{"id":"https://openalex.org/W7130345092","doi":"https://doi.org/10.1109/o-cocosda68185.2025.11384905","title":"LAFAEK-Corpus-1M+: A Large-Scale Tetun Corpus to Build a Low-Resourced LLM for Speech and Text Processing","display_name":"LAFAEK-Corpus-1M+: A Large-Scale Tetun Corpus to Build a Low-Resourced LLM for Speech and Text Processing","publication_year":2025,"publication_date":"2025-11-12","ids":{"openalex":"https://openalex.org/W7130345092","doi":"https://doi.org/10.1109/o-cocosda68185.2025.11384905"},"language":null,"primary_location":{"id":"doi:10.1109/o-cocosda68185.2025.11384905","is_oa":false,"landing_page_url":"https://doi.org/10.1109/o-cocosda68185.2025.11384905","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 28th Conference of the Oriental COCOSDA International Committee for the Co-ordination and Standardisation of Speech Databases and Assessment Techniques (O-COCOSDA)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102253560","display_name":"Yuichi Nishida","orcid":null},"institutions":[{"id":"https://openalex.org/I42405503","display_name":"Gifu University","ror":"https://ror.org/024exxj48","country_code":"JP","type":"education","lineage":["https://openalex.org/I42405503"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yuichi Nishida","raw_affiliation_strings":["Gifu University, Graduate School of Engineering,Gifu,Japan,501-1193"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Gifu University, Graduate School of Engineering,Gifu,Japan,501-1193","institution_ids":["https://openalex.org/I42405503"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101266074","display_name":"Yuto Kuroda","orcid":null},"institutions":[{"id":"https://openalex.org/I42405503","display_name":"Gifu University","ror":"https://ror.org/024exxj48","country_code":"JP","type":"education","lineage":["https://openalex.org/I42405503"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yuto Kuroda","raw_affiliation_strings":["Gifu University, Graduate School of Engineering,Gifu,Japan,501-1193"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Gifu University, Graduate School of Engineering,Gifu,Japan,501-1193","institution_ids":["https://openalex.org/I42405503"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5011699677","display_name":"Satoshi Tamura","orcid":"https://orcid.org/0000-0003-2898-2686"},"institutions":[{"id":"https://openalex.org/I42405503","display_name":"Gifu University","ror":"https://ror.org/024exxj48","country_code":"JP","type":"education","lineage":["https://openalex.org/I42405503"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Satoshi Tamura","raw_affiliation_strings":["Gifu University, Graduate School of Engineering,Gifu,Japan,501-1193"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Gifu University, Graduate School of Engineering,Gifu,Japan,501-1193","institution_ids":["https://openalex.org/I42405503"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"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":0.8160127,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.7441999912261963,"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":0.7441999912261963,"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":0.05299999937415123,"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/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.032600000500679016,"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/focus","display_name":"Focus (optics)","score":0.6658999919891357},{"id":"https://openalex.org/keywords/text-corpus","display_name":"Text corpus","score":0.6492999792098999},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.5867999792098999},{"id":"https://openalex.org/keywords/corpus-linguistics","display_name":"Corpus linguistics","score":0.45489999651908875},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.42590001225471497},{"id":"https://openalex.org/keywords/text-processing","display_name":"Text processing","score":0.4147000014781952},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.40880000591278076},{"id":"https://openalex.org/keywords/speech-translation","display_name":"Speech translation","score":0.3781999945640564}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8385000228881836},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7626000046730042},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6718999743461609},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.6658999919891357},{"id":"https://openalex.org/C2474386","wikidata":"https://www.wikidata.org/wiki/Q461183","display_name":"Text corpus","level":2,"score":0.6492999792098999},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.5867999792098999},{"id":"https://openalex.org/C532629269","wikidata":"https://www.wikidata.org/wiki/Q865083","display_name":"Corpus linguistics","level":2,"score":0.45489999651908875},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.42590001225471497},{"id":"https://openalex.org/C2779500292","wikidata":"https://www.wikidata.org/wiki/Q14802672","display_name":"Text processing","level":2,"score":0.4147000014781952},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.40880000591278076},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.40149998664855957},{"id":"https://openalex.org/C2780366754","wikidata":"https://www.wikidata.org/wiki/Q7494857","display_name":"Speech translation","level":3,"score":0.3781999945640564},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.366100013256073},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.36320000886917114},{"id":"https://openalex.org/C129792486","wikidata":"https://www.wikidata.org/wiki/Q1050419","display_name":"Language identification","level":3,"score":0.32919999957084656},{"id":"https://openalex.org/C155092808","wikidata":"https://www.wikidata.org/wiki/Q182557","display_name":"Computational linguistics","level":2,"score":0.3138999938964844},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.28529998660087585},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.28209999203681946},{"id":"https://openalex.org/C83479923","wikidata":"https://www.wikidata.org/wiki/Q2063748","display_name":"Universal Networking Language","level":4,"score":0.2799000144004822},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.27480000257492065},{"id":"https://openalex.org/C64249296","wikidata":"https://www.wikidata.org/wiki/Q5250411","display_name":"Deep linguistic processing","level":2,"score":0.2727000117301941},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.25929999351501465},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.25870001316070557},{"id":"https://openalex.org/C2985367798","wikidata":"https://www.wikidata.org/wiki/Q1346592","display_name":"Parallel corpora","level":3,"score":0.251800000667572}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/o-cocosda68185.2025.11384905","is_oa":false,"landing_page_url":"https://doi.org/10.1109/o-cocosda68185.2025.11384905","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 28th Conference of the Oriental COCOSDA International Committee for the Co-ordination and Standardisation of Speech Databases and Assessment Techniques (O-COCOSDA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.8049867749214172}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"This":[0],"paper":[1],"introduces":[2],"a":[3,50,54,74,82],"Tetun":[4,55,62,83],"text":[5,51],"corpus":[6,52,79,108],"Lafaek-Corpus-1M+.":[7],"A":[8],"Large":[9],"Language":[10],"Model":[11],"(LLM)":[12],"has":[13],"attracted":[14],"full":[15],"attention":[16],"in":[17],"natural":[18],"language":[19,46],"processing":[20],"and":[21,48,103],"speech":[22],"processing.":[23],"To":[24],"build":[25,81],"an":[26],"LLM,":[27],"huge":[28],"corpora":[29],"are":[30],"basically":[31],"needed,":[32],"however,":[33],"it":[34],"is":[35,91,109],"quite":[36],"hard":[37],"for":[38,53],"low-resourced":[39],"languages.":[40],"We":[41,57,85],"focus":[42],"on":[43],"one":[44],"Asian":[45],"Tetun,":[47],"make":[49],"LLM.":[56,84],"collect":[58],"more":[59],"than":[60,99],"million":[61],"sentences":[63],"from":[64],"various":[65],"resources.":[66],"After":[67],"that,":[68],"we":[69],"applied":[70],"continual":[71],"pre-training":[72],"to":[73,80],"Llama-3.1":[75],"model":[76],"using":[77],"our":[78,94,107],"conducted":[86],"machine":[87],"translation":[88],"experiments.":[89],"It":[90],"found":[92],"that":[93],"LLM":[95],"achieved":[96],"better":[97],"performance":[98],"the":[100,104],"original":[101],"model,":[102],"effectiveness":[105],"of":[106],"clarified.":[110]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-02-19T00:00:00"}