{"id":"https://openalex.org/W7134810722","doi":"https://doi.org/10.1145/3800681","title":"Exploiting Domain-Specific Parallel Data on Multilingual Language Models for Low-Resource Language Translation","display_name":"Exploiting Domain-Specific Parallel Data on Multilingual Language Models for Low-Resource Language Translation","publication_year":2026,"publication_date":"2026-03-09","ids":{"openalex":"https://openalex.org/W7134810722","doi":"https://doi.org/10.1145/3800681"},"language":"en","primary_location":{"id":"doi:10.1145/3800681","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3800681","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1145/3800681","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5002889503","display_name":"Surangika Ranathunga","orcid":"https://orcid.org/0000-0003-0701-0204"},"institutions":[{"id":"https://openalex.org/I51158804","display_name":"Massey University","ror":"https://ror.org/052czxv31","country_code":"NZ","type":"education","lineage":["https://openalex.org/I51158804"]}],"countries":["NZ"],"is_corresponding":false,"raw_author_name":"Surangika Ranathunga","raw_affiliation_strings":["Massey University"],"raw_orcid":"https://orcid.org/0000-0003-0701-0204","affiliations":[{"raw_affiliation_string":"Massey University","institution_ids":["https://openalex.org/I51158804"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003441670","display_name":"Shravan Nayak","orcid":"https://orcid.org/0000-0002-5298-7121"},"institutions":[{"id":"https://openalex.org/I70931966","display_name":"Universit\u00e9 de Montr\u00e9al","ror":"https://ror.org/0161xgx34","country_code":"CA","type":"education","lineage":["https://openalex.org/I70931966"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Shravan Nayak","raw_affiliation_strings":["Universit\u00e9 de Montr\u00e9al"],"raw_orcid":"https://orcid.org/0000-0002-5298-7121","affiliations":[{"raw_affiliation_string":"Universit\u00e9 de Montr\u00e9al","institution_ids":["https://openalex.org/I70931966"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128678965","display_name":"En-Shiun Lee","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"En-Shiun Lee","raw_affiliation_strings":["Ontario Tech"],"raw_orcid":"https://orcid.org/0000-0003-4592-3522","affiliations":[{"raw_affiliation_string":"Ontario Tech","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128633035","display_name":"Xin Peng","orcid":null},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Xin Peng","raw_affiliation_strings":["University of Toronto"],"raw_orcid":"https://orcid.org/0009-0000-0816-3793","affiliations":[{"raw_affiliation_string":"University of Toronto","institution_ids":["https://openalex.org/I185261750"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Shih-Ting Huang","orcid":"https://orcid.org/0009-0005-2021-6209"},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Shih-Ting Huang","raw_affiliation_strings":["University of Toronto"],"raw_orcid":"https://orcid.org/0009-0005-2021-6209","affiliations":[{"raw_affiliation_string":"University of Toronto","institution_ids":["https://openalex.org/I185261750"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yuchen Zeng","orcid":"https://orcid.org/0009-0006-3452-5536"},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Yuchen Zeng","raw_affiliation_strings":["University of Toronto"],"raw_orcid":"https://orcid.org/0009-0006-3452-5536","affiliations":[{"raw_affiliation_string":"University of Toronto","institution_ids":["https://openalex.org/I185261750"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101245165","display_name":"Yanke Mao","orcid":null},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Yanke Mao","raw_affiliation_strings":["University of Toronto"],"raw_orcid":"https://orcid.org/0009-0009-8561-1743","affiliations":[{"raw_affiliation_string":"University of Toronto","institution_ids":["https://openalex.org/I185261750"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101570910","display_name":"Tong Su","orcid":"https://orcid.org/0009-0008-5819-2443"},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Tong Su","raw_affiliation_strings":["University of Toronto"],"raw_orcid":"https://orcid.org/0009-0008-5819-2443","affiliations":[{"raw_affiliation_string":"University of Toronto","institution_ids":["https://openalex.org/I185261750"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128670007","display_name":"Yun-Hsiang Chan","orcid":null},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Yun-Hsiang Chan","raw_affiliation_strings":["University of Toronto"],"raw_orcid":"https://orcid.org/0009-0001-9010-5943","affiliations":[{"raw_affiliation_string":"University of Toronto","institution_ids":["https://openalex.org/I185261750"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109138785","display_name":"Songchen Yuan","orcid":null},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Songchen Yuan","raw_affiliation_strings":["University of Toronto"],"raw_orcid":"https://orcid.org/0009-0009-4030-4512","affiliations":[{"raw_affiliation_string":"University of Toronto","institution_ids":["https://openalex.org/I185261750"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5052573996","display_name":"Anthony Rinaldi","orcid":"https://orcid.org/0000-0003-3686-7485"},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Anthony Rinaldi","raw_affiliation_strings":["University of Toronto"],"raw_orcid":"https://orcid.org/0000-0003-3686-7485","affiliations":[{"raw_affiliation_string":"University of Toronto","institution_ids":["https://openalex.org/I185261750"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":11,"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":0.31129734,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"25","issue":"4","first_page":"1","last_page":"34"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.8058000206947327,"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":0.8058000206947327,"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":0.08370000123977661,"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":0.017100000753998756,"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":0.599399983882904},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5476999878883362},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.5295000076293945},{"id":"https://openalex.org/keywords/divergence","display_name":"Divergence (linguistics)","score":0.4984000027179718},{"id":"https://openalex.org/keywords/parallel-corpora","display_name":"Parallel corpora","score":0.48570001125335693},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.4749999940395355},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4571000039577484},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.44200000166893005}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8551999926567078},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.599399983882904},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5598999857902527},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5476999878883362},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.5295000076293945},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5113999843597412},{"id":"https://openalex.org/C207390915","wikidata":"https://www.wikidata.org/wiki/Q1230525","display_name":"Divergence (linguistics)","level":2,"score":0.4984000027179718},{"id":"https://openalex.org/C2985367798","wikidata":"https://www.wikidata.org/wiki/Q1346592","display_name":"Parallel corpora","level":3,"score":0.48570001125335693},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.4749999940395355},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4571000039577484},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.44200000166893005},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4242999851703644},{"id":"https://openalex.org/C100463513","wikidata":"https://www.wikidata.org/wiki/Q5227322","display_name":"Data model (GIS)","level":2,"score":0.3301999866962433},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.31360000371932983},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.3034999966621399},{"id":"https://openalex.org/C116409475","wikidata":"https://www.wikidata.org/wiki/Q1385056","display_name":"External Data Representation","level":2,"score":0.29510000348091125},{"id":"https://openalex.org/C2986862884","wikidata":"https://www.wikidata.org/wiki/Q7553","display_name":"Language translation","level":3,"score":0.27619999647140503},{"id":"https://openalex.org/C77660490","wikidata":"https://www.wikidata.org/wiki/Q244916","display_name":"Intermediate language","level":3,"score":0.2696000039577484},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2671999931335449},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.2653999924659729},{"id":"https://openalex.org/C179603123","wikidata":"https://www.wikidata.org/wiki/Q1941921","display_name":"Modeling language","level":3,"score":0.2567000091075897},{"id":"https://openalex.org/C56288433","wikidata":"https://www.wikidata.org/wiki/Q58673","display_name":"Data manipulation language","level":2,"score":0.2556999921798706}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3800681","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3800681","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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":{"id":"doi:10.1145/3800681","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3800681","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W2758950307","https://openalex.org/W2963532001","https://openalex.org/W3034255912","https://openalex.org/W3034999214","https://openalex.org/W3035032094","https://openalex.org/W3117034213","https://openalex.org/W3137010024","https://openalex.org/W3169369929","https://openalex.org/W3169625465","https://openalex.org/W3174724858","https://openalex.org/W3191290329","https://openalex.org/W3198189804","https://openalex.org/W3199365283","https://openalex.org/W4285296929","https://openalex.org/W4404784034"],"related_works":[],"abstract_inverted_index":{"Neural":[0],"Machine":[1],"Translation":[2],"(NMT)":[3],"systems":[4,44],"built":[5],"on":[6,94],"multilingual":[7],"sequence-to-sequence":[8],"Language":[9],"Models":[10],"(msLMs)":[11],"fail":[12],"to":[13,61,64],"deliver":[14],"expected":[15],"results":[16],"when":[17],"the":[18,29,33,39,67,74,81,89],"amount":[19],"of":[20,41,73,76,83,91],"parallel":[21,52,105],"data":[22,53,106],"for":[23,45,102,112],"a":[24,50],"language,":[25],"as":[26,28],"well":[27],"language\u2019s":[30],"representation":[31],"in":[32,80,107],"model":[34,96],"are":[35],"limited.":[36],"This":[37],"restricts":[38],"capabilities":[40],"domain-specific":[42,84,109],"NMT":[43,95,110],"low-resource":[46],"languages":[47],"(LRLs).":[48],"As":[49],"solution,":[51],"from":[54],"auxiliary":[55,104],"domains":[56],"can":[57],"be":[58],"used":[59],"either":[60],"fine-tune":[62],"or":[63],"further":[65],"pre-train":[66],"msLM.":[68],"We":[69,86,98],"present":[70],"an":[71],"evaluation":[72],"effectiveness":[75],"these":[77],"two":[78],"techniques":[79],"context":[82],"LRL-NMT.":[85],"also":[87],"explore":[88],"impact":[90],"domain":[92],"divergence":[93],"performance.":[97],"recommend":[99],"several":[100],"strategies":[101],"utilizing":[103],"building":[108],"models":[111],"LRLs.":[113]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-03-11T00:00:00"}
