{"id":"https://openalex.org/W4410056584","doi":"https://doi.org/10.1177/14727978251337995","title":"Improving machine translation accuracy for underrepresented languages in linguistic research using transformer models","display_name":"Improving machine translation accuracy for underrepresented languages in linguistic research using transformer models","publication_year":2025,"publication_date":"2025-05-03","ids":{"openalex":"https://openalex.org/W4410056584","doi":"https://doi.org/10.1177/14727978251337995"},"language":"en","primary_location":{"id":"doi:10.1177/14727978251337995","is_oa":false,"landing_page_url":"https://doi.org/10.1177/14727978251337995","pdf_url":null,"source":{"id":"https://openalex.org/S2765058733","display_name":"Journal of Computational Methods in Sciences and Engineering","issn_l":"1472-7978","issn":["1472-7978","1875-8983"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318577","host_organization_name":"IOS Press","host_organization_lineage":["https://openalex.org/P4310318577"],"host_organization_lineage_names":["IOS Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Computational Methods in Sciences and Engineering","raw_type":"journal-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/A5100405054","display_name":"Yuanyuan Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210131919","display_name":"Xi'an University of Technology","ror":"https://ror.org/038avdt50","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210131919"]},{"id":"https://openalex.org/I180632629","display_name":"Xi'an International Studies University","ror":"https://ror.org/05gcme754","country_code":"CN","type":"education","lineage":["https://openalex.org/I180632629"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yuanyuan Liu","raw_affiliation_strings":["Xi\u2019an Kedagaoxin University","School of International Education and Humanities, Xi\u2019an Kedagaoxin University, Xi\u2019an, China"],"affiliations":[{"raw_affiliation_string":"Xi\u2019an Kedagaoxin University","institution_ids":["https://openalex.org/I4210131919"]},{"raw_affiliation_string":"School of International Education and Humanities, Xi\u2019an Kedagaoxin University, Xi\u2019an, China","institution_ids":["https://openalex.org/I180632629"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5100405054"],"corresponding_institution_ids":["https://openalex.org/I180632629","https://openalex.org/I4210131919"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0463977,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"25","issue":"5","first_page":"4523","last_page":"4538"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9984999895095825,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9904000163078308,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.8351637125015259},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6478191018104553},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6295713186264038},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.5849911570549011},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.498035192489624},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4917307198047638},{"id":"https://openalex.org/keywords/xhosa","display_name":"Xhosa","score":0.44753363728523254},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.4310300350189209},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3320952355861664},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.25094470381736755}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8351637125015259},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6478191018104553},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6295713186264038},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.5849911570549011},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.498035192489624},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4917307198047638},{"id":"https://openalex.org/C2777578687","wikidata":"https://www.wikidata.org/wiki/Q13218","display_name":"Xhosa","level":2,"score":0.44753363728523254},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.4310300350189209},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3320952355861664},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.25094470381736755},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1177/14727978251337995","is_oa":false,"landing_page_url":"https://doi.org/10.1177/14727978251337995","pdf_url":null,"source":{"id":"https://openalex.org/S2765058733","display_name":"Journal of Computational Methods in Sciences and Engineering","issn_l":"1472-7978","issn":["1472-7978","1875-8983"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318577","host_organization_name":"IOS Press","host_organization_lineage":["https://openalex.org/P4310318577"],"host_organization_lineage_names":["IOS Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Computational Methods in Sciences and Engineering","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.5899999737739563,"id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W3035620341","https://openalex.org/W3163832451","https://openalex.org/W3198952510","https://openalex.org/W4212924400","https://openalex.org/W4220862951","https://openalex.org/W4281485039","https://openalex.org/W4283273715","https://openalex.org/W4289593661","https://openalex.org/W4311192353","https://openalex.org/W4384663467","https://openalex.org/W4386099061","https://openalex.org/W4386175605","https://openalex.org/W4386280750","https://openalex.org/W4387004586","https://openalex.org/W4387641387","https://openalex.org/W4387917900","https://openalex.org/W4388116457","https://openalex.org/W4388297110","https://openalex.org/W4389049929","https://openalex.org/W4390421998","https://openalex.org/W4391281457","https://openalex.org/W4391964546","https://openalex.org/W4396659704","https://openalex.org/W4399726444","https://openalex.org/W4401046527","https://openalex.org/W4406171371"],"related_works":["https://openalex.org/W1619002","https://openalex.org/W3176018525","https://openalex.org/W2903533908","https://openalex.org/W2903810591","https://openalex.org/W2963499882","https://openalex.org/W3026554633","https://openalex.org/W2888520903","https://openalex.org/W2890256614","https://openalex.org/W3098873988","https://openalex.org/W2949454572"],"abstract_inverted_index":{"Machine":[0],"translation":[1,36,64,201],"(MT)":[2],"for":[3,34,222,229],"underrepresented":[4,223],"languages,":[5,224],"such":[6],"as":[7],"Xhosa,":[8,121],"presents":[9],"significant":[10,198],"challenges":[11],"due":[12],"to":[13,30,74,115,120,128,135,185],"limited":[14],"linguistic":[15],"resources":[16],"and":[17,62,92,105,110,169,187,241],"the":[18,50,79,85,157,166,182,189,192,203,212,218],"complex":[19],"nature":[20],"of":[21,53,71,87,90,94,140,214],"these":[22],"languages.":[23],"This":[24,47,232],"research":[25],"proposes":[26],"a":[27,69,226],"novel":[28],"approach":[29],"improve":[31],"MT":[32,221],"accuracy":[33],"Xhosa-to-English":[35],"using":[37,156,165,181],"Adaptive":[38],"Gradient":[39],"Boosted":[40],"Bidirectional":[41],"Encoder":[42],"Representations":[43],"from":[44],"Transformers":[45],"(AdaGrad-BBERT).":[46],"method":[48],"combines":[49],"powerful":[51],"capabilities":[52],"BERT":[54,131],"with":[55,150,195],"adaptive":[56],"gradient":[57],"boosting,":[58],"enhancing":[59,230],"contextual":[60],"understanding":[61],"overall":[63],"accuracy.":[65],"The":[66,147,208],"system":[67,210],"integrates":[68],"series":[70],"preprocessing":[72],"steps":[73],"optimize":[75],"model":[76,170,190],"performance.":[77],"Initially,":[78],"dataset":[80],"undergoes":[81],"text":[82],"cleaning,":[83],"including":[84],"removal":[86],"noise,":[88],"normalization":[89],"punctuation,":[91],"correction":[93],"spelling":[95],"inconsistencies.":[96],"Tokenization":[97],"uses":[98],"BERT\u2019s":[99],"word-piece":[100],"model,":[101],"effectively":[102],"handling":[103],"rare":[104],"out-of-vocabulary":[106],"words.":[107],"Part-of-speech":[108],"tagging":[109],"dependency":[111],"parsing":[112],"are":[113,133,179],"applied":[114],"capture":[116],"syntactic":[117],"relationships":[118],"specific":[119],"which":[122],"has":[123],"distinct":[124],"grammatical":[125],"structures":[126],"compared":[127],"English.":[129],"Pre-trained":[130],"embeddings":[132],"employed":[134],"generate":[136],"rich,":[137],"context-sensitive":[138],"representations":[139],"Xhosa":[141],"words,":[142],"ensuring":[143],"more":[144],"accurate":[145],"translations.":[146],"encoder-decoder":[148],"architecture":[149],"an":[151],"attention":[152],"mechanism":[153],"is":[154,163,172],"fine-tuned":[155],"AdaGrad-BBERT":[158,215],"optimization":[159],"technique.":[160],"Translation":[161],"quality":[162],"evaluated":[164],"BLEU":[167],"score,":[168],"performance":[171],"assessed":[173],"over":[174],"multiple":[175],"training":[176],"epochs.":[177],"Simulations":[178],"conducted":[180],"TensorFlow":[183],"framework":[184],"train":[186],"evaluate":[188],"on":[191],"Xhosa-English":[193],"dataset,":[194],"results":[196],"demonstrating":[197],"improvements":[199],"in":[200,216,220,237],"accuracy,":[202],"BLUE":[204],"score":[205],"increased":[206],"0.896.":[207],"proposed":[209],"highlights":[211],"potential":[213],"bridging":[217],"gap":[219],"offering":[225],"scalable":[227],"solution":[228,233],"MT.":[231],"holds":[234],"promising":[235],"applications":[236],"education,":[238],"cross-cultural":[239],"communication,":[240],"digital":[242],"inclusion.":[243]},"counts_by_year":[],"updated_date":"2026-01-08T20:05:33.558190","created_date":"2025-10-10T00:00:00"}