{"id":"https://openalex.org/W4411112993","doi":"https://doi.org/10.18653/v1/2025.americasnlp-1.14","title":"Harnessing NLP for Indigenous Language Education: Fine-Tuning Large Language Models for Sentence Transformation","display_name":"Harnessing NLP for Indigenous Language Education: Fine-Tuning Large Language Models for Sentence Transformation","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4411112993","doi":"https://doi.org/10.18653/v1/2025.americasnlp-1.14"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.americasnlp-1.14","doi":"https://doi.org/10.18653/v1/2025.americasnlp-1.14","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.americasnlp-1.14","pdf_url":"https://aclanthology.org/2025.americasnlp-1.14.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-1.14.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":0.3567,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.54602513,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"119","last_page":"125"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9121000170707703,"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":0.9121000170707703,"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":0.08389999717473984,"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/T12031","display_name":"Speech and dialogue systems","score":0.0006000000284984708,"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/indigenous-languages","display_name":"indigenous languages","score":0.8960000276565552},{"id":"https://openalex.org/keywords/sentence-transformation","display_name":"sentence transformation","score":0.9670000076293945},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.9399999976158142},{"id":"https://openalex.org/keywords/bribri","display_name":"Bribri","score":0.6959999799728394},{"id":"https://openalex.org/keywords/guarani-language","display_name":"Guarani","score":0.9929999709129333},{"id":"https://openalex.org/keywords/maya","display_name":"Maya","score":0.972000002861023},{"id":"https://openalex.org/keywords/grammatical-transformation","display_name":"grammatical transformation","score":0.5099999904632568},{"id":"https://openalex.org/keywords/tense-and-aspect","display_name":"tense and aspect","score":0.5559999942779541},{"id":"https://openalex.org/keywords/grammatical-voice","display_name":"grammatical voice","score":0.5860000252723694},{"id":"https://openalex.org/keywords/low-rank-adaptation","display_name":"low-rank adaptation","score":0.7070000171661377},{"id":"https://openalex.org/keywords/few-shot-prompting","display_name":"few-shot prompting","score":0.7360000014305115},{"id":"https://openalex.org/keywords/zero-shot-prompting","display_name":"zero-shot prompting","score":0.8199999928474426},{"id":"https://openalex.org/keywords/llama-3-2","display_name":"Llama 3.2","score":0.7770000100135803},{"id":"https://openalex.org/keywords/endangered-languages","display_name":"endangered languages","score":0.7570000290870667},{"id":"https://openalex.org/keywords/language-preservation","display_name":"language preservation","score":0.6809999942779541},{"id":"https://openalex.org/keywords/language-teaching","display_name":"language teaching","score":0.5270000100135803}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7641327381134033},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7348160743713379},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7037370204925537},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.633212685585022},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5718424916267395},{"id":"https://openalex.org/C204241405","wikidata":"https://www.wikidata.org/wiki/Q461499","display_name":"Transformation (genetics)","level":3,"score":0.5622797608375549},{"id":"https://openalex.org/C55958113","wikidata":"https://www.wikidata.org/wiki/Q169480","display_name":"Indigenous","level":2,"score":0.4664287865161896},{"id":"https://openalex.org/C2781370049","wikidata":"https://www.wikidata.org/wiki/Q645304","display_name":"Indigenous language","level":3,"score":0.4442398250102997},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.4375988841056824},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.054474055767059326},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"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/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.americasnlp-1.14","doi":"https://doi.org/10.18653/v1/2025.americasnlp-1.14","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.americasnlp-1.14","pdf_url":"https://aclanthology.org/2025.americasnlp-1.14.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-1.14","doi":"https://doi.org/10.18653/v1/2025.americasnlp-1.14","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.americasnlp-1.14","pdf_url":"https://aclanthology.org/2025.americasnlp-1.14.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":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4411112993.pdf","grobid_xml":"https://content.openalex.org/works/W4411112993.grobid-xml"},"referenced_works_count":4,"referenced_works":["https://openalex.org/W2948618784","https://openalex.org/W4226155321","https://openalex.org/W4285077564","https://openalex.org/W4322718191"],"related_works":["https://openalex.org/W4411113179","https://openalex.org/W4411113082","https://openalex.org/W4401042315","https://openalex.org/W3156371424","https://openalex.org/W4402466742","https://openalex.org/W4401043064","https://openalex.org/W4411113312","https://openalex.org/W4311192353","https://openalex.org/W4411113399","https://openalex.org/W4385565067"],"abstract_inverted_index":{"Indigenous":[0,35,59],"languages":[1,131,196],"face":[2],"significant":[3],"challenges":[4],"due":[5],"to":[6,54,63,99,113],"their":[7,15],"endangered":[8],"status":[9],"and":[10,41,82,93,96,108,135,156,172,197],"limited":[11],"resources":[12],"which":[13],"makes":[14],"integration":[16],"into":[17],"NLP":[18,192],"systems":[19],"difficult.This":[20],"study":[21],"investigates":[22],"the":[23,43,46,121,185],"use":[24],"of":[25,149,187],"Large":[26],"Language":[27],"Models":[28],"(LLMs)":[29],"for":[30,151,154,158,167,170,174,194],"sentence":[31,56,103,181],"transformation":[32,91],"tasks":[33],"in":[34,58,77,102,140,160,179],"languages,":[36],"focusing":[37],"on":[38,71],"Bribri,":[39,152,168],"Guarani,":[40,155,171],"Maya.Here,":[42],"dataset":[44],"from":[45],"AmericasNLP":[47],"2025":[48],"Shared":[49],"Task":[50],"2":[51],"is":[52,62],"used":[53],"explore":[55],"transformations":[57],"languages.The":[60],"goal":[61],"create":[64],"educational":[65],"tools":[66,193],"by":[67],"modifying":[68],"sentences":[69],"based":[70],"linguistic":[72,200],"instructions,":[73],"such":[74],"as":[75],"changes":[76],"tense,":[78],"aspect,":[79],"voice,":[80],"person,":[81],"other":[83],"grammatical":[84],"features.The":[85],"methodology":[86],"involves":[87],"preprocessing":[88],"data,":[89],"simplifying":[90],"tags,":[92],"designing":[94],"zero-shot":[95],"few-shot":[97,141],"prompts":[98],"guide":[100],"LLMs":[101,188],"rewriting.Fine-tuning":[104],"techniques":[105],"like":[106],"LoRA":[107],"Bits-and-Bytes":[109],"quantization":[110],"were":[111],"employed":[112],"optimize":[114],"model":[115,145],"performance":[116,128],"while":[117],"reducing":[118],"computational":[119],"costs.Among":[120],"tested":[122],"models,":[123],"Llama":[124,143],"3.2(3B-Instruct)":[125],"demonstrated":[126],"superior":[127],"across":[129],"all":[130],"with":[132],"high":[133],"BLEU":[134,147],"ChrF++":[136,163],"scores,":[137],"particularly":[138],"excelling":[139],"settings.The":[142],"3.2":[144],"achieved":[146],"scores":[148,164],"19.51":[150],"13.67":[153],"55.86":[157],"Maya":[159],"test":[161],"settings.Additionally,":[162],"reached":[165],"50.29":[166],"58.55":[169],"80.12":[173],"Maya,":[175],"showcasing":[176],"its":[177],"effectiveness":[178],"handling":[180],"transformation.These":[182],"results":[183],"highlight":[184],"potential":[186],"that":[189],"can":[190],"improve":[191],"indigenous":[195],"help":[198],"preserve":[199],"diversity.":[201]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2025-10-10T00:00:00"}
