{"id":"https://openalex.org/W7143385366","doi":"https://doi.org/10.25881/18110193_2026_1_64","title":"Fine-tuning the RuBERT language model to improve the accuracy of medical query analysis","display_name":"Fine-tuning the RuBERT language model to improve the accuracy of medical query analysis","publication_year":2026,"publication_date":"2026-03-29","ids":{"openalex":"https://openalex.org/W7143385366","doi":"https://doi.org/10.25881/18110193_2026_1_64"},"language":"en","primary_location":{"id":"doi:10.25881/18110193_2026_1_64","doi":"https://doi.org/10.25881/18110193_2026_1_64","is_oa":true,"landing_page_url":"https://doi.org/10.25881/18110193_2026_1_64","pdf_url":"https://www.vit-j.ru/jour/article/download/313/123","source":{"id":"https://openalex.org/S4210205142","display_name":"Vrach i informacionnye tehnologii","issn_l":"1811-0193","issn":["1811-0193","2413-5208"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["russia-white-list-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Medical Doctor and Information Technologies","raw_type":"journal-article"},"volume":null,"type":"article","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://www.vit-j.ru/jour/article/download/313/123","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5035864988","display_name":"\u0418\u0440\u0438\u043d\u0430 \u041b\u0435\u043e\u043d\u0438\u0434\u043e\u0432\u043d\u0430 \u041a\u0430\u0448\u0438\u0440\u0438\u043d\u0430","orcid":"https://orcid.org/0000-0002-8664-9817","observed_orcids":["https://orcid.org/0000-0002-8664-9817"]},"institutions":[{"id":"https://openalex.org/I4210135186","display_name":"MIREA - Russian Technological University","ror":"https://ror.org/04qrtgy16","country_code":"RU","type":"education","lineage":["https://openalex.org/I4210135186"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"I. L. Kashirina","raw_affiliation_strings":["MIREA \u2013 Russian Technological University"],"raw_orcid":"https://orcid.org/0000-0002-8664-9817","affiliations":[{"raw_affiliation_string":"MIREA \u2013 Russian Technological University","institution_ids":["https://openalex.org/I4210135186"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103750914","display_name":"\u042e \u0412 \u0421\u0442\u0430\u0440\u0438\u0447\u043a\u043e\u0432\u0430","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210135186","display_name":"MIREA - Russian Technological University","ror":"https://ror.org/04qrtgy16","country_code":"RU","type":"education","lineage":["https://openalex.org/I4210135186"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Yu. V. Starichkova","raw_affiliation_strings":["MIREA \u2013 Russian Technological University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MIREA \u2013 Russian Technological University","institution_ids":["https://openalex.org/I4210135186"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5130964833","display_name":"T. K. Le","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210135186","display_name":"MIREA - Russian Technological University","ror":"https://ror.org/04qrtgy16","country_code":"RU","type":"education","lineage":["https://openalex.org/I4210135186"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"T. K. Le","raw_affiliation_strings":["MIREA \u2013 Russian Technological University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MIREA \u2013 Russian Technological University","institution_ids":["https://openalex.org/I4210135186"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210135186"],"apc_list":null,"apc_paid":null,"fwci":1.3951,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.80881696,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":"1","first_page":"64","last_page":"73"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.5590999722480774,"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":0.5590999722480774,"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/T10286","display_name":"Information Retrieval and Search Behavior","score":0.4255000054836273,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T13702","display_name":"Machine Learning in Healthcare","score":0.004900000058114529,"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/rubert","display_name":"RuBERT","score":0.9900000095367432},{"id":"https://openalex.org/keywords/fine-tuning","display_name":"fine-tuning","score":0.7889999747276306},{"id":"https://openalex.org/keywords/semantic-search","display_name":"semantic search","score":0.8769999742507935},{"id":"https://openalex.org/keywords/russian-language","display_name":"Russian language","score":0.6679999828338623},{"id":"https://openalex.org/keywords/dimensionality-reduction","display_name":"dimensionality reduction","score":0.8669999837875366},{"id":"https://openalex.org/keywords/text-embeddings","display_name":"text embeddings","score":0.7300000190734863},{"id":"https://openalex.org/keywords/ndcg","display_name":"NDCG","score":0.7260000109672546}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8011000156402588},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5943999886512756},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5928000211715698},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5730999708175659},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5412999987602234},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4702000021934509},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.4677000045776367},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.45190000534057617},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.44269999861717224},{"id":"https://openalex.org/C192028432","wikidata":"https://www.wikidata.org/wiki/Q845739","display_name":"Query language","level":2,"score":0.4171000123023987},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4133000075817108},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.4009999930858612},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3944000005722046},{"id":"https://openalex.org/C71901391","wikidata":"https://www.wikidata.org/wiki/Q7126699","display_name":"Upload","level":2,"score":0.3937000036239624},{"id":"https://openalex.org/C534262118","wikidata":"https://www.wikidata.org/wiki/Q177719","display_name":"Medical diagnosis","level":2,"score":0.3878999948501587},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3781000077724457},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3643999993801117},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.33230000734329224},{"id":"https://openalex.org/C70518039","wikidata":"https://www.wikidata.org/wiki/Q16000077","display_name":"Dimensionality reduction","level":2,"score":0.3294000029563904},{"id":"https://openalex.org/C99016210","wikidata":"https://www.wikidata.org/wiki/Q5488129","display_name":"Query expansion","level":2,"score":0.32089999318122864},{"id":"https://openalex.org/C111030470","wikidata":"https://www.wikidata.org/wiki/Q1430460","display_name":"Curse of dimensionality","level":2,"score":0.3190999925136566},{"id":"https://openalex.org/C164120249","wikidata":"https://www.wikidata.org/wiki/Q995982","display_name":"Web search query","level":3,"score":0.3167000114917755},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.314300000667572},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.3001999855041504},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.28690001368522644},{"id":"https://openalex.org/C89686163","wikidata":"https://www.wikidata.org/wiki/Q1187982","display_name":"Vector space model","level":2,"score":0.2784999907016754},{"id":"https://openalex.org/C3019150057","wikidata":"https://www.wikidata.org/wiki/Q92779279","display_name":"Medical information","level":2,"score":0.266400009393692},{"id":"https://openalex.org/C77660490","wikidata":"https://www.wikidata.org/wiki/Q244916","display_name":"Intermediate language","level":3,"score":0.26190000772476196},{"id":"https://openalex.org/C2777462759","wikidata":"https://www.wikidata.org/wiki/Q18395344","display_name":"Word embedding","level":3,"score":0.25999999046325684},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.25870001316070557}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.25881/18110193_2026_1_64","doi":"https://doi.org/10.25881/18110193_2026_1_64","is_oa":true,"landing_page_url":"https://doi.org/10.25881/18110193_2026_1_64","pdf_url":"https://www.vit-j.ru/jour/article/download/313/123","source":{"id":"https://openalex.org/S4210205142","display_name":"Vrach i informacionnye tehnologii","issn_l":"1811-0193","issn":["1811-0193","2413-5208"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["russia-white-list-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Medical Doctor and Information Technologies","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.25881/18110193_2026_1_64","doi":"https://doi.org/10.25881/18110193_2026_1_64","is_oa":true,"landing_page_url":"https://doi.org/10.25881/18110193_2026_1_64","pdf_url":"https://www.vit-j.ru/jour/article/download/313/123","source":{"id":"https://openalex.org/S4210205142","display_name":"Vrach i informacionnye tehnologii","issn_l":"1811-0193","issn":["1811-0193","2413-5208"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["russia-white-list-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Medical Doctor and Information Technologies","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/W7143385366.pdf","grobid_xml":"https://content.openalex.org/works/W7143385366.grobid-xml"},"referenced_works_count":14,"referenced_works":["https://openalex.org/W1520352740","https://openalex.org/W2131676173","https://openalex.org/W2626778328","https://openalex.org/W2946676565","https://openalex.org/W2963341956","https://openalex.org/W2970641574","https://openalex.org/W3027879771","https://openalex.org/W3162922479","https://openalex.org/W4221161239","https://openalex.org/W4223547049","https://openalex.org/W4384648639","https://openalex.org/W4411104601","https://openalex.org/W7133214597","https://openalex.org/W7133227460"],"related_works":["https://openalex.org/W4223547049","https://openalex.org/W4221161239","https://openalex.org/W4405663072","https://openalex.org/W7204837561","https://openalex.org/W4401535404","https://openalex.org/W7140294502","https://openalex.org/W7220910191","https://openalex.org/W4315565033","https://openalex.org/W7102329530","https://openalex.org/W4405507526"],"abstract_inverted_index":{"The":[0,47,101,125,139],"aim":[1],"of":[2,10,13,42,76,81,142],"the":[3,8,20,25,30,50,68,74,97,106,112,143],"study":[4,48,107],"was":[5,130],"to":[6,35,64,96,111],"improve":[7],"accuracy":[9],"semantic":[11],"search":[12,91,133],"medical":[14,56,136],"information":[15],"in":[16,89,105,135],"Russian":[17],"by":[18],"finetuning":[19],"RuBERT":[21,99,127],"language":[22,102],"model":[23,103],"on":[24],"specialized":[26],"RuMedDaNet":[27,51],"dataset":[28],"using":[29],"Matryoshka":[31],"Representation":[32],"Learning":[33],"method":[34,129],"create":[36],"compact":[37],"and":[38,45,145],"efficient":[39],"vector":[40,77],"representations":[41,78],"text.":[43],"Materials":[44],"Methods.":[46],"utilized":[49],"dataset,":[52],"which":[53,71],"contains":[54],"Russian-language":[55],"texts.":[57],"Various":[58],"embedding":[59],"training":[60],"techniques":[61],"were":[62],"applied":[63],"optimize":[65],"performance,":[66],"including":[67],"\u201cmatryoshka\u201d":[69],"approach,":[70],"enables":[72],"reducing":[73],"dimensionality":[75],"without":[79],"loss":[80],"quality.":[82],"Results.":[83],"Experiments":[84],"demonstrated":[85],"a":[86],"significant":[87],"improvement":[88],"key":[90],"metrics":[92],"(NDCG,":[93],"MRR)":[94],"compared":[95],"baseline":[98],"model.":[100],"trained":[104],"has":[108],"been":[109],"uploaded":[110],"Hugging":[113],"Face":[114],"platform,":[115],"where":[116],"it":[117],"is":[118],"now":[119],"available":[120],"for":[121,132,147],"open":[122],"use.":[123],"Conclusion.":[124],"proposed":[126],"fine-tuning":[128],"effective":[131],"tasks":[134],"RAG":[137],"systems.":[138],"current":[140],"limitations":[141],"approach":[144],"directions":[146],"further":[148],"research":[149],"are":[150],"discussed.":[151]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2026-03-31T00:00:00"}