{"id":"https://openalex.org/W7117773532","doi":"https://doi.org/10.1145/3773274.3774670","title":"Enhancing Question Answering for Low-Resource Languages: The Case of Kazakh Language","display_name":"Enhancing Question Answering for Low-Resource Languages: The Case of Kazakh Language","publication_year":2025,"publication_date":"2025-12-01","ids":{"openalex":"https://openalex.org/W7117773532","doi":"https://doi.org/10.1145/3773274.3774670"},"language":null,"primary_location":{"id":"doi:10.1145/3773274.3774670","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3773274.3774670","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 18th IEEE/ACM International Conference on Utility and Cloud Computing","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/A5082431551","display_name":"Arailym Tleubayeva","orcid":"https://orcid.org/0000-0001-9560-9756"},"institutions":[{"id":"https://openalex.org/I4210141757","display_name":"Astana Medical University","ror":"https://ror.org/038mavt60","country_code":"KZ","type":"education","lineage":["https://openalex.org/I4210141757"]}],"countries":["KZ"],"is_corresponding":false,"raw_author_name":"Arailym Tleubayeva","raw_affiliation_strings":["School of Artificial Intelligence and Data Science, Astana IT University, Astana, Kazakhstan"],"raw_orcid":"https://orcid.org/0000-0001-9560-9756","affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence and Data Science, Astana IT University, Astana, Kazakhstan","institution_ids":["https://openalex.org/I4210141757"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066584563","display_name":"Zhansaya Makhambetova","orcid":null},"institutions":[{"id":"https://openalex.org/I4210141757","display_name":"Astana Medical University","ror":"https://ror.org/038mavt60","country_code":"KZ","type":"education","lineage":["https://openalex.org/I4210141757"]}],"countries":["KZ"],"is_corresponding":false,"raw_author_name":"Zhansaya Makhambetova","raw_affiliation_strings":["School of Creative Industry, Astana IT University, Astana, Kazakhstan"],"raw_orcid":"https://orcid.org/0000-0001-5024-0289","affiliations":[{"raw_affiliation_string":"School of Creative Industry, Astana IT University, Astana, Kazakhstan","institution_ids":["https://openalex.org/I4210141757"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5092706663","display_name":"Aigerim Mansurova","orcid":"https://orcid.org/0009-0003-1978-9574"},"institutions":[{"id":"https://openalex.org/I4210141757","display_name":"Astana Medical University","ror":"https://ror.org/038mavt60","country_code":"KZ","type":"education","lineage":["https://openalex.org/I4210141757"]}],"countries":["KZ"],"is_corresponding":false,"raw_author_name":"Aigerim Mansurova","raw_affiliation_strings":["Big Data and Blockchain Technologies Research and Innovation Center, Astana IT University, Astana, Kazakhstan"],"raw_orcid":"https://orcid.org/0009-0003-1978-9574","affiliations":[{"raw_affiliation_string":"Big Data and Blockchain Technologies Research and Innovation Center, Astana IT University, Astana, Kazakhstan","institution_ids":["https://openalex.org/I4210141757"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5067593236","display_name":"Adai Shomanov","orcid":"https://orcid.org/0000-0001-8253-7474"},"institutions":[{"id":"https://openalex.org/I60559429","display_name":"Nazarbayev University","ror":"https://ror.org/052bx8q98","country_code":"KZ","type":"education","lineage":["https://openalex.org/I60559429"]}],"countries":["KZ"],"is_corresponding":false,"raw_author_name":"Adai Shomanov","raw_affiliation_strings":["Computer Science Department, Nazarbayev University, Astana, Kazakhstan"],"raw_orcid":"https://orcid.org/0000-0001-8253-7474","affiliations":[{"raw_affiliation_string":"Computer Science Department, Nazarbayev University, Astana, Kazakhstan","institution_ids":["https://openalex.org/I60559429"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"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":0.78524797,"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":"3"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.666100025177002,"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":0.666100025177002,"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":0.181099995970726,"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/T13629","display_name":"Text Readability and Simplification","score":0.01979999989271164,"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/question-answering","display_name":"Question answering","score":0.7851999998092651},{"id":"https://openalex.org/keywords/agglutinative-language","display_name":"Agglutinative language","score":0.6241000294685364},{"id":"https://openalex.org/keywords/kazakh","display_name":"Kazakh","score":0.5605000257492065},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.4708000123500824},{"id":"https://openalex.org/keywords/clef","display_name":"Clef","score":0.4480000138282776},{"id":"https://openalex.org/keywords/word-embedding","display_name":"Word embedding","score":0.43790000677108765},{"id":"https://openalex.org/keywords/multilingualism","display_name":"Multilingualism","score":0.413100004196167},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.40450000762939453},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.40119999647140503},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.3774000108242035}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7989000082015991},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.7851999998092651},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6880000233650208},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.626800000667572},{"id":"https://openalex.org/C80875076","wikidata":"https://www.wikidata.org/wiki/Q171263","display_name":"Agglutinative language","level":3,"score":0.6241000294685364},{"id":"https://openalex.org/C2781297163","wikidata":"https://www.wikidata.org/wiki/Q9252","display_name":"Kazakh","level":2,"score":0.5605000257492065},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4745999872684479},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.4708000123500824},{"id":"https://openalex.org/C107763842","wikidata":"https://www.wikidata.org/wiki/Q181040","display_name":"Clef","level":3,"score":0.4480000138282776},{"id":"https://openalex.org/C2777462759","wikidata":"https://www.wikidata.org/wiki/Q18395344","display_name":"Word embedding","level":3,"score":0.43790000677108765},{"id":"https://openalex.org/C2780035574","wikidata":"https://www.wikidata.org/wiki/Q30081","display_name":"Multilingualism","level":2,"score":0.413100004196167},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.40450000762939453},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.40119999647140503},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3774000108242035},{"id":"https://openalex.org/C176982825","wikidata":"https://www.wikidata.org/wiki/Q835922","display_name":"Lexical analysis","level":2,"score":0.3578000068664551},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.3531000018119812},{"id":"https://openalex.org/C2780403423","wikidata":"https://www.wikidata.org/wiki/Q6537700","display_name":"Lexical database","level":3,"score":0.34049999713897705},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.3400999903678894},{"id":"https://openalex.org/C155092808","wikidata":"https://www.wikidata.org/wiki/Q182557","display_name":"Computational linguistics","level":2,"score":0.3264000117778778},{"id":"https://openalex.org/C100660578","wikidata":"https://www.wikidata.org/wiki/Q18733","display_name":"Recall","level":2,"score":0.32580000162124634},{"id":"https://openalex.org/C188338183","wikidata":"https://www.wikidata.org/wiki/Q80735","display_name":"Stop words","level":3,"score":0.32359999418258667},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.3147999942302704},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.3140999972820282},{"id":"https://openalex.org/C117884012","wikidata":"https://www.wikidata.org/wiki/Q94489","display_name":"n-gram","level":3,"score":0.31299999356269836},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.29649999737739563},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.28839999437332153},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.2815000116825104},{"id":"https://openalex.org/C161831844","wikidata":"https://www.wikidata.org/wiki/Q2554325","display_name":"Lemmatisation","level":2,"score":0.274399995803833},{"id":"https://openalex.org/C154775046","wikidata":"https://www.wikidata.org/wiki/Q188","display_name":"German","level":2,"score":0.27250000834465027},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2671000063419342},{"id":"https://openalex.org/C161156560","wikidata":"https://www.wikidata.org/wiki/Q1638872","display_name":"Document retrieval","level":2,"score":0.26579999923706055},{"id":"https://openalex.org/C2779135771","wikidata":"https://www.wikidata.org/wiki/Q403574","display_name":"Named-entity recognition","level":3,"score":0.25380000472068787},{"id":"https://openalex.org/C98501671","wikidata":"https://www.wikidata.org/wiki/Q1948408","display_name":"Text segmentation","level":3,"score":0.2508000135421753}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3773274.3774670","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3773274.3774670","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 18th IEEE/ACM International Conference on Utility and Cloud Computing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.42477527260780334,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"The":[0,127],"Kazakh":[1,117],"language,":[2],"with":[3,71,95],"its":[4],"agglutinative":[5],"morphology":[6],"and":[7,38,50,57,68,78,124,135],"scarce":[8],"annotated":[9],"data,":[10],"presents":[11],"challenges":[12],"for":[13,140],"accurate":[14],"Question":[15],"Answering":[16],"(QA).":[17],"This":[18],"study":[19],"proposes":[20],"a":[21,84,130],"three-stage":[22],"framework":[23,128],"to":[24],"improve":[25],"multilingual":[26,42,112],"QA":[27,43,138],"performance":[28],"in":[29],"low-resource":[30,141],"settings":[31],"through":[32],"model":[33],"adaptation,":[34],"semantic":[35],"representation":[36],"evaluation,":[37],"retrieval":[39,86,121],"optimization.":[40],"First,":[41],"models":[44,63],"(mT5,":[45],"XLM-R,":[46],"mDeBERTa-v3,":[47],"AYA,":[48],"Kaz-RoBERTa,":[49],"KazakhBERTmulti)":[51],"were":[52,64],"fine-tuned":[53],"using":[54],"SentencePiece":[55],"tokenization":[56],"adapter-based":[58],"training.":[59],"Second,":[60],"five":[61],"embedding":[62],"benchmarked":[65],"via":[66],"Domain":[67],"QuestionType":[69],"classification,":[70],"Snowflake-Arctic":[72],"achieving":[73],"the":[74],"highest":[75],"accuracy":[76],"(0.87)":[77],"BGE-M3":[79],"demonstrating":[80],"strong":[81],"robustness.":[82,126],"Finally,":[83],"memory-aware":[85],"mechanism":[87],"was":[88],"implemented":[89],"by":[90],"integrating":[91],"Safe":[92],"Memory":[93],"clustering":[94],"FAISS":[96],"indexing,":[97],"improving":[98],"contextual":[99],"recall":[100],"(R@10":[101],"=":[102],"0.984)":[103],"without":[104],"loss":[105],"of":[106],"precision.":[107],"Results":[108],"show":[109],"that":[110],"adapted":[111],"transformers":[113],"consistently":[114],"outperform":[115],"native":[116],"models,":[118],"while":[119],"enhanced":[120],"strengthens":[122],"grounding":[123],"cross-domain":[125],"provides":[129],"reproducible":[131],"pathway":[132],"toward":[133],"scalable":[134],"linguistically":[136],"inclusive":[137],"systems":[139],"languages.":[142]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-12-31T00:00:00"}