{"id":"https://openalex.org/W4387620809","doi":"https://doi.org/10.1109/opcs59592.2023.10275765","title":"Generative Pre-Trained Transformer for Kazakh Text Generation Tasks","display_name":"Generative Pre-Trained Transformer for Kazakh Text Generation Tasks","publication_year":2023,"publication_date":"2023-08-14","ids":{"openalex":"https://openalex.org/W4387620809","doi":"https://doi.org/10.1109/opcs59592.2023.10275765"},"language":"en","primary_location":{"id":"doi:10.1109/opcs59592.2023.10275765","doi":"https://doi.org/10.1109/opcs59592.2023.10275765","is_oa":false,"landing_page_url":"https://doi.org/10.1109/opcs59592.2023.10275765","pdf_url":null,"source":{"id":"https://openalex.org/S7407106663","display_name":"International Asian School-Seminar Optimization Problems of Complex Systems (OPCS)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 19th International Asian School-Seminar on Optimization Problems of Complex Systems (OPCS)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"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/A5011719526","display_name":"Gulmira Tolegen","orcid":"https://orcid.org/0000-0001-8467-3699","observed_orcids":["https://orcid.org/0000-0001-8467-3699"]},"institutions":[{"id":"https://openalex.org/I4210135055","display_name":"Institute of Information and Computational Technologies","ror":"https://ror.org/03v6e0k54","country_code":"KZ","type":"facility","lineage":["https://openalex.org/I4210135055"]}],"countries":["KZ"],"is_corresponding":false,"raw_author_name":"Gulmira Tolegen","raw_affiliation_strings":["Institute of Information and Computational Technologies, Almaty, Kazakhstan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Information and Computational Technologies, Almaty, Kazakhstan","institution_ids":["https://openalex.org/I4210135055"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002964869","display_name":"Alymzhan Toleu","orcid":"https://orcid.org/0000-0001-9246-319X","observed_orcids":["https://orcid.org/0000-0001-9246-319X"]},"institutions":[{"id":"https://openalex.org/I4210135055","display_name":"Institute of Information and Computational Technologies","ror":"https://ror.org/03v6e0k54","country_code":"KZ","type":"facility","lineage":["https://openalex.org/I4210135055"]}],"countries":["KZ"],"is_corresponding":false,"raw_author_name":"Alymzhan Toleu","raw_affiliation_strings":["Institute of Information and Computational Technologies, Almaty, Kazakhstan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Information and Computational Technologies, Almaty, Kazakhstan","institution_ids":["https://openalex.org/I4210135055"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031261567","display_name":"Rustam Mussabayev","orcid":"https://orcid.org/0000-0001-7283-5144","observed_orcids":["https://orcid.org/0000-0001-7283-5144"]},"institutions":[{"id":"https://openalex.org/I4210135055","display_name":"Institute of Information and Computational Technologies","ror":"https://ror.org/03v6e0k54","country_code":"KZ","type":"facility","lineage":["https://openalex.org/I4210135055"]}],"countries":["KZ"],"is_corresponding":false,"raw_author_name":"Rustam Mussabayev","raw_affiliation_strings":["Institute of Information and Computational Technologies, Almaty, Kazakhstan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Information and Computational Technologies, Almaty, Kazakhstan","institution_ids":["https://openalex.org/I4210135055"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011502758","display_name":"\u0411\u0430\u0433\u0430\u0448\u0430\u0440 \u0416\u0443\u043c\u0430\u0436\u0430\u043d\u043e\u0432","orcid":"https://orcid.org/0000-0002-5035-9076","observed_orcids":["https://orcid.org/0000-0002-5035-9076"]},"institutions":[{"id":"https://openalex.org/I4210135055","display_name":"Institute of Information and Computational Technologies","ror":"https://ror.org/03v6e0k54","country_code":"KZ","type":"facility","lineage":["https://openalex.org/I4210135055"]}],"countries":["KZ"],"is_corresponding":false,"raw_author_name":"Bagashar Zhumazhanov","raw_affiliation_strings":["Institute of Information and Computational Technologies, Almaty, Kazakhstan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Information and Computational Technologies, Almaty, Kazakhstan","institution_ids":["https://openalex.org/I4210135055"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5062407577","display_name":"Gulzat Z. Ziyatbekova","orcid":"https://orcid.org/0000-0002-9290-6074","observed_orcids":["https://orcid.org/0000-0002-9290-6074"]},"institutions":[{"id":"https://openalex.org/I185571130","display_name":"Al-Farabi Kazakh National University","ror":"https://ror.org/03q0vrn42","country_code":"KZ","type":"education","lineage":["https://openalex.org/I185571130"]}],"countries":["KZ"],"is_corresponding":false,"raw_author_name":"Gulzat Ziyatbekova","raw_affiliation_strings":["Al-Farabi Kazakh National University, Almaty, Kazakhstan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Al-Farabi Kazakh National University, Almaty, Kazakhstan","institution_ids":["https://openalex.org/I185571130"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.5524,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.6741887,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"114","last_page":"118"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.8945000171661377,"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/T10028","display_name":"Topic Modeling","score":0.8945000171661377,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.09839999675750732,"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":0.0032999999821186066,"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/kazakh-language","display_name":"Kazakh language","score":0.972000002861023},{"id":"https://openalex.org/keywords/generative-pre-trained-transformer","display_name":"generative pre-trained transformer","score":0.7689999938011169},{"id":"https://openalex.org/keywords/low-resource-languages","display_name":"low-resource languages","score":0.8880000114440918},{"id":"https://openalex.org/keywords/morphologically-complex-languages","display_name":"morphologically complex languages","score":0.9020000100135803},{"id":"https://openalex.org/keywords/question-answering","display_name":"question answering","score":0.6729999780654907},{"id":"https://openalex.org/keywords/cross-linguistic-comparison","display_name":"cross-linguistic comparison","score":0.8539999723434448},{"id":"https://openalex.org/keywords/pre-trained-language-models","display_name":"pre-trained language models","score":0.6570000052452087},{"id":"https://openalex.org/keywords/russian-language","display_name":"Russian language","score":0.6809999942779541}],"concepts":[{"id":"https://openalex.org/C2781297163","wikidata":"https://www.wikidata.org/wiki/Q9252","display_name":"Kazakh","level":2,"score":0.9763211607933044},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8214209079742432},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6783477663993835},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6607222557067871},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.6454252600669861},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6066679954528809},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5113153457641602},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.48651355504989624},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.4666903614997864},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.2189072072505951},{"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/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","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},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/opcs59592.2023.10275765","doi":"https://doi.org/10.1109/opcs59592.2023.10275765","is_oa":false,"landing_page_url":"https://doi.org/10.1109/opcs59592.2023.10275765","pdf_url":null,"source":{"id":"https://openalex.org/S7407106663","display_name":"International Asian School-Seminar Optimization Problems of Complex Systems (OPCS)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 19th International Asian School-Seminar on Optimization Problems of Complex Systems (OPCS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W2626778328","https://openalex.org/W2741586102","https://openalex.org/W2896457183","https://openalex.org/W2963341956","https://openalex.org/W2982399380","https://openalex.org/W3011574394","https://openalex.org/W3030163527","https://openalex.org/W3106719394","https://openalex.org/W3205068155","https://openalex.org/W4224308101","https://openalex.org/W4226278401","https://openalex.org/W4226399820","https://openalex.org/W4283026156","https://openalex.org/W4308095351","https://openalex.org/W4308760226","https://openalex.org/W4320005767","https://openalex.org/W4322718191","https://openalex.org/W4385570322","https://openalex.org/W4391215636"],"related_works":["https://openalex.org/W7140185546","https://openalex.org/W4394618785","https://openalex.org/W7117773532","https://openalex.org/W4415721977","https://openalex.org/W4403689071","https://openalex.org/W7221942935","https://openalex.org/W4401610852","https://openalex.org/W4312288006","https://openalex.org/W4402683452","https://openalex.org/W7155510507"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"an":[3],"empirical":[4],"study":[5],"evaluating":[6],"text":[7,41,138,154],"generation":[8,66],"models":[9],"for":[10,34,87,113,121,142,172,176],"the":[11,35,46,81,101,122,131,173],"low-resource":[12,88,102],"and":[13,73,109,118,158,178],"morphologically":[14],"complex":[15],"Kazakh":[16,36,91,105,137,153,177],"language.":[17],"In":[18],"this":[19,143],"study,":[20],"we":[21,28,44],"leveraged":[22],"a":[23,30,39,50,63,149,163],"transformer-based":[24],"neural":[25],"architecture.":[26],"Initially,":[27],"trained":[29],"large":[31,150,164],"language":[32,37,57,165],"model":[33,48,58,112],"using":[38,49],"substantial":[40],"corpus.":[42],"Then,":[43],"fine-tuned":[45],"base":[47],"specialized":[51],"question-answering":[52,174],"dataset.":[53],"The":[54,75,95],"proposed":[55],"pretrained":[56],"(PLM)":[59],"was":[60,125,128,159],"evaluated":[61],"on":[62],"conversation":[64],"response":[65],"task,":[67],"investigating":[68],"its":[69,110,119],"performance":[70,120],"across":[71],"domains":[72,157],"languages.":[74,180],"findings":[76,97],"of":[77,83,104,146,152],"cross-lingual":[78],"comparison":[79],"underlines":[80],"challenges":[82],"achieving":[84],"good":[85],"results":[86],"languages":[89],"like":[90],"with":[92],"current":[93],"solutions.":[94],"experimental":[96],"revealed":[98],"that":[99],"despite":[100],"characteristics":[103],"language,":[106],"Kazakh's":[107],"PLMs":[108],"fin-tuned":[111],"question":[114],"answering":[115],"were":[116,140,169],"obtained":[117],"BLEU":[123],"score":[124],"8.5%,":[126],"which":[127],"better":[129],"than":[130],"random":[132],"guess":[133],"4.01%.":[134],"Additionally,":[135],"Two":[136],"corpora":[139],"collected":[141,171],"work.":[144],"One":[145],"datasets":[147,168],"comprised":[148],"collection":[151],"from":[155],"different":[156],"used":[160],"to":[161],"train":[162],"model.":[166],"Second":[167],"specifically":[170],"task":[175],"Russian":[179]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3}],"updated_date":"2026-10-30T12:39:25.321706","created_date":"2023-10-14T00:00:00"}