{"id":"https://openalex.org/W7164740236","doi":"https://doi.org/10.5715/jnlp.33.691","title":"LlmMT+1: Enhancing Non-dominant Language Pair in Large Language Model-based Machine Translation","display_name":"LlmMT+1: Enhancing Non-dominant Language Pair in Large Language Model-based Machine Translation","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7164740236","doi":"https://doi.org/10.5715/jnlp.33.691"},"language":"en","primary_location":{"id":"doi:10.5715/jnlp.33.691","is_oa":true,"landing_page_url":"https://doi.org/10.5715/jnlp.33.691","pdf_url":"https://www.jstage.jst.go.jp/article/jnlp/33/2/33_691/_pdf","source":{"id":"https://openalex.org/S4210212357","display_name":"Journal of Natural Language Processing","issn_l":"1340-7619","issn":["1340-7619","2185-8314"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Natural Language Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://www.jstage.jst.go.jp/article/jnlp/33/2/33_691/_pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5138607862","display_name":"Xinger Fu","orcid":null},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Xinger Fu","raw_affiliation_strings":["Graduate School of Informatics, Kyoto University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Informatics, Kyoto University","institution_ids":["https://openalex.org/I22299242"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138626040","display_name":"Masaaki Nagata","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Masaaki Nagata","raw_affiliation_strings":["NTT Communication Science Laboratories"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102757632","display_name":"Chenhui Chu","orcid":"https://orcid.org/0000-0001-9848-6384"},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Chenhui Chu","raw_affiliation_strings":["Graduate School of Informatics, Kyoto University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Informatics, Kyoto University","institution_ids":["https://openalex.org/I22299242"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"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":0.61742513,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"33","issue":"2","first_page":"691","last_page":"721"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.7914000153541565,"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":0.7914000153541565,"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":0.05490000173449516,"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":0.01360000018030405,"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/machine-translation","display_name":"Machine translation","score":0.6437000036239624},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.4056999981403351},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.3937000036239624},{"id":"https://openalex.org/keywords/universal-networking-language","display_name":"Universal Networking Language","score":0.33160001039505005},{"id":"https://openalex.org/keywords/language-identification","display_name":"Language identification","score":0.2863999903202057},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.2766000032424927}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6812999844551086},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.6437000036239624},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5529999732971191},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5238999724388123},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.4056999981403351},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.3937000036239624},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.3395000100135803},{"id":"https://openalex.org/C83479923","wikidata":"https://www.wikidata.org/wiki/Q2063748","display_name":"Universal Networking Language","level":4,"score":0.33160001039505005},{"id":"https://openalex.org/C129792486","wikidata":"https://www.wikidata.org/wiki/Q1050419","display_name":"Language identification","level":3,"score":0.2863999903202057},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2766000032424927},{"id":"https://openalex.org/C110046852","wikidata":"https://www.wikidata.org/wiki/Q468495","display_name":"Computer-assisted translation","level":3,"score":0.26350000500679016},{"id":"https://openalex.org/C24687705","wikidata":"https://www.wikidata.org/wiki/Q3753284","display_name":"Example-based machine translation","level":3,"score":0.26010000705718994},{"id":"https://openalex.org/C94922259","wikidata":"https://www.wikidata.org/wiki/Q33215","display_name":"Constructed language","level":2,"score":0.25209999084472656},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.25060001015663147}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.5715/jnlp.33.691","is_oa":true,"landing_page_url":"https://doi.org/10.5715/jnlp.33.691","pdf_url":"https://www.jstage.jst.go.jp/article/jnlp/33/2/33_691/_pdf","source":{"id":"https://openalex.org/S4210212357","display_name":"Journal of Natural Language Processing","issn_l":"1340-7619","issn":["1340-7619","2185-8314"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Natural Language Processing","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.5715/jnlp.33.691","is_oa":true,"landing_page_url":"https://doi.org/10.5715/jnlp.33.691","pdf_url":"https://www.jstage.jst.go.jp/article/jnlp/33/2/33_691/_pdf","source":{"id":"https://openalex.org/S4210212357","display_name":"Journal of Natural Language Processing","issn_l":"1340-7619","issn":["1340-7619","2185-8314"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Natural Language Processing","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.5449851155281067}],"awards":[],"funders":[{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7164740236.pdf","grobid_xml":"https://content.openalex.org/works/W7164740236.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Large":[0],"language":[1,30,43,79,85,158],"model":[2,129,141,172],"(LLM)":[3],"based":[4,106,160],"machine":[5],"translation":[6,27,80,180,197],"(MT)":[7],"has":[8],"gained":[9],"increasing":[10],"attention.":[11],"However,":[12],"most":[13],"LLM-based":[14,90,123],"MT":[15,91,124],"models":[16,194],"are":[17,60],"primarily":[18],"designed":[19],"for":[20],"dominant-language":[21,35],"pairs":[22,54,159],"and":[23,102,137,174],"perform":[24],"poorly":[25],"on":[26,107,161],"between":[28],"non-dominant":[29,53,78,157],"pairs.":[31,198],"We":[32,115,154],"define":[33],"a":[34,72,83,139,148],"pair":[36,86],"as":[37],"one":[38,42],"where":[39],"at":[40],"least":[41],"is":[44,134],"dominant":[45],"in":[46,191],"the":[47,94,108,112,162,166,186],"model\u2019s":[48],"pre-training":[49,109,163],"corpus.":[50],"In":[51],"contrast,":[52],"consist":[55],"of":[56,111,122,165,188],"two":[57,120,171],"languages":[58,146,168],"that":[59,176],"underrepresented":[61],"or":[62],"unseen":[63],"during":[64],"pre-training.":[65],"To":[66],"address":[67],"this":[68,117],"limitation,":[69],"we":[70],"propose":[71],"generalizable":[73],"recipe,":[74],"LlmMT+1.":[75],"LlmMT+1":[76,177],"enhances":[77],"by":[81],"adding":[82],"new":[84,196],"to":[87,119,195],"an":[88,127],"existing":[89],"model,":[92],"adapting":[93,192],"training":[95,132,152],"strategy,":[96],"including":[97],"continual":[98],"pre-training,":[99],"supervised":[100],"fine-tuning,":[101],"direct":[103],"preference":[104,189],"optimization":[105,190],"status":[110,164],"involved":[113,167],"languages.":[114],"apply":[116],"recipe":[118],"types":[121,173],"models:":[125],"(1)":[126],"English-dominant":[128],"(TowerBase-13B),":[130],"whose":[131],"corpus":[133],"predominantly":[135],"English,":[136],"(2)":[138],"multilingual":[140,151,193],"(Aya-expanse-8B),":[142],"which":[143],"supports":[144],"23":[145],"with":[147],"more":[149],"balanced":[150],"strategy.":[153],"evaluate":[155],"six":[156],"across":[169],"these":[170],"demonstrate":[175],"consistently":[178],"improves":[179],"performance.":[181],"Our":[182],"ablation":[183],"studies":[184],"highlight":[185],"effectiveness":[187]},"counts_by_year":[],"updated_date":"2026-08-21T09:56:20.448147","created_date":"2026-06-15T00:00:00"}