{"id":"https://openalex.org/W7107861696","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249135","title":"100\u00d7 Monolingual Data Augmentation Using LLMs to Build a Parallel Corpus for Machine Translation","display_name":"100\u00d7 Monolingual Data Augmentation Using LLMs to Build a Parallel Corpus for Machine Translation","publication_year":2025,"publication_date":"2025-10-22","ids":{"openalex":"https://openalex.org/W7107861696","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249135"},"language":null,"primary_location":{"id":"doi:10.1109/apsipaasc65261.2025.11249135","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249135","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-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":null,"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.,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Japan Broadcasting Corp.,Japan","institution_ids":["https://openalex.org/I4210107548"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Naoto 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.,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Japan Broadcasting Corp.,Japan","institution_ids":["https://openalex.org/I4210107548"]}]},{"author_position":"middle","author":{"id":null,"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.,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Japan Broadcasting Corp.,Japan","institution_ids":["https://openalex.org/I4210107548"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Hideya Mino","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":"Hideya Mino","raw_affiliation_strings":["Japan Broadcasting Corp.,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Japan Broadcasting Corp.,Japan","institution_ids":["https://openalex.org/I4210107548"]}]},{"author_position":"last","author":{"id":null,"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.,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Japan Broadcasting Corp.,Japan","institution_ids":["https://openalex.org/I4210107548"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.74544922,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1170","last_page":"1175"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9447000026702881,"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":0.9447000026702881,"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":0.019700000062584877,"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/T13629","display_name":"Text Readability and Simplification","score":0.009700000286102295,"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/leverage","display_name":"Leverage (statistics)","score":0.7954999804496765},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.7501999735832214},{"id":"https://openalex.org/keywords/domain-adaptation","display_name":"Domain adaptation","score":0.6675000190734863},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.5526999831199646},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.49709999561309814},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.47940000891685486}],"concepts":[{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.7954999804496765},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.7501999735832214},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7135999798774719},{"id":"https://openalex.org/C2776434776","wikidata":"https://www.wikidata.org/wiki/Q19246213","display_name":"Domain adaptation","level":3,"score":0.6675000190734863},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5817000269889832},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5691999793052673},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.5526999831199646},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.49709999561309814},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.47940000891685486},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4417000114917755},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.4406999945640564},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.41760000586509705},{"id":"https://openalex.org/C2985684807","wikidata":"https://www.wikidata.org/wiki/Q1513879","display_name":"Text generation","level":2,"score":0.3010999858379364},{"id":"https://openalex.org/C2985367798","wikidata":"https://www.wikidata.org/wiki/Q1346592","display_name":"Parallel corpora","level":3,"score":0.2980000078678131},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.2685999870300293},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.25589999556541443}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipaasc65261.2025.11249135","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249135","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.8235529065132141}],"awards":[],"funders":[{"id":"https://openalex.org/F4320335839","display_name":"National Institute of Information and Communications Technology","ror":"https://ror.org/016bgq349"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W2101105183","https://openalex.org/W2610850660","https://openalex.org/W2611838487","https://openalex.org/W2963216553","https://openalex.org/W2963532001","https://openalex.org/W2970641574","https://openalex.org/W3105214104","https://openalex.org/W4395680645","https://openalex.org/W4402670035","https://openalex.org/W4402670196","https://openalex.org/W4402671186","https://openalex.org/W4402683829"],"related_works":[],"abstract_inverted_index":{"The":[0],"aim":[1],"of":[2,10,71,125,135],"this":[3,65],"study":[4],"is":[5],"to":[6,74,80],"address":[7],"the":[8,58,69,88,112,117,122,133,139],"generation":[9,102],"high-quality":[11],"synthetic":[12,76,113],"data":[13,26,53,77,114],"for":[14],"domain":[15,60],"adaptation":[16],"in":[17,100,149],"news":[18,108],"machine":[19,22],"translation.":[20],"Effective":[21],"translation":[23,109,123],"requires":[24],"training":[25],"that":[27,54,111,132],"includes":[28],"domain-relevant":[29],"characteristics":[30],"such":[31],"as":[32],"topical":[33],"focus":[34],"and":[35,46,96,138],"writing":[36],"style.":[37],"Large":[38],"language":[39],"models":[40],"(LLMs)":[41],"can":[42],"generate":[43,75],"both":[44],"bilingual":[45],"monolingual":[47,52,90],"data;":[48],"however,":[49],"producing":[50],"diverse":[51],"closely":[55],"aligns":[56],"with":[57,87],"target":[59],"remains":[61],"a":[62,101,146],"challenge.":[63],"In":[64],"work,":[66],"we":[67],"explore":[68],"feasibility":[70],"using":[72],"LLMs":[73,99,144],"by":[78,116],"attempting":[79],"create":[81],"100":[82],"times":[83],"parallel":[84],"sentence":[85],"pairs":[86],"original":[89],"sentences.":[91],"We":[92],"leverage":[93],"domain-specific":[94],"keywords":[95,137],"combine":[97],"multiple":[98,143],"pipeline.":[103],"Experimental":[104],"results":[105,129],"on":[106],"Thai-Japanese":[107],"confirmed":[110],"generated":[115],"proposed":[118],"method":[119],"significantly":[120],"improved":[121],"performance":[124],"general-purpose":[126],"models.":[127],"These":[128],"also":[130],"revealed":[131],"use":[134],"appropriate":[136],"strategic":[140],"switching":[141],"between":[142],"play":[145],"crucial":[147],"role":[148],"outperforming":[150],"conventional":[151],"methods.":[152]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-11-28T00:00:00"}