{"id":"https://openalex.org/W7156058740","doi":"https://doi.org/10.1109/smartindustrycon68821.2026.11492814","title":"Modelling Subword Embeddings of Low-Resource Languages for the Digitalisation of Industry 4.0 Industrial Systems","display_name":"Modelling Subword Embeddings of Low-Resource Languages for the Digitalisation of Industry 4.0 Industrial Systems","publication_year":2026,"publication_date":"2026-03-23","ids":{"openalex":"https://openalex.org/W7156058740","doi":"https://doi.org/10.1109/smartindustrycon68821.2026.11492814"},"language":"en","primary_location":{"id":"doi:10.1109/smartindustrycon68821.2026.11492814","doi":"https://doi.org/10.1109/smartindustrycon68821.2026.11492814","is_oa":false,"landing_page_url":"https://doi.org/10.1109/smartindustrycon68821.2026.11492814","pdf_url":null,"source":{"id":"https://openalex.org/S7407088122","display_name":"International Russian Smart Industry Conference (SmartIndustryCon)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 International Russian Smart Industry Conference (SmartIndustryCon)","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/A5135642748","display_name":"Mullosharaf K. Arabov","orcid":"https://orcid.org/0000-0003-2525-1183","observed_orcids":["https://orcid.org/0000-0003-2525-1183"]},"institutions":[{"id":"https://openalex.org/I21203515","display_name":"Kazan Federal University","ror":"https://ror.org/05256ym39","country_code":"RU","type":"education","lineage":["https://openalex.org/I21203515"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"M. K. Arabov","raw_affiliation_strings":["Kazan Federal University,Institute of Computational Mathematics and Information Technologies,Kazan,Russia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kazan Federal University,Institute of Computational Mathematics and Information Technologies,Kazan,Russia","institution_ids":["https://openalex.org/I21203515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026938498","display_name":"\u0420. \u041d. \u0413\u0430\u0439\u043d\u0443\u043b\u043b\u0438\u043d","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I2800546203","display_name":"Kazan State Technical University named after A. N. Tupolev","ror":"https://ror.org/01b7wh712","country_code":"RU","type":"education","lineage":["https://openalex.org/I2800546203"]},{"id":"https://openalex.org/I54195498","display_name":"Kazan State Technological University","ror":"https://ror.org/03shav252","country_code":"RU","type":"education","lineage":["https://openalex.org/I54195498"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"R. N. Gainullin","raw_affiliation_strings":["Kazan National Research Technological University,Institute of Management, Automation and Information Technologies,Kazan,Russia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kazan National Research Technological University,Institute of Management, Automation and Information Technologies,Kazan,Russia","institution_ids":["https://openalex.org/I2800546203","https://openalex.org/I54195498"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5134696223","display_name":"A. I. Khusaenov","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I21203515","display_name":"Kazan Federal University","ror":"https://ror.org/05256ym39","country_code":"RU","type":"education","lineage":["https://openalex.org/I21203515"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"A. I. Khusaenov","raw_affiliation_strings":["Kazan Federal University,Institute of Computational Mathematics and Information Technologies,Kazan,Russia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kazan Federal University,Institute of Computational Mathematics and Information Technologies,Kazan,Russia","institution_ids":["https://openalex.org/I21203515"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.3224,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.81721497,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"74","last_page":"79"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9110999703407288,"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":0.9110999703407288,"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":0.08340000361204147,"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/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.00039999998989515007,"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/subword-embeddings","display_name":"subword embeddings","score":0.9539999961853027},{"id":"https://openalex.org/keywords/low-resource-languages","display_name":"low-resource languages","score":0.9990000128746033},{"id":"https://openalex.org/keywords/tatar-language","display_name":"Tatar language","score":0.921999990940094},{"id":"https://openalex.org/keywords/agglutinative-languages","display_name":"agglutinative languages","score":0.9559999704360962},{"id":"https://openalex.org/keywords/morphologically-rich-languages","display_name":"morphologically rich languages","score":0.796999990940094},{"id":"https://openalex.org/keywords/fasttext","display_name":"FastText","score":0.8610000014305115},{"id":"https://openalex.org/keywords/word2vec","display_name":"Word2Vec","score":0.9940000176429749},{"id":"https://openalex.org/keywords/character-n-grams","display_name":"character n-grams","score":0.9739999771118164},{"id":"https://openalex.org/keywords/morphological-productivity","display_name":"morphological productivity","score":0.8190000057220459},{"id":"https://openalex.org/keywords/lexical-coverage","display_name":"lexical coverage","score":0.7730000019073486},{"id":"https://openalex.org/keywords/industry-4-0","display_name":"Industry 4.0","score":0.7860000133514404},{"id":"https://openalex.org/keywords/event-logs","display_name":"event logs","score":0.6420000195503235}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5672000050544739},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3878999948501587},{"id":"https://openalex.org/C2777986313","wikidata":"https://www.wikidata.org/wiki/Q1661989","display_name":"Industry 4.0","level":2,"score":0.36079999804496765},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.33219999074935913},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.29330000281333923},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.2646999955177307},{"id":"https://openalex.org/C180198813","wikidata":"https://www.wikidata.org/wiki/Q121182","display_name":"Information system","level":2,"score":0.25940001010894775},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.24709999561309814},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.24480000138282776},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.24459999799728394}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/smartindustrycon68821.2026.11492814","doi":"https://doi.org/10.1109/smartindustrycon68821.2026.11492814","is_oa":false,"landing_page_url":"https://doi.org/10.1109/smartindustrycon68821.2026.11492814","pdf_url":null,"source":{"id":"https://openalex.org/S7407088122","display_name":"International Russian Smart Industry Conference (SmartIndustryCon)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 International Russian Smart Industry Conference (SmartIndustryCon)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9","score":0.4943999946117401}],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320327643","display_name":"Kazan Federal University","ror":"https://ror.org/05256ym39"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W2493916176","https://openalex.org/W2789970834","https://openalex.org/W2991542269","https://openalex.org/W4389723799","https://openalex.org/W4392945187","https://openalex.org/W4394596832","https://openalex.org/W4394994777","https://openalex.org/W4401752816","https://openalex.org/W4405786244","https://openalex.org/W4413821941","https://openalex.org/W4415524053","https://openalex.org/W4415524509","https://openalex.org/W4415524823"],"related_works":["https://openalex.org/W2989457779","https://openalex.org/W7202078769","https://openalex.org/W7135237425","https://openalex.org/W7155203046","https://openalex.org/W4400319345","https://openalex.org/W2888831408","https://openalex.org/W3129408137","https://openalex.org/W3029311208","https://openalex.org/W4408242671","https://openalex.org/W7212291010"],"abstract_inverted_index":{"The":[0,93,152,175],"Industry":[1,62],"4.0":[2,63],"paradigm":[3],"relies":[4],"on":[5,86,161],"intelligent":[6],"methods":[7],"for":[8,45,57,118],"analysing":[9],"textual":[10],"data":[11,31],"such":[12],"as":[13,69],"technical":[14],"documentation,":[15],"event":[16],"logs,":[17],"and":[18,32,78,90,107,111,134,155,166,173,185],"decision":[19],"support":[20],"materials.":[21],"Low-resource":[22],"languages,":[23],"however,":[24],"remain":[25],"underrepresented":[26],"due":[27],"to":[28,105,180,187],"limited":[29],"training":[30],"the":[33,66,162],"absence":[34],"of":[35,76],"high-quality":[36],"language":[37,68],"models,":[38],"a":[39,70],"challenge":[40],"that":[41,96,141],"is":[42,81,116,126,178],"especially":[43],"pronounced":[44],"morphologically":[46],"rich":[47],"agglutinative":[48,190],"languages.":[49,191],"This":[50],"paper":[51],"investigates":[52],"semantic":[53],"vector":[54],"representation":[55],"modelling":[56,87],"low-resource":[58,189],"languages":[59],"in":[60],"an":[61,84,167],"context,":[64],"using":[65,99],"Tatar":[67],"case":[71],"study.":[72],"A":[73,121],"comparative":[74],"analysis":[75],"Word2Vec":[77],"FastText":[79,143],"architectures":[80],"conducted":[82],"with":[83],"emphasis":[85],"morphological":[88],"productivity":[89],"contextual":[91],"relationships.":[92],"results":[94,139],"demonstrate":[95],"subword-based":[97],"approaches":[98],"character":[100],"n-grams":[101],"significantly":[102],"improve":[103],"robustness":[104],"rare":[106],"unseen":[108],"word":[109],"forms":[110],"enhance":[112],"lexical":[113],"coverage,":[114],"which":[115],"crucial":[117],"industrial":[119,182],"applications.":[120],"reproducible":[122],"embedding":[123],"construction":[124],"methodology":[125],"proposed,":[127],"including":[128],"heterogeneous":[129],"corpus":[130],"compilation,":[131],"hyperparameter":[132],"optimisation,":[133],"multi-metric":[135],"quality":[136],"evaluation.":[137],"Experimental":[138],"show":[140],"customised":[142],"models":[144,154],"achieve":[145],"statistically":[146],"significant":[147],"improvements":[148],"over":[149],"baseline":[150],"approaches.":[151],"trained":[153],"source":[156],"code":[157],"are":[158],"publicly":[159],"available":[160],"Hugging":[163],"Face":[164],"platform,":[165],"interactive":[168],"web":[169],"interface":[170],"supports":[171],"testing":[172],"visualisation.":[174],"proposed":[176],"approach":[177],"applicable":[179],"downstream":[181],"NLP":[183],"tasks":[184],"transferable":[186],"other":[188]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-04-28T00:00:00"}
