{"id":"https://openalex.org/W7212159293","doi":"https://doi.org/10.3389/fdata.2026.1900836","title":"Fine-tuning multilingual sentence transformers for low-resource skill-concept matching across Kazakh, Russian, and English","display_name":"Fine-tuning multilingual sentence transformers for low-resource skill-concept matching across Kazakh, Russian, and English","publication_year":2026,"publication_date":"2026-09-10","ids":{"openalex":"https://openalex.org/W7212159293","doi":"https://doi.org/10.3389/fdata.2026.1900836","pmid":"https://pubmed.ncbi.nlm.nih.gov/42787011","pmcid":"https://www.ncbi.nlm.nih.gov/pmc/articles/13600825"},"language":"en","primary_location":{"id":"doi:10.3389/fdata.2026.1900836","doi":"https://doi.org/10.3389/fdata.2026.1900836","is_oa":true,"landing_page_url":"https://doi.org/10.3389/fdata.2026.1900836","pdf_url":"https://www.frontiersin.org/journals/big-data/articles/10.3389/fdata.2026.1900836/pdf","source":{"id":"https://openalex.org/S4210201220","display_name":"Frontiers in Big Data","issn_l":"2624-909X","issn":["2624-909X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["cwts-core","doaj","jufo-1","ki-jl-1","norway-1","poland-20","russia-white-list-2","vabb-shw"],"host_organization":"https://openalex.org/P4310320527","host_organization_name":"Frontiers Media","host_organization_lineage":["https://openalex.org/P4310320527"],"host_organization_lineage_names":["Frontiers Media"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Big Data","raw_type":"journal-article"},"volume":null,"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.frontiersin.org/journals/big-data/articles/10.3389/fdata.2026.1900836/pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5011618580","display_name":"Sandugash Serikbayeva","orcid":"https://orcid.org/0000-0003-1729-6875","observed_orcids":["https://orcid.org/0000-0003-1729-6875","https://orcid.org/0000-0002-3627-3321"]},"institutions":[{"id":"https://openalex.org/I10232997","display_name":"L. N. Gumilyov Eurasian National University","ror":"https://ror.org/0242cby63","country_code":"KZ","type":"education","lineage":["https://openalex.org/I10232997"]}],"countries":["KZ"],"is_corresponding":false,"raw_author_name":"Sandugash Serikbayeva","raw_affiliation_strings":["Department of Information Systems, L.N. Gumilyov Eurasian National University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Information Systems, L.N. Gumilyov Eurasian National University","institution_ids":["https://openalex.org/I10232997"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135589855","display_name":"Madina Sambetbayeva","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I10232997","display_name":"L. N. Gumilyov Eurasian National University","ror":"https://ror.org/0242cby63","country_code":"KZ","type":"education","lineage":["https://openalex.org/I10232997"]}],"countries":["KZ"],"is_corresponding":true,"raw_author_name":"Madina Sambetbayeva","raw_affiliation_strings":["Department of Information Systems, L.N. Gumilyov Eurasian National University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Information Systems, L.N. Gumilyov Eurasian National University","institution_ids":["https://openalex.org/I10232997"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5097332785","display_name":"Valiya Ramazanova","orcid":"https://orcid.org/0000-0001-6100-3123","observed_orcids":["https://orcid.org/0000-0001-6100-3123"]},"institutions":[{"id":"https://openalex.org/I10232997","display_name":"L. N. Gumilyov Eurasian National University","ror":"https://ror.org/0242cby63","country_code":"KZ","type":"education","lineage":["https://openalex.org/I10232997"]}],"countries":["KZ"],"is_corresponding":false,"raw_author_name":"Valiya Ramazanova","raw_affiliation_strings":["Department of Information Systems, L.N. Gumilyov Eurasian National University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Information Systems, L.N. Gumilyov Eurasian National University","institution_ids":["https://openalex.org/I10232997"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017370698","display_name":"Aigerim Yerimbetova","orcid":"https://orcid.org/0000-0002-2013-1513","observed_orcids":["https://orcid.org/0000-0002-2013-1513"]},"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":"Aigerim Yerimbetova","raw_affiliation_strings":["Institute of Information and Computational Technologies, CS MSHE RK","School of Engineering and Information Technology, META University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Information and Computational Technologies, CS MSHE RK","institution_ids":["https://openalex.org/I4210135055"]},{"raw_affiliation_string":"School of Engineering and Information Technology, META University","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071285401","display_name":"Zhanar Lamasheva","orcid":"https://orcid.org/0000-0002-9535-2636","observed_orcids":["https://orcid.org/0000-0002-9535-2636"]},"institutions":[{"id":"https://openalex.org/I10232997","display_name":"L. N. Gumilyov Eurasian National University","ror":"https://ror.org/0242cby63","country_code":"KZ","type":"education","lineage":["https://openalex.org/I10232997"]}],"countries":["KZ"],"is_corresponding":false,"raw_author_name":"Zhanar Lamasheva","raw_affiliation_strings":["Department of Information Systems, L.N. Gumilyov Eurasian National University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Information Systems, L.N. Gumilyov Eurasian National University","institution_ids":["https://openalex.org/I10232997"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5121468868","display_name":"Zhanna Sadirmekova","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4405257690","display_name":"Astana IT University","ror":"https://ror.org/05jnvbc31","country_code":"KZ","type":"education","lineage":["https://openalex.org/I4405257690"]}],"countries":["KZ"],"is_corresponding":false,"raw_author_name":"Zhanna Sadirmekova","raw_affiliation_strings":["School of Software Engineering, Astana IT University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Software Engineering, Astana IT University","institution_ids":["https://openalex.org/I4405257690"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050469386","display_name":"A. Batyrkhanov","orcid":"https://orcid.org/0000-0001-6231-3641","observed_orcids":["https://orcid.org/0000-0001-6231-3641","https://orcid.org/0009-0003-1735-282X"]},"institutions":[{"id":"https://openalex.org/I4210154294","display_name":"Khalel Dosmukhamedov Atyrau University","ror":"https://ror.org/05nmhtv58","country_code":"KZ","type":"education","lineage":["https://openalex.org/I4210154294"]}],"countries":["KZ"],"is_corresponding":true,"raw_author_name":"Ardak Batyrkhanov","raw_affiliation_strings":["Department of Software Engineering, Atyrau University named after Kh. Dosmukhamedov"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Software Engineering, Atyrau University named after Kh. Dosmukhamedov","institution_ids":["https://openalex.org/I4210154294"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5086295610","display_name":"Yersaiyn Mailybayev","orcid":"https://orcid.org/0000-0002-1977-3690","observed_orcids":["https://orcid.org/0000-0002-1977-3690"]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Yersaiyn Mailybayev","raw_affiliation_strings":["Department of Computer Technology and Telecommunications, International University of Transportation and Humanities"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Technology and Telecommunications, International University of Transportation and Humanities","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5050469386","https://openalex.org/A5086295610","https://openalex.org/A5135589855"],"corresponding_institution_ids":["https://openalex.org/I10232997","https://openalex.org/I4210154294"],"apc_list":{"value":1175,"currency":"CHF","value_usd":1418},"apc_paid":{"value":1175,"currency":"CHF","value_usd":1418},"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.66184682,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"9","issue":null,"first_page":"1900836","last_page":"1900836"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.986299991607666,"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":0.986299991607666,"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":0.003800000064074993,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.0010000000474974513,"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/multilingual-sentence-embeddings","display_name":"multilingual sentence embeddings","score":0.8519999980926514},{"id":"https://openalex.org/keywords/kazakh-language","display_name":"Kazakh language","score":0.8600000143051147},{"id":"https://openalex.org/keywords/russian-language","display_name":"Russian language","score":0.9700000286102295},{"id":"https://openalex.org/keywords/english-language","display_name":"English language","score":0.5519999861717224},{"id":"https://openalex.org/keywords/low-resource-languages","display_name":"low-resource languages","score":0.8640000224113464},{"id":"https://openalex.org/keywords/code-mixed-text","display_name":"code-mixed text","score":0.6510000228881836},{"id":"https://openalex.org/keywords/cross-lingual-transfer","display_name":"cross-lingual transfer","score":0.8230000138282776},{"id":"https://openalex.org/keywords/paraphrase-corpus","display_name":"paraphrase corpus","score":0.8130000233650208},{"id":"https://openalex.org/keywords/semantic-similarity","display_name":"semantic similarity","score":0.6629999876022339},{"id":"https://openalex.org/keywords/agglomerative-hierarchical-clustering","display_name":"agglomerative clustering","score":0.8119999766349792},{"id":"https://openalex.org/keywords/threshold-calibration","display_name":"threshold calibration","score":0.5139999985694885}],"concepts":[{"id":"https://openalex.org/C2781297163","wikidata":"https://www.wikidata.org/wiki/Q9252","display_name":"Kazakh","level":2,"score":0.8791000247001648},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6621000170707703},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6313999891281128},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5946000218391418},{"id":"https://openalex.org/C2781121862","wikidata":"https://www.wikidata.org/wiki/Q256","display_name":"Turkish","level":2,"score":0.5712000131607056},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.5419999957084656},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5297999978065491},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.4948999881744385},{"id":"https://openalex.org/C2780922921","wikidata":"https://www.wikidata.org/wiki/Q255189","display_name":"Paraphrase","level":2,"score":0.4505999982357025},{"id":"https://openalex.org/C2780762811","wikidata":"https://www.wikidata.org/wiki/Q1784941","display_name":"Cosine similarity","level":3,"score":0.447299987077713},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.40049999952316284},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.39259999990463257},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.3822000026702881},{"id":"https://openalex.org/C55078378","wikidata":"https://www.wikidata.org/wiki/Q1136628","display_name":"Pearson product-moment correlation coefficient","level":2,"score":0.3783999979496002},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.33640000224113464},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32760000228881836},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.31529998779296875},{"id":"https://openalex.org/C92835128","wikidata":"https://www.wikidata.org/wiki/Q1277447","display_name":"Hierarchical clustering","level":3,"score":0.3147999942302704},{"id":"https://openalex.org/C2781122975","wikidata":"https://www.wikidata.org/wiki/Q16928266","display_name":"Semantic feature","level":2,"score":0.29899999499320984},{"id":"https://openalex.org/C142575187","wikidata":"https://www.wikidata.org/wiki/Q3358290","display_name":"Pyramid (geometry)","level":2,"score":0.2946000099182129},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.2912999987602234},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.2883000075817108},{"id":"https://openalex.org/C547195049","wikidata":"https://www.wikidata.org/wiki/Q1725664","display_name":"Terminology","level":2,"score":0.28049999475479126},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.27900001406669617},{"id":"https://openalex.org/C117220453","wikidata":"https://www.wikidata.org/wiki/Q5172842","display_name":"Correlation","level":2,"score":0.2770000100135803},{"id":"https://openalex.org/C49020025","wikidata":"https://www.wikidata.org/wiki/Q1059099","display_name":"Chaining","level":2,"score":0.2757999897003174},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.27230000495910645},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2687000036239624},{"id":"https://openalex.org/C13672336","wikidata":"https://www.wikidata.org/wiki/Q3460803","display_name":"Bag-of-words model","level":2,"score":0.2630999982357025},{"id":"https://openalex.org/C120174047","wikidata":"https://www.wikidata.org/wiki/Q847073","display_name":"Euclidean distance","level":2,"score":0.2590000033378601},{"id":"https://openalex.org/C121934690","wikidata":"https://www.wikidata.org/wiki/Q1084","display_name":"Noun","level":2,"score":0.25209999084472656}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.3389/fdata.2026.1900836","doi":"https://doi.org/10.3389/fdata.2026.1900836","is_oa":true,"landing_page_url":"https://doi.org/10.3389/fdata.2026.1900836","pdf_url":"https://www.frontiersin.org/journals/big-data/articles/10.3389/fdata.2026.1900836/pdf","source":{"id":"https://openalex.org/S4210201220","display_name":"Frontiers in Big Data","issn_l":"2624-909X","issn":["2624-909X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["cwts-core","doaj","jufo-1","ki-jl-1","norway-1","poland-20","russia-white-list-2","vabb-shw"],"host_organization":"https://openalex.org/P4310320527","host_organization_name":"Frontiers Media","host_organization_lineage":["https://openalex.org/P4310320527"],"host_organization_lineage_names":["Frontiers Media"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Big Data","raw_type":"journal-article"},{"id":"pmid:42787011","doi":null,"is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/42787011","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in big data","raw_type":"Journal Article"},{"id":"pmh:oai:pubmedcentral.nih.gov:13600825","doi":null,"is_oa":true,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/42787011/","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Front Big Data","raw_type":"Text"},{"id":"pmh:oai:doaj.org/article:d12f6e8e92c14426bfbaa222baa39f0c","doi":null,"is_oa":false,"landing_page_url":"https://doaj.org/article/d12f6e8e92c14426bfbaa222baa39f0c","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Frontiers in Big Data, Vol 9 (2026)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.3389/fdata.2026.1900836","doi":"https://doi.org/10.3389/fdata.2026.1900836","is_oa":true,"landing_page_url":"https://doi.org/10.3389/fdata.2026.1900836","pdf_url":"https://www.frontiersin.org/journals/big-data/articles/10.3389/fdata.2026.1900836/pdf","source":{"id":"https://openalex.org/S4210201220","display_name":"Frontiers in Big Data","issn_l":"2624-909X","issn":["2624-909X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["cwts-core","doaj","jufo-1","ki-jl-1","norway-1","poland-20","russia-white-list-2","vabb-shw"],"host_organization":"https://openalex.org/P4310320527","host_organization_name":"Frontiers Media","host_organization_lineage":["https://openalex.org/P4310320527"],"host_organization_lineage_names":["Frontiers Media"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Big Data","raw_type":"journal-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7212159293.pdf","grobid_xml":"https://content.openalex.org/works/W7212159293.grobid-xml"},"referenced_works_count":31,"referenced_works":["https://openalex.org/W151377110","https://openalex.org/W1614298861","https://openalex.org/W1987971958","https://openalex.org/W2250539671","https://openalex.org/W2252174795","https://openalex.org/W2462305634","https://openalex.org/W2611029872","https://openalex.org/W2739351760","https://openalex.org/W2795038878","https://openalex.org/W2884159461","https://openalex.org/W2905749056","https://openalex.org/W2952638691","https://openalex.org/W2963341956","https://openalex.org/W2970641574","https://openalex.org/W2970854433","https://openalex.org/W2983040767","https://openalex.org/W3017311573","https://openalex.org/W3017604292","https://openalex.org/W3039695075","https://openalex.org/W3117329469","https://openalex.org/W3117375542","https://openalex.org/W3196024535","https://openalex.org/W3199275090","https://openalex.org/W3216501378","https://openalex.org/W4221152574","https://openalex.org/W4225106321","https://openalex.org/W4310923309","https://openalex.org/W4384299914","https://openalex.org/W4385681674","https://openalex.org/W4402670856","https://openalex.org/W4404416750"],"related_works":["https://openalex.org/W7204196117","https://openalex.org/W7203744576","https://openalex.org/W7167494496","https://openalex.org/W7169842386","https://openalex.org/W7172102927","https://openalex.org/W7165958500","https://openalex.org/W7171153722","https://openalex.org/W7167603247","https://openalex.org/W7170484999","https://openalex.org/W7203672858"],"abstract_inverted_index":{"Introduction:":[0],"Matching":[1],"short,":[2],"specialized":[3],"skill":[4,54,159],"expressions":[5],"across":[6,59],"English,":[7],"Russian,":[8],"and":[9,56,61,78,100,117,148],"Kazakh":[10,27,79,92,101],"is":[11],"challenging":[12],"because":[13],"general-domain":[14],"multilingual":[15,33],"encoders":[16],"underperform":[17],"on":[18,43],"terse,":[19],"code-mixed,":[20],"domain-specific":[21],"phrases,":[22],"particularly":[23],"in":[24],"the":[25,63],"low-resource":[26],"setting.":[28],"Methods:":[29],"We":[30,52],"fine-tuned":[31],"a":[32,37,44,156],"Sentence":[34],"Transformer":[35],"using":[36],"staged":[38],"Multiple":[39],"Negatives":[40],"Ranking":[41],"objective":[42],"trilingual":[45],"paraphrase":[46],"corpus,":[47],"including":[48],"Russian":[49,77,82],"augmentation":[50],"pairs.":[51],"evaluated":[53],"matching":[55],"semantic":[57],"similarity":[58,80,152],"languages":[60],"assessed":[62],"resulting":[64],"embeddings":[65],"through":[66],"downstream":[67,158],"skill-taxonomy":[68],"clustering.":[69],"Results:":[70],"Fine-tuning":[71],"preserved":[72],"English":[73],"performance":[74],"while":[75,91],"improving":[76],"quality.":[81],"cosine":[83,93],"Pearson":[84,94,103],"correlation":[85],"increased":[86,95],"from":[87,96,104,113,121],"0.8125":[88],"to":[89,98,106,115,123],"0.8221,":[90],"0.5989":[97],"0.6050":[99],"dot-product":[102],"0.4487":[105],"0.4912.":[107],"Agglomerative":[108],"clustering":[109],"improved":[110],"mean":[111],"silhouette":[112],"0.27126":[114],"0.2851":[116],"reduced":[118],"erroneous":[119],"clusters":[120],"19.74%":[122],"13.97%.":[124],"Discussion:":[125],"The":[126],"results":[127],"provide":[128],"evidence":[129],"consistent":[130],"with":[131],"cross-lingual":[132],"transfer":[133],"as":[134],"an":[135],"important":[136],"mechanism":[137],"of":[138],"improvement":[139],"for":[140],"Kazakh.":[141],"They":[142],"also":[143],"motivate":[144],"language-specific":[145],"threshold":[146],"calibration":[147],"demonstrate":[149],"that":[150],"intrinsic":[151],"improvements":[153],"translate":[154],"into":[155],"cleaner":[157],"taxonomy.":[160]},"counts_by_year":[],"updated_date":"2026-10-31T12:09:11.096373","created_date":"2026-09-11T00:00:00"}