{"id":"https://openalex.org/W4409892901","doi":"https://doi.org/10.3390/bdcc9050116","title":"Transferring Natural Language Datasets Between Languages Using Large Language Models for Modern Decision Support and Sci-Tech Analytical Systems","display_name":"Transferring Natural Language Datasets Between Languages Using Large Language Models for Modern Decision Support and Sci-Tech Analytical Systems","publication_year":2025,"publication_date":"2025-04-28","ids":{"openalex":"https://openalex.org/W4409892901","doi":"https://doi.org/10.3390/bdcc9050116"},"language":"en","primary_location":{"id":"doi:10.3390/bdcc9050116","is_oa":true,"landing_page_url":"https://doi.org/10.3390/bdcc9050116","pdf_url":"https://www.mdpi.com/2504-2289/9/5/116/pdf?version=1745832800","source":{"id":"https://openalex.org/S4210238752","display_name":"Big Data and Cognitive Computing","issn_l":"2504-2289","issn":["2504-2289"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Big Data and Cognitive Computing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/2504-2289/9/5/116/pdf?version=1745832800","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5036267345","display_name":"Dmitrii Popov","orcid":null},"institutions":[{"id":"https://openalex.org/I126527374","display_name":"Peoples' Friendship University of Russia","ror":"https://ror.org/02dn9h927","country_code":"RU","type":"education","lineage":["https://openalex.org/I126527374"]},{"id":"https://openalex.org/I1313323035","display_name":"Russian Academy of Sciences","ror":"https://ror.org/05qrfxd25","country_code":"RU","type":"government","lineage":["https://openalex.org/I1313323035"]},{"id":"https://openalex.org/I3129897247","display_name":"Russian New University","ror":"https://ror.org/00gj2kk32","country_code":"RU","type":"education","lineage":["https://openalex.org/I3129897247"]},{"id":"https://openalex.org/I4210107660","display_name":"Institute for Information Transmission Problems","ror":"https://ror.org/013w2d378","country_code":"RU","type":"facility","lineage":["https://openalex.org/I4210107660"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Dmitrii Popov","raw_affiliation_strings":["Faculty of Physics and Mathematics and Natural Sciences, RUDN University, Moscow 117198, Russia","Federal Research Center \u201cComputer Science and Control\u201d of the Russian Academy of Sciences (FRC CSC RAS), Moscow 119333, Russia","Institute for Information Transmission Problems of the Russian Academy of Sciences (IITP RAS), Moscow 127051, Russia"],"raw_orcid":"https://orcid.org/0009-0003-5010-6487","affiliations":[{"raw_affiliation_string":"Faculty of Physics and Mathematics and Natural Sciences, RUDN University, Moscow 117198, Russia","institution_ids":["https://openalex.org/I3129897247","https://openalex.org/I126527374"]},{"raw_affiliation_string":"Federal Research Center \u201cComputer Science and Control\u201d of the Russian Academy of Sciences (FRC CSC RAS), Moscow 119333, Russia","institution_ids":["https://openalex.org/I1313323035"]},{"raw_affiliation_string":"Institute for Information Transmission Problems of the Russian Academy of Sciences (IITP RAS), Moscow 127051, Russia","institution_ids":["https://openalex.org/I4210107660"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114494341","display_name":"Egor Terentev","orcid":null},"institutions":[{"id":"https://openalex.org/I126527374","display_name":"Peoples' Friendship University of Russia","ror":"https://ror.org/02dn9h927","country_code":"RU","type":"education","lineage":["https://openalex.org/I126527374"]},{"id":"https://openalex.org/I1313323035","display_name":"Russian Academy of Sciences","ror":"https://ror.org/05qrfxd25","country_code":"RU","type":"government","lineage":["https://openalex.org/I1313323035"]},{"id":"https://openalex.org/I3129897247","display_name":"Russian New University","ror":"https://ror.org/00gj2kk32","country_code":"RU","type":"education","lineage":["https://openalex.org/I3129897247"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Egor Terentev","raw_affiliation_strings":["Faculty of Physics and Mathematics and Natural Sciences, RUDN University, Moscow 117198, Russia","Federal Research Center \u201cComputer Science and Control\u201d of the Russian Academy of Sciences (FRC CSC RAS), Moscow 119333, Russia"],"raw_orcid":"https://orcid.org/0009-0003-6797-9292","affiliations":[{"raw_affiliation_string":"Faculty of Physics and Mathematics and Natural Sciences, RUDN University, Moscow 117198, Russia","institution_ids":["https://openalex.org/I3129897247","https://openalex.org/I126527374"]},{"raw_affiliation_string":"Federal Research Center \u201cComputer Science and Control\u201d of the Russian Academy of Sciences (FRC CSC RAS), Moscow 119333, Russia","institution_ids":["https://openalex.org/I1313323035"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5117363387","display_name":"Danil Serenko","orcid":null},"institutions":[{"id":"https://openalex.org/I126527374","display_name":"Peoples' Friendship University of Russia","ror":"https://ror.org/02dn9h927","country_code":"RU","type":"education","lineage":["https://openalex.org/I126527374"]},{"id":"https://openalex.org/I1313323035","display_name":"Russian Academy of Sciences","ror":"https://ror.org/05qrfxd25","country_code":"RU","type":"government","lineage":["https://openalex.org/I1313323035"]},{"id":"https://openalex.org/I3129897247","display_name":"Russian New University","ror":"https://ror.org/00gj2kk32","country_code":"RU","type":"education","lineage":["https://openalex.org/I3129897247"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Danil Serenko","raw_affiliation_strings":["Faculty of Physics and Mathematics and Natural Sciences, RUDN University, Moscow 117198, Russia","Federal Research Center \u201cComputer Science and Control\u201d of the Russian Academy of Sciences (FRC CSC RAS), Moscow 119333, Russia"],"raw_orcid":"https://orcid.org/0009-0003-6676-7255","affiliations":[{"raw_affiliation_string":"Faculty of Physics and Mathematics and Natural Sciences, RUDN University, Moscow 117198, Russia","institution_ids":["https://openalex.org/I3129897247","https://openalex.org/I126527374"]},{"raw_affiliation_string":"Federal Research Center \u201cComputer Science and Control\u201d of the Russian Academy of Sciences (FRC CSC RAS), Moscow 119333, Russia","institution_ids":["https://openalex.org/I1313323035"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000595079","display_name":"Ilya Sochenkov","orcid":"https://orcid.org/0000-0003-3113-3765"},"institutions":[{"id":"https://openalex.org/I1313323035","display_name":"Russian Academy of Sciences","ror":"https://ror.org/05qrfxd25","country_code":"RU","type":"government","lineage":["https://openalex.org/I1313323035"]},{"id":"https://openalex.org/I4210101868","display_name":"Institute for System Programming","ror":"https://ror.org/017ef8252","country_code":"RU","type":"facility","lineage":["https://openalex.org/I1313323035","https://openalex.org/I4210101868","https://openalex.org/I4210124601"]},{"id":"https://openalex.org/I4210107660","display_name":"Institute for Information Transmission Problems","ror":"https://ror.org/013w2d378","country_code":"RU","type":"facility","lineage":["https://openalex.org/I4210107660"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Ilya Sochenkov","raw_affiliation_strings":["Federal Research Center \u201cComputer Science and Control\u201d of the Russian Academy of Sciences (FRC CSC RAS), Moscow 119333, Russia","Institute for Information Transmission Problems of the Russian Academy of Sciences (IITP RAS), Moscow 127051, Russia","Ivannikov Institute for System Programming of the Russian Academy of Sciences (ISP RAS), Moscow 109004, Russia"],"raw_orcid":"https://orcid.org/0000-0003-3113-3765","affiliations":[{"raw_affiliation_string":"Federal Research Center \u201cComputer Science and Control\u201d of the Russian Academy of Sciences (FRC CSC RAS), Moscow 119333, Russia","institution_ids":["https://openalex.org/I1313323035"]},{"raw_affiliation_string":"Institute for Information Transmission Problems of the Russian Academy of Sciences (IITP RAS), Moscow 127051, Russia","institution_ids":["https://openalex.org/I4210107660"]},{"raw_affiliation_string":"Ivannikov Institute for System Programming of the Russian Academy of Sciences (ISP RAS), Moscow 109004, Russia","institution_ids":["https://openalex.org/I4210101868"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5082093340","display_name":"Igor Buyanov","orcid":"https://orcid.org/0009-0000-6994-151X"},"institutions":[{"id":"https://openalex.org/I1313323035","display_name":"Russian Academy of Sciences","ror":"https://ror.org/05qrfxd25","country_code":"RU","type":"government","lineage":["https://openalex.org/I1313323035"]}],"countries":["RU"],"is_corresponding":true,"raw_author_name":"Igor Buyanov","raw_affiliation_strings":["Federal Research Center \u201cComputer Science and Control\u201d of the Russian Academy of Sciences (FRC CSC RAS), Moscow 119333, Russia"],"raw_orcid":"https://orcid.org/0009-0000-6994-151X","affiliations":[{"raw_affiliation_string":"Federal Research Center \u201cComputer Science and Control\u201d of the Russian Academy of Sciences (FRC CSC RAS), Moscow 119333, Russia","institution_ids":["https://openalex.org/I1313323035"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5082093340"],"corresponding_institution_ids":["https://openalex.org/I1313323035"],"apc_list":{"value":1400,"currency":"CHF","value_usd":1515},"apc_paid":{"value":1400,"currency":"CHF","value_usd":1515},"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.03708617,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"9","issue":"5","first_page":"116","last_page":"116"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9990000128746033,"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":0.9990000128746033,"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":0.996999979019165,"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/T11719","display_name":"Data Quality and Management","score":0.9883999824523926,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.632569432258606},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.5624574422836304},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.45187729597091675},{"id":"https://openalex.org/keywords/natural","display_name":"Natural (archaeology)","score":0.42151787877082825},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41322600841522217},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.12278562784194946}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.632569432258606},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.5624574422836304},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.45187729597091675},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.42151787877082825},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41322600841522217},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.12278562784194946},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.3390/bdcc9050116","is_oa":true,"landing_page_url":"https://doi.org/10.3390/bdcc9050116","pdf_url":"https://www.mdpi.com/2504-2289/9/5/116/pdf?version=1745832800","source":{"id":"https://openalex.org/S4210238752","display_name":"Big Data and Cognitive Computing","issn_l":"2504-2289","issn":["2504-2289"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Big Data and Cognitive Computing","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:c51a7de24d20406396265a550e87d4ca","is_oa":true,"landing_page_url":"https://doaj.org/article/c51a7de24d20406396265a550e87d4ca","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,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Big Data and Cognitive Computing, Vol 9, Iss 5, p 116 (2025)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.3390/bdcc9050116","is_oa":true,"landing_page_url":"https://doi.org/10.3390/bdcc9050116","pdf_url":"https://www.mdpi.com/2504-2289/9/5/116/pdf?version=1745832800","source":{"id":"https://openalex.org/S4210238752","display_name":"Big Data and Cognitive Computing","issn_l":"2504-2289","issn":["2504-2289"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Big Data and Cognitive Computing","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4409892901.pdf","grobid_xml":"https://content.openalex.org/works/W4409892901.grobid-xml"},"referenced_works_count":22,"referenced_works":["https://openalex.org/W6036858","https://openalex.org/W1584778245","https://openalex.org/W2064675550","https://openalex.org/W2164370343","https://openalex.org/W2234028104","https://openalex.org/W2888987968","https://openalex.org/W2964756555","https://openalex.org/W3039695075","https://openalex.org/W3103329136","https://openalex.org/W3113941328","https://openalex.org/W3114114934","https://openalex.org/W3197876970","https://openalex.org/W4386102168","https://openalex.org/W4386432221","https://openalex.org/W4391164242","https://openalex.org/W4392450534","https://openalex.org/W4401042461","https://openalex.org/W4401042514","https://openalex.org/W4401042993","https://openalex.org/W4405552797","https://openalex.org/W6739901393","https://openalex.org/W6898505805"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W3204019825","https://openalex.org/W4226226396","https://openalex.org/W3153750606","https://openalex.org/W4308854837"],"abstract_inverted_index":{"The":[0,105],"decision-making":[1],"process":[2],"to":[3,10,30,40,93,159],"rule":[4],"R&amp;D":[5],"relies":[6],"on":[7,155],"information":[8],"related":[9],"current":[11],"trends":[12],"in":[13,56,64,122],"particular":[14],"research":[15],"areas.":[16],"In":[17,147],"this":[18],"work,":[19],"we":[20,150],"investigated":[21],"how":[22],"one":[23,38],"can":[24],"use":[25],"large":[26],"language":[27,39,116],"models":[28,154],"(LLMs)":[29],"transfer":[31,144],"the":[32,57,78,114,125,130,142,148,152,156],"dataset":[33,110,158],"and":[34,74,127],"its":[35],"annotation":[36,66,91,101,143],"from":[37,82],"another.":[41],"This":[42,85],"is":[43,98,111],"crucial":[44],"since":[45,124],"sharing":[46],"knowledge":[47],"between":[48],"different":[49],"languages":[50],"could":[51],"boost":[52],"certain":[53],"underresourced":[54],"directions":[55],"target":[58],"language,":[59],"saving":[60],"lots":[61],"of":[62,90,107,119,133],"effort":[63],"data":[65],"or":[67],"quick":[68],"prototyping.":[69],"We":[70,137],"experiment":[71],"with":[72],"English":[73],"Russian":[75],"pairs,":[76],"translating":[77],"DEFT":[79],"(Definition":[80],"Extraction":[81],"Texts)":[83],"corpus.":[84],"corpus":[86],"contains":[87],"three":[88],"layers":[89],"dedicated":[92],"term-definition":[94],"pair":[95],"mining,":[96],"which":[97],"a":[99,109,139,161],"rare":[100],"type":[102],"for":[103,113,141],"Russian.":[104],"presence":[106],"such":[108],"beneficial":[112],"natural":[115],"processing":[117],"methods":[118],"trend":[120],"analysis":[121],"science":[123],"terms":[126],"definitions":[128],"are":[129],"basic":[131],"blocks":[132],"any":[134],"scientific":[135],"field.":[136],"provide":[138],"pipeline":[140],"using":[145],"LLMs.":[146],"end,":[149],"train":[151],"BERT-based":[153],"translated":[157],"establish":[160],"baseline.":[162]},"counts_by_year":[],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}
