{"id":"https://openalex.org/W7224919656","doi":"https://doi.org/10.1109/ubmk71847.2026.11745341","title":"Building an Open Multi-Author Uzbek Literary Corpus: A Reusable Resource for NLP and Literary Research","display_name":"Building an Open Multi-Author Uzbek Literary Corpus: A Reusable Resource for NLP and Literary Research","publication_year":2026,"publication_date":"2026-09-01","ids":{"openalex":"https://openalex.org/W7224919656","doi":"https://doi.org/10.1109/ubmk71847.2026.11745341"},"language":"en","primary_location":{"id":"doi:10.1109/ubmk71847.2026.11745341","doi":"https://doi.org/10.1109/ubmk71847.2026.11745341","is_oa":true,"landing_page_url":"https://doi.org/10.1109/ubmk71847.2026.11745341","pdf_url":null,"source":{"id":"https://openalex.org/S4306498178","display_name":"International Conference on Computer Science and Engineering (UBMK)","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 11th International Conference on Computer Science and Engineering (UBMK)","raw_type":"proceedings-article"},"parent_works":[],"lineage":["https://openalex.org/W7224919656"],"child_works_count":0,"type":"conference-paper","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1109/ubmk71847.2026.11745341","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5093120375","display_name":"Khamroeva Shahlo Mirdjonovna","orcid":"https://orcid.org/0000-0002-5429-4708","observed_orcids":["https://orcid.org/0000-0002-5429-4708"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Khamroeva Shahlo Mirdjonovna","raw_affiliation_strings":["Tashkent State University of Uzbek Language and Literature"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tashkent State University of Uzbek Language and Literature","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000757756","display_name":"Lolakhon Khamidovna Nigmatova","orcid":"https://orcid.org/0000-0002-8101-6447","observed_orcids":["https://orcid.org/0000-0002-8101-6447"]},"institutions":[{"id":"https://openalex.org/I3131790217","display_name":"Bukhara State University","ror":"https://ror.org/05k4xnj24","country_code":"UZ","type":"education","lineage":["https://openalex.org/I3131790217"]}],"countries":["UZ"],"is_corresponding":false,"raw_author_name":"Nigmatova Lolakhon Khamidovna","raw_affiliation_strings":["Bukhara State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bukhara State University","institution_ids":["https://openalex.org/I3131790217"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088192245","display_name":"Muyassar Kholova","orcid":"https://orcid.org/0000-0002-7604-2958","observed_orcids":["https://orcid.org/0000-0002-7604-2958"]},"institutions":[{"id":"https://openalex.org/I4210159709","display_name":"Termez State University","ror":"https://ror.org/05416zy49","country_code":"UZ","type":"education","lineage":["https://openalex.org/I4210159709"]}],"countries":["UZ"],"is_corresponding":false,"raw_author_name":"Muyassar Kholova","raw_affiliation_strings":["Termez State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Termez State University","institution_ids":["https://openalex.org/I4210159709"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008453894","display_name":"Rustam Abdurasulovich Karimov","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I3131790217","display_name":"Bukhara State University","ror":"https://ror.org/05k4xnj24","country_code":"UZ","type":"education","lineage":["https://openalex.org/I3131790217"]}],"countries":["UZ"],"is_corresponding":false,"raw_author_name":"Karimov Rustam Abdurasulovich","raw_affiliation_strings":["Bukhara State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bukhara State University","institution_ids":["https://openalex.org/I3131790217"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5160218117","display_name":"Abdurayimova Durdona Samat Kizi","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Abdurayimova Durdona Samat Kizi","raw_affiliation_strings":["Tashkent State University of Uzbek Language and Literature"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tashkent State University of Uzbek Language and Literature","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5160169722","display_name":"Bakhodirov Sanjarbek","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4405255639","display_name":"Alisher Navo'i Tashkent State University of Uzbek Language and Literature","ror":"https://ror.org/03870dx82","country_code":"UZ","type":"education","lineage":["https://openalex.org/I4405255639"]}],"countries":["UZ"],"is_corresponding":false,"raw_author_name":"Bakhodirov Sanjarbek","raw_affiliation_strings":["Tashkent State University of Uzbek Language and Lterature"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tashkent State University of Uzbek Language and Lterature","institution_ids":["https://openalex.org/I4405255639"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5160186214","display_name":"Xasanova Lola Adizovna","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4405257638","display_name":"Asia International University","ror":"https://ror.org/05gb5xf93","country_code":"UZ","type":"education","lineage":["https://openalex.org/I4405257638"]}],"countries":["UZ"],"is_corresponding":false,"raw_author_name":"Xasanova Lola Adizovna","raw_affiliation_strings":["Asia International University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Asia International University","institution_ids":["https://openalex.org/I4405257638"]}]}],"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":0.0,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1450","last_page":"1455"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.5770999789237976,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.5770999789237976,"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/T12377","display_name":"Digital Humanities and Scholarship","score":0.4077000021934509,"subfield":{"id":"https://openalex.org/subfields/1208","display_name":"Literature and Literary Theory"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12373","display_name":"Linguistic research and analysis","score":0.0026000000070780516,"subfield":{"id":"https://openalex.org/subfields/1203","display_name":"Language and Linguistics"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/uzbek-language","display_name":"Uzbek language","score":0.9129999876022339},{"id":"https://openalex.org/keywords/literary-corpus","display_name":"literary corpus","score":0.9359999895095825},{"id":"https://openalex.org/keywords/low-resource-languages","display_name":"low-resource languages","score":0.859000027179718},{"id":"https://openalex.org/keywords/text-preprocessing","display_name":"text preprocessing","score":0.578000009059906},{"id":"https://openalex.org/keywords/stylometry","display_name":"stylometry","score":0.6499999761581421},{"id":"https://openalex.org/keywords/domain-adaptation","display_name":"domain adaptation","score":0.4909999966621399},{"id":"https://openalex.org/keywords/digital-humanities","display_name":"digital humanities","score":0.6000000238418579},{"id":"https://openalex.org/keywords/corpus-metadata","display_name":"corpus metadata","score":0.5450000166893005}],"concepts":[{"id":"https://openalex.org/C2778718127","wikidata":"https://www.wikidata.org/wiki/Q9264","display_name":"Uzbek","level":2,"score":0.8806999921798706},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.6219000220298767},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5418000221252441},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.47780001163482666},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4535999894142151},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.42010000348091125},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.3052999973297119},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.30300000309944153},{"id":"https://openalex.org/C2776092919","wikidata":"https://www.wikidata.org/wiki/Q9072","display_name":"Estonian","level":2,"score":0.2694999873638153},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.2551000118255615}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ubmk71847.2026.11745341","doi":"https://doi.org/10.1109/ubmk71847.2026.11745341","is_oa":true,"landing_page_url":"https://doi.org/10.1109/ubmk71847.2026.11745341","pdf_url":null,"source":{"id":"https://openalex.org/S4306498178","display_name":"International Conference on Computer Science and Engineering (UBMK)","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 11th International Conference on Computer Science and Engineering (UBMK)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1109/ubmk71847.2026.11745341","doi":"https://doi.org/10.1109/ubmk71847.2026.11745341","is_oa":true,"landing_page_url":"https://doi.org/10.1109/ubmk71847.2026.11745341","pdf_url":null,"source":{"id":"https://openalex.org/S4306498178","display_name":"International Conference on Computer Science and Engineering (UBMK)","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 11th International Conference on Computer Science and Engineering (UBMK)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W2095881835","https://openalex.org/W2244626821","https://openalex.org/W3017311573","https://openalex.org/W3017961061","https://openalex.org/W3133702157","https://openalex.org/W3204096139","https://openalex.org/W4245628022","https://openalex.org/W4250089123","https://openalex.org/W4252392280","https://openalex.org/W4362515116","https://openalex.org/W4415524407","https://openalex.org/W7133225605"],"related_works":["https://openalex.org/W7224876827","https://openalex.org/W7104054234","https://openalex.org/W7224894096","https://openalex.org/W6992740216","https://openalex.org/W7167276350","https://openalex.org/W4392841031","https://openalex.org/W7224784389","https://openalex.org/W4405272602","https://openalex.org/W7167283312","https://openalex.org/W3148481248"],"abstract_inverted_index":{"Open":[0],"and":[1,40,65,76,92,100,107,120,138,147],"well-structured":[2],"literary":[3,32,49,115],"corpora":[4],"are":[5],"essential":[6],"for":[7,20,35,117],"advancing":[8],"natural":[9],"language":[10,41,126],"processing":[11],"in":[12,74],"low-resource":[13],"languages,":[14],"yet":[15],"such":[16],"resources":[17],"remain":[18],"scarce":[19],"Uzbek.":[21],"This":[22,128],"paper":[23,129],"describes":[24],"the":[25,68,90,110,131,142,156],"development":[26],"of":[27,124,144],"an":[28],"open":[29],"multi-author":[30],"Uzbek":[31,125,157],"corpus":[33,45,98,132,151],"intended":[34],"computational":[36,66],"linguistics,":[37],"digital":[38],"humanities,":[39],"technology":[42],"research.":[43,149],"The":[44,150],"comprises":[46],"approximately":[47],"700":[48],"works":[50],"written":[51],"by":[52],"20":[53],"prominent":[54],"authors,":[55],"totaling":[56],"more":[57],"than":[58],"1.84":[59],"million":[60],"tokens.":[61],"To":[62],"ensure":[63],"consistency":[64],"usability,":[67],"texts":[69],"were":[70],"collected,":[71],"normalized,":[72],"encoded":[73],"UTF-8,":[75],"enriched":[77],"with":[78,141],"standardized":[79],"metadata":[80],"through":[81,155],"a":[82,113],"unified":[83],"preprocessing":[84,136],"workflow.":[85],"A":[86],"hierarchical":[87],"organization":[88],"at":[89,161],"author":[91],"document":[93],"levels":[94],"enables":[95],"efficient":[96],"retrieval,":[97],"exploration,":[99],"statistical":[101],"analysis.":[102],"Beyond":[103],"supporting":[104],"corpus-based":[105],"linguistic":[106],"stylometric":[108],"studies,":[109],"dataset":[111],"provides":[112],"valuable":[114],"resource":[116],"educational":[118],"purposes":[119],"future":[121],"domain":[122],"adaptation":[123],"models.":[127],"details":[130],"architecture,":[133],"construction":[134],"process,":[135],"procedures,":[137],"descriptive":[139],"characteristics,":[140],"aim":[143],"facilitating":[145],"transparent":[146],"reproducible":[148],"is":[152],"publicly":[153],"available":[154],"Poetic":[158],"Corpus":[159],"platform":[160],"https://uzbekpoetikcorpus.uz/.":[162]},"counts_by_year":[],"updated_date":"2026-11-08T12:12:28.789561","created_date":"2026-10-31T00:00:00"}
