{"id":"https://openalex.org/W4405633848","doi":"https://doi.org/10.1109/o-cocosda64382.2024.10800470","title":"Construction of Large Language Models for Taigi and Hakka Using Transfer Learning","display_name":"Construction of Large Language Models for Taigi and Hakka Using Transfer Learning","publication_year":2024,"publication_date":"2024-10-17","ids":{"openalex":"https://openalex.org/W4405633848","doi":"https://doi.org/10.1109/o-cocosda64382.2024.10800470"},"language":"en","primary_location":{"id":"doi:10.1109/o-cocosda64382.2024.10800470","is_oa":false,"landing_page_url":"https://doi.org/10.1109/o-cocosda64382.2024.10800470","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 27th 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/A5045461759","display_name":"Yen\u2010Chun Lai","orcid":"https://orcid.org/0000-0002-4703-5708"},"institutions":[{"id":"https://openalex.org/I148366613","display_name":"National Yang Ming Chiao Tung University","ror":"https://ror.org/00se2k293","country_code":"TW","type":"education","lineage":["https://openalex.org/I148366613"]}],"countries":["TW"],"is_corresponding":true,"raw_author_name":"Yen-Chun Lai","raw_affiliation_strings":["National Yang Ming Chiao Tung University"],"affiliations":[{"raw_affiliation_string":"National Yang Ming Chiao Tung University","institution_ids":["https://openalex.org/I148366613"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102853626","display_name":"Yijun Zheng","orcid":"https://orcid.org/0000-0002-0163-6401"},"institutions":[{"id":"https://openalex.org/I2800704394","display_name":"Copiah-Lincoln Community College","ror":"https://ror.org/02kc2j595","country_code":"US","type":"education","lineage":["https://openalex.org/I2800704394"]},{"id":"https://openalex.org/I4210136767","display_name":"Link Institut (Switzerland)","ror":"https://ror.org/04vhpaz11","country_code":"CH","type":"company","lineage":["https://openalex.org/I4210136767"]}],"countries":["CH","US"],"is_corresponding":false,"raw_author_name":"Yi-Jun Zheng","raw_affiliation_strings":["D-Link Co"],"affiliations":[{"raw_affiliation_string":"D-Link Co","institution_ids":["https://openalex.org/I2800704394","https://openalex.org/I4210136767"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010556270","display_name":"Wen\u2010Han Hsu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wen-Han Hsu","raw_affiliation_strings":["BRONCI Technology Inc.,Taiwan"],"affiliations":[{"raw_affiliation_string":"BRONCI Technology Inc.,Taiwan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101992437","display_name":"Yanming Lin","orcid":"https://orcid.org/0000-0001-9056-7972"},"institutions":[{"id":"https://openalex.org/I148366613","display_name":"National Yang Ming Chiao Tung University","ror":"https://ror.org/00se2k293","country_code":"TW","type":"education","lineage":["https://openalex.org/I148366613"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yan-Ming Lin","raw_affiliation_strings":["National Yang Ming Chiao Tung University"],"affiliations":[{"raw_affiliation_string":"National Yang Ming Chiao Tung University","institution_ids":["https://openalex.org/I148366613"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021183142","display_name":"Cheng-Hsiu Cho","orcid":null},"institutions":[{"id":"https://openalex.org/I148366613","display_name":"National Yang Ming Chiao Tung University","ror":"https://ror.org/00se2k293","country_code":"TW","type":"education","lineage":["https://openalex.org/I148366613"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Cheng-Hsiu Cho","raw_affiliation_strings":["National Yang Ming Chiao Tung University"],"affiliations":[{"raw_affiliation_string":"National Yang Ming Chiao Tung University","institution_ids":["https://openalex.org/I148366613"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Chlh-Chung Kuo","orcid":null},"institutions":[{"id":"https://openalex.org/I148366613","display_name":"National Yang Ming Chiao Tung University","ror":"https://ror.org/00se2k293","country_code":"TW","type":"education","lineage":["https://openalex.org/I148366613"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Chlh-Chung Kuo","raw_affiliation_strings":["National Yang Ming Chiao Tung University"],"affiliations":[{"raw_affiliation_string":"National Yang Ming Chiao Tung University","institution_ids":["https://openalex.org/I148366613"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050297067","display_name":"Chao-Shih Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I148366613","display_name":"National Yang Ming Chiao Tung University","ror":"https://ror.org/00se2k293","country_code":"TW","type":"education","lineage":["https://openalex.org/I148366613"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Chao-Shih Huang","raw_affiliation_strings":["National Yang Ming Chiao Tung University"],"affiliations":[{"raw_affiliation_string":"National Yang Ming Chiao Tung University","institution_ids":["https://openalex.org/I148366613"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5082271172","display_name":"Yuan\u2010Fu Liao","orcid":"https://orcid.org/0000-0003-0191-2178"},"institutions":[{"id":"https://openalex.org/I148366613","display_name":"National Yang Ming Chiao Tung University","ror":"https://ror.org/00se2k293","country_code":"TW","type":"education","lineage":["https://openalex.org/I148366613"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yuan-Fu Liao","raw_affiliation_strings":["National Yang Ming Chiao Tung University"],"affiliations":[{"raw_affiliation_string":"National Yang Ming Chiao Tung University","institution_ids":["https://openalex.org/I148366613"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5045461759"],"corresponding_institution_ids":["https://openalex.org/I148366613"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.21142795,"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":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.7231000065803528,"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":0.7231000065803528,"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/computer-science","display_name":"Computer science","score":0.7329740524291992},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.5650845170021057},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.48768389225006104},{"id":"https://openalex.org/keywords/transfer","display_name":"Transfer (computing)","score":0.43355095386505127},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4156899154186249}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7329740524291992},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.5650845170021057},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.48768389225006104},{"id":"https://openalex.org/C2776175482","wikidata":"https://www.wikidata.org/wiki/Q1195816","display_name":"Transfer (computing)","level":2,"score":0.43355095386505127},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4156899154186249},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/o-cocosda64382.2024.10800470","is_oa":false,"landing_page_url":"https://doi.org/10.1109/o-cocosda64382.2024.10800470","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 27th 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":[{"score":0.5199999809265137,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W1564346437","https://openalex.org/W2948506235","https://openalex.org/W3137010024","https://openalex.org/W3202167223","https://openalex.org/W4324157275","https://openalex.org/W4393252719","https://openalex.org/W4399211775","https://openalex.org/W4399283475","https://openalex.org/W6601894380","https://openalex.org/W6765544429","https://openalex.org/W6863534613"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Taigi":[0,40,77,103,138,184],"(also":[1],"known":[2],"as":[3],"Taiwanese":[4,163],"Hokkien)":[5],"and":[6,41,78,104,119,139,164,185],"Hakka":[7,42,79,105,165],"were":[8],"once":[9],"the":[10,21,49,81,85,89,110,113,132,144,147,176,192],"predominant":[11],"native":[12],"languages":[13],"in":[14,45,137],"Taiwan,":[15],"but":[16],"they":[17],"are":[18],"now":[19],"on":[20,174],"verge":[22],"of":[23,51,65,91,102,116,146,157,181],"extinction.":[24],"To":[25],"address":[26],"this":[27,29],"crisis,":[28],"study":[30],"explores":[31],"how":[32],"to":[33,43,87,108,134],"construct":[34],"large":[35],"language":[36,56,166],"models":[37,62],"(LLMs)":[38],"for":[39,76,128,183,187],"aid":[44],"their":[46],"revitalization":[47],"despite":[48],"scarcity":[50],"linguistic":[52],"resources":[53],"(the":[54],"low-resource":[55],"issue).":[57],"Our":[58],"approach":[59],"leverages":[60],"pre-trained":[61],"from":[63],"LLMs":[64,149,177],"resource-rich":[66],"languages,":[67],"following":[68],"three":[69],"key":[70],"steps:":[71],"(1)":[72],"introducing":[73],"specific":[74],"characters":[75],"into":[80],"LLM's":[82],"tokenizer,":[83],"enabling":[84],"model":[86],"recognize":[88],"orthography":[90],"both":[92],"languages;":[93,118],"(2)":[94],"conducting":[95],"continual":[96],"pre-training":[97],"with":[98,112],"a":[99,151],"small":[100],"amount":[101],"text":[106],"data":[107,124],"familiarize":[109],"LLM":[111,133],"lexical":[114],"choices":[115],"these":[117],"(3)":[120],"generating":[121],"task-specific":[122],"training":[123],"via":[125],"machine":[126],"translation":[127],"instruction":[129],"fine-tuning,":[130],"allowing":[131],"perform":[135],"tasks":[136],"Hakka.":[140],"Finally,":[141],"we":[142],"evaluated":[143],"performance":[145,193],"constructed":[148],"using":[150],"reading":[152],"comprehension":[153],"question":[154],"bank":[155],"(consisting":[156],"1,000":[158],"multiple-choice":[159],"questions)":[160],"developed":[161],"by":[162],"experts.":[167],"The":[168],"experimental":[169],"results":[170],"indicate":[171],"that":[172,191],"based":[173],"LLaMA2-70B,":[175],"achieved":[178],"accuracy":[179],"rates":[180],"85.6%":[182],"87.7%":[186],"Hakka,":[188],"respectively,":[189],"suggesting":[190],"is":[194],"approaching":[195],"human-level":[196],"proficiency.":[197]},"counts_by_year":[],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}
