{"id":"https://openalex.org/W4416033772","doi":"https://doi.org/10.18653/v1/2025.wmt-1.97","title":"Tackling Low-Resource NMT with Instruction-Tuned LLaMA: A Study on Kokborok and Bodo","display_name":"Tackling Low-Resource NMT with Instruction-Tuned LLaMA: A Study on Kokborok and Bodo","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416033772","doi":"https://doi.org/10.18653/v1/2025.wmt-1.97"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2025.wmt-1.97","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.wmt-1.97","pdf_url":"https://aclanthology.org/2025.wmt-1.97.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":"Proceedings of the Tenth Conference on Machine Translation","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.wmt-1.97.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100697349","display_name":"Deepak Kumar","orcid":"https://orcid.org/0000-0002-0418-5116"},"institutions":[{"id":"https://openalex.org/I132153292","display_name":"Indian Institute of Technology Patna","ror":"https://ror.org/01ft5vz71","country_code":"IN","type":"education","lineage":["https://openalex.org/I132153292"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Deepak Kumar","raw_affiliation_strings":["Indian Institute of Technology , Patna"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology , Patna","institution_ids":["https://openalex.org/I132153292"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101277481","display_name":"Kshetrimayum Boynao Singh","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kshetrimayum Boynao Singh","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5085370631","display_name":"Asif Ekbal","orcid":"https://orcid.org/0000-0003-3612-8834"},"institutions":[{"id":"https://openalex.org/I132153292","display_name":"Indian Institute of Technology Patna","ror":"https://ror.org/01ft5vz71","country_code":"IN","type":"education","lineage":["https://openalex.org/I132153292"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Asif Ekbal","raw_affiliation_strings":["Indian Institute of Technology , Patna"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology , Patna","institution_ids":["https://openalex.org/I132153292"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1215","last_page":"1221"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.133200004696846,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.133200004696846,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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/T12326","display_name":"Network Packet Processing and Optimization","score":0.09059999883174896,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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/T13194","display_name":"ICT in Developing Communities","score":0.07919999957084656,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/set","display_name":"Set (abstract data type)","score":0.2944999933242798},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.25440001487731934},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.23819999396800995},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.23720000684261322},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.22699999809265137}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4837999939918518},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.2944999933242798},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.29010000824928284},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.27799999713897705},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.25440001487731934},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.23819999396800995},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.23720000684261322},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.23499999940395355},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.22699999809265137},{"id":"https://openalex.org/C151201525","wikidata":"https://www.wikidata.org/wiki/Q177239","display_name":"Limit (mathematics)","level":2,"score":0.22599999606609344}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.wmt-1.97","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.wmt-1.97","pdf_url":"https://aclanthology.org/2025.wmt-1.97.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":"Proceedings of the Tenth Conference on Machine Translation","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.wmt-1.97","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.wmt-1.97","pdf_url":"https://aclanthology.org/2025.wmt-1.97.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":"Proceedings of the Tenth Conference on Machine Translation","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416033772.pdf","grobid_xml":"https://content.openalex.org/works/W4416033772.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"a":[3,44,59,82,94,134,139,144],"new":[4],"neural":[5],"machine":[6],"translation":[7,118],"(NMT)":[8],"system":[9],"aimed":[10],"at":[11],"low-resource":[12,109,126],"language":[13],"pairs:":[14],"English":[15,19,51,91,128,149],"to":[16,20,66,70,101,129,150,189],"Kokborok":[17,48],"and":[18,49,89,143,162,173,184],"Bodo.The":[21],"framework":[22],"leverages":[23],"the":[24,35,67,74,77,103,112,121,131,168,171,175],"LLaMA3-8B-Instruct":[25],"model":[26,36,78,106,132,187],"along":[27],"with":[28,111],"LoRAbased":[29],"parameter-efficient":[30],"fine-tuning.For":[31],"translating":[32,124],"into":[33],"Kokborok,":[34,151],"undergoes":[37],"an":[38],"initial":[39],"continued":[40],"pre-training":[41],"phase":[42],"on":[43,81],"dataset":[45,85,115],"containing":[46],"75,000":[47],"25,000":[50],"monolingual":[52],"sentences,":[53,92],"followed":[54],"by":[55],"instruction-tuning.This":[56],"tuning":[57],"uses":[58],"reformulated":[60],"version":[61],"of":[62,86,137,141,147,155,170],"WMT25":[63,113],"dataset,":[64],"adapted":[65],"Alpaca":[68],"format":[69],"support":[71,191],"instructional":[72],"goals.In":[73],"Bodo":[75,88],"translation,":[76],"is":[79],"pre-trained":[80],"more":[83],"extensive":[84],"350,000":[87],"125,000":[90],"using":[93],"similar":[95],"instruction-tuning":[96],"approach.LoRA":[97],"adapters":[98],"are":[99],"used":[100],"modify":[102],"large":[104],"LLaMA3":[105],"for":[107,125,178],"these":[108],"settings.Testing":[110],"test":[114],"reveals":[116],"modest":[117],"results,":[119],"highlighting":[120],"difficulties":[122],"in":[123,157,160,164,186],"languages.Translating":[127],"Bodo,":[130],"achieved":[133],"BLEU":[135],"score":[136,146],"4.38,":[138],"TER":[140],"92.5,":[142],"chrF":[145],"35.4.For":[148],"it":[152],"yielded":[153],"scores":[154],"5.59":[156],"chrF,":[158],"105.4":[159],"TER,":[161],"0.17":[163],"BLEU.These":[165],"results":[166],"underscore":[167],"intricacies":[169],"task":[172],"highlight":[174],"critical":[176],"need":[177],"further":[179],"data":[180],"collection,":[181],"domain-specific":[182],"adaptations,":[183],"improvements":[185],"design":[188],"better":[190],"underrepresented":[192],"languages.":[193]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-11-08T00:00:00"}
