733221","display_name":"Rei Endo","orcid":null},"institutions":[{"id":"https://openalex.org/I4210107548","display_name":"Japan Broadcasting Corporation (Japan)","ror":"https://ror.org/01s8tz949","country_code":"JP","type":"company","lineage":["https://openalex.org/I4210107548"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Rei Endo","raw_affiliation_strings":["Japan Broadcasting Corp. , Tokyo , Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Japan Broadcasting Corp. , Tokyo , Japan","institution_ids":["https://openalex.org/I4210107548"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5139840416","display_name":"Yoshihiko Kawai","orcid":null},"institutions":[{"id":"https://openalex.org/I4210107548","display_name":"Japan Broadcasting Corporation (Japan)","ror":"https://ror.org/01s8tz949","country_code":"JP","type":"company","lineage":["https://openalex.org/I4210107548"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yoshihiko Kawai","raw_affiliation_strings":["Japan Broadcasting Corp. , Tokyo , Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Japan Broadcasting Corp. , Tokyo , Japan","institution_ids":["https://openalex.org/I4210107548"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210107548"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.95809913,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"41381","last_page":"41394"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13310","display_name":"Subtitles and Audiovisual Media","score":0.6220999956130981,"subfield":{"id":"https://openalex.org/subfields/1203","display_name":"Language and Linguistics"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T13310","display_name":"Subtitles and Audiovisual Media","score":0.6220999956130981,"subfield":{"id":"https://openalex.org/subfields/1203","display_name":"Language and Linguistics"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.06769999861717224,"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/T10759","display_name":"Translation Studies and Practices","score":0.06469999998807907,"subfield":{"id":"https://openalex.org/subfields/1203","display_name":"Language and Linguistics"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/subtitle","display_name":"Subtitle","score":0.7660999894142151},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.5181999802589417},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.24609999358654022},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.2345999926328659}],"concepts":[{"id":"https://openalex.org/C2780364048","wikidata":"https://www.wikidata.org/wiki/Q204028","display_name":"Subtitle","level":2,"score":0.7660999894142151},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5533999800682068},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.5181999802589417},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47290000319480896},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.47189998626708984},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.35569998621940613},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.2653999924659729},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.24609999358654022},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2345999926328659},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.23319999873638153}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.findings-acl.2059","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.2059","pdf_url":"https://aclanthology.org/2026.findings-acl.2059.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 2026","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.findings-acl.2059","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.2059","pdf_url":"https://aclanthology.org/2026.findings-acl.2059.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 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166883568.pdf","grobid_xml":"https://content.openalex.org/works/W7166883568.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Large":[0],"language":[1],"models":[2],"(LLMs)":[3],"have":[4],"demonstrated":[5],"strong":[6],"performance":[7,63],"in":[8,156],"translation":[9,11,62],"tasks.Subtitle":[10],"presents":[12],"unique":[13],"challenges,":[14],"such":[15,95],"as":[16,96],"preserving":[17],"the":[18,23,93,104,110,113,140],"original":[19,84],"work's":[20],"worldview":[21],"and":[22,99,106,151],"distinctive":[24],"speaking":[25],"styles":[26],"of":[27,109],"its":[28],"characters.Achieving":[29],"high-quality":[30],"translations":[31],"that":[32,57,88,136],"reflect":[33],"these":[34],"stylistic":[35,154],"nuances":[36],"typically":[37],"requires":[38],"bilingual":[39,73,128],"data":[40,54,81,129,137],"for":[41,64,147],"a":[42,53,70],"specific":[43,65],"movie,":[44],"which":[45,125],"is":[46],"often":[47],"scarce":[48],"or":[49],"unavailable.Thus,":[50],"we":[51],"propose":[52],"augmentation":[55],"method":[56,78,142],"uses":[58],"LLMs":[59],"to":[60,102],"improve":[61],"movies,":[66],"even":[67],"when":[68],"only":[69],"few":[71],"hundred":[72],"sentence":[74],"pairs":[75],"are":[76,116],"available.The":[77],"expands":[79],"source-side":[80],"by":[82],"rewriting":[83],"subtitles":[85],"using":[86,122,139],"information":[87],"can":[89],"be":[90],"extracted":[91],"from":[92],"context,":[94],"character":[97],"profiles":[98],"scene":[100],"descriptions,":[101],"maintain":[103],"tone":[105],"thematic":[107],"consistency":[108],"movie.For":[111],"translation,":[112,150],"augmented":[114,138],"sentences":[115],"aligned":[117],"with":[118],"manually":[119],"translated":[120],"originals":[121],"structural":[123],"similarity,":[124],"enables":[126],"stylepreserving":[127],"generation":[130],"via":[131],"oneshot":[132],"learning.Experimental":[133],"results":[134],"show":[135],"proposed":[141],"effectively":[143],"improves":[144],"BLEU":[145],"scores":[146],"film":[148],"subtitle":[149],"achieves":[152],"superior":[153],"quality":[155],"human":[157],"evaluation.":[158]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-07-02T00:00:00"}