{"id":"https://openalex.org/W4411113399","doi":"https://doi.org/10.18653/v1/2025.americasnlp-1.15","title":"Leveraging Large Language Models for Spanish-Indigenous Language Machine Translation at AmericasNLP 2025","display_name":"Leveraging Large Language Models for Spanish-Indigenous Language Machine Translation at AmericasNLP 2025","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4411113399","doi":"https://doi.org/10.18653/v1/2025.americasnlp-1.15"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.americasnlp-1.15","doi":"https://doi.org/10.18653/v1/2025.americasnlp-1.15","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.americasnlp-1.15","pdf_url":"https://aclanthology.org/2025.americasnlp-1.15.pdf","source":{"id":"https://openalex.org/S7407104986","display_name":"Workshop on Natural Language Processing for Indigenous Languages of the Americas (AmericasNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"conference"},"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 Fifth Workshop on NLP for Indigenous Languages of the Americas (AmericasNLP)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://aclanthology.org/2025.americasnlp-1.15.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5093457049","display_name":"Mahshar Yahan","orcid":"https://orcid.org/0009-0001-0350-1666","observed_orcids":["https://orcid.org/0009-0001-0350-1666"]},"institutions":[{"id":"https://openalex.org/I205200222","display_name":"Uttara University","ror":"https://ror.org/035zypg15","country_code":"BD","type":"education","lineage":["https://openalex.org/I205200222"]}],"countries":["BD"],"is_corresponding":false,"raw_author_name":"Mahshar Yahan","raw_affiliation_strings":["Department of Computer Science and Engineering Uttara University , Bangladesh"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering Uttara University , Bangladesh","institution_ids":["https://openalex.org/I205200222"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038408881","display_name":"Mohammad Shariful Islam","orcid":"https://orcid.org/0009-0007-8442-1425","observed_orcids":["https://orcid.org/0009-0007-8442-1425"]},"institutions":[{"id":"https://openalex.org/I205200222","display_name":"Uttara University","ror":"https://ror.org/035zypg15","country_code":"BD","type":"education","lineage":["https://openalex.org/I205200222"]}],"countries":["BD"],"is_corresponding":false,"raw_author_name":"Dr. Mohammad Islam","raw_affiliation_strings":["Department of Computer Science and Engineering Uttara University , Bangladesh"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering Uttara University , Bangladesh","institution_ids":["https://openalex.org/I205200222"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I205200222"],"apc_list":null,"apc_paid":null,"fwci":1.7834,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":{"value":0.87311063,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"126","last_page":"133"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9901999831199646,"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":0.9901999831199646,"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":0.006500000134110451,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.0008999999845400453,"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/low-resource-language-translation","display_name":"low-resource translation","score":0.7710000276565552},{"id":"https://openalex.org/keywords/multilingual-large-language-models","display_name":"multilingual large language models","score":0.6919999718666077},{"id":"https://openalex.org/keywords/nllb-200","display_name":"NLLB-200","score":0.9210000038146973},{"id":"https://openalex.org/keywords/llama-3-1","display_name":"Llama 3.1","score":0.9520000219345093},{"id":"https://openalex.org/keywords/fine-tuning","display_name":"fine-tuning","score":0.75},{"id":"https://openalex.org/keywords/dynamic-batching","display_name":"dynamic batching","score":0.8270000219345093},{"id":"https://openalex.org/keywords/tokenization","display_name":"tokenization","score":0.6970000267028809},{"id":"https://openalex.org/keywords/awajun","display_name":"Awaj\u00fan","score":0.9350000023841858},{"id":"https://openalex.org/keywords/quechua","display_name":"Quechua","score":0.9990000128746033},{"id":"https://openalex.org/keywords/nahuatl","display_name":"Nahuatl language","score":0.9959999918937683},{"id":"https://openalex.org/keywords/otomi","display_name":"Otomi","score":0.9990000128746033},{"id":"https://openalex.org/keywords/endangered-languages","display_name":"endangered languages","score":0.9259999990463257}],"concepts":[{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.8019800186157227},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7596111297607422},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5006978511810303},{"id":"https://openalex.org/C55958113","wikidata":"https://www.wikidata.org/wiki/Q169480","display_name":"Indigenous","level":2,"score":0.4726361632347107},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4480050206184387},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.42931675910949707},{"id":"https://openalex.org/C83479923","wikidata":"https://www.wikidata.org/wiki/Q2063748","display_name":"Universal Networking Language","level":4,"score":0.42883947491645813},{"id":"https://openalex.org/C2781370049","wikidata":"https://www.wikidata.org/wiki/Q645304","display_name":"Indigenous language","level":3,"score":0.4235718846321106},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.34154048562049866},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.3280564546585083},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.22211381793022156},{"id":"https://openalex.org/C129353971","wikidata":"https://www.wikidata.org/wiki/Q5156949","display_name":"Comprehension approach","level":3,"score":0.10428398847579956},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C105580179","wikidata":"https://www.wikidata.org/wiki/Q188928","display_name":"Messenger RNA","level":3,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.americasnlp-1.15","doi":"https://doi.org/10.18653/v1/2025.americasnlp-1.15","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.americasnlp-1.15","pdf_url":"https://aclanthology.org/2025.americasnlp-1.15.pdf","source":{"id":"https://openalex.org/S7407104986","display_name":"Workshop on Natural Language Processing for Indigenous Languages of the Americas (AmericasNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"conference"},"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 Fifth Workshop on NLP for Indigenous Languages of the Americas (AmericasNLP)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.americasnlp-1.15","doi":"https://doi.org/10.18653/v1/2025.americasnlp-1.15","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.americasnlp-1.15","pdf_url":"https://aclanthology.org/2025.americasnlp-1.15.pdf","source":{"id":"https://openalex.org/S7407104986","display_name":"Workshop on Natural Language Processing for Indigenous Languages of the Americas (AmericasNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"conference"},"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 Fifth Workshop on NLP for Indigenous Languages of the Americas (AmericasNLP)","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.4074000120162964,"display_name":"Reduced inequalities"}],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4411113399.pdf","grobid_xml":"https://content.openalex.org/works/W4411113399.grobid-xml"},"referenced_works_count":6,"referenced_works":["https://openalex.org/W4223451762","https://openalex.org/W4226155321","https://openalex.org/W4285077564","https://openalex.org/W4287855189","https://openalex.org/W4322718191","https://openalex.org/W4400064586"],"related_works":["https://openalex.org/W6901544924","https://openalex.org/W4388496338","https://openalex.org/W4385565061","https://openalex.org/W4378770590","https://openalex.org/W4385564874","https://openalex.org/W7198701875","https://openalex.org/W4385565107","https://openalex.org/W7083426091","https://openalex.org/W7208826806","https://openalex.org/W7126223119"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"our":[3,69],"approach":[4,89],"to":[5,65],"machine":[6,136],"translation":[7,103,137],"between":[8],"Spanish":[9],"and":[10,41,52,60,76,87,97,119],"13":[11],"Indigenous":[12],"languages":[13,84],"of":[14,19,27,115,127],"the":[15,20,25,101,107,125],"Americas":[16],"as":[17,47],"part":[18],"AmericasNLP":[21],"2025":[22],"shared":[23],"task.Addressing":[24],"challenges":[26],"low-resource":[28],"translation,":[29],"we":[30,111],"fine-tuned":[31],"advanced":[32],"multilingual":[33],"models,":[34],"including":[35],"NLLB-200":[36],"(Distilled-600M),":[37],"Llama":[38],"3.1":[39],"(8B-Instruct)":[40],"XGLM":[42],"1.7B,":[43],"using":[44],"techniques":[45],"such":[46],"dynamic":[48],"batching,":[49],"token":[50],"adjustments,":[51],"embedding":[53],"initialization.Data":[54],"preprocessing":[55],"steps":[56],"like":[57,85],"punctuation":[58],"removal":[59],"tokenization":[61],"refinements":[62],"were":[63],"employed":[64],"achieve":[66],"data":[67],"generalization.While":[68],"models":[70],"demonstrated":[71],"strong":[72],"performance":[73],"for":[74,94,117,121,138],"Awajun":[75,95,118],"Quechua":[77,98],"translations,":[78],"they":[79],"struggled":[80],"with":[81],"morphologically":[82],"complex":[83],"Nahuatl":[86],"Otom\u00ed.Our":[88],"achieved":[90],"competitive":[91],"ChrF++":[92,113],"scores":[93,114],"(35.16)":[96],"(31.01)":[99],"in":[100,106,130],"Spanish-to-Indigenous":[102],"track":[104,109],"(Es\u2192Xx).Similarly,":[105],"Indigenous-to-Spanish":[108],"(Xx\u2192Es),":[110],"obtained":[112],"33.70":[116],"31.71":[120],"Quechua.These":[122],"results":[123],"underscore":[124],"potential":[126],"tailored":[128],"methodologies":[129],"preserving":[131],"linguistic":[132],"diversity":[133],"while":[134],"advancing":[135],"endangered":[139],"languages.":[140]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":1}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2025-10-10T00:00:00"}
