{"id":"https://openalex.org/W7203621887","doi":"https://doi.org/10.2139/ssrn.7300078","title":"Uzbek 65 million web corpus with FastText and Word2Vec models","display_name":"Uzbek 65 million web corpus with FastText and Word2Vec models","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7203621887","doi":"https://doi.org/10.2139/ssrn.7300078"},"language":"en","primary_location":{"id":"doi:10.2139/ssrn.7300078","doi":"https://doi.org/10.2139/ssrn.7300078","is_oa":true,"landing_page_url":"https://doi.org/10.2139/ssrn.7300078","pdf_url":"https://doi.org/10.2139/ssrn.7300078","source":{"id":"https://openalex.org/S4210172589","display_name":"SSRN Electronic Journal","issn_l":"1556-5068","issn":["1556-5068"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I1318003438","host_organization_name":"RELX Group (Netherlands)","host_organization_lineage":["https://openalex.org/I1318003438"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"posted-content"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.2139/ssrn.7300078","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5003849886","display_name":"Khabibulla A. Madatov","orcid":"https://orcid.org/0000-0002-3664-4954","observed_orcids":["https://orcid.org/0000-0002-3664-4954"]},"institutions":[{"id":"https://openalex.org/I14916453","display_name":"Urgench State University","ror":"https://ror.org/0593kfr97","country_code":"UZ","type":"education","lineage":["https://openalex.org/I14916453"]}],"countries":["UZ"],"is_corresponding":false,"raw_author_name":"Khabibula Madatov","raw_affiliation_strings":["Urgench State University named after Abu Rayhan Biruni , 14 , Kh. Alimdjan str , Urgench , 220100 , Uzbekistan"],"raw_orcid":"https://orcid.org/0000-0002-3664-4954","affiliations":[{"raw_affiliation_string":"Urgench State University named after Abu Rayhan Biruni , 14 , Kh. Alimdjan str , Urgench , 220100 , Uzbekistan","institution_ids":["https://openalex.org/I14916453"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115395574","display_name":"Surayyo Khajibaeva","orcid":"https://orcid.org/0009-0004-8482-0395","observed_orcids":["https://orcid.org/0009-0004-8482-0395"]},"institutions":[{"id":"https://openalex.org/I14916453","display_name":"Urgench State University","ror":"https://ror.org/0593kfr97","country_code":"UZ","type":"education","lineage":["https://openalex.org/I14916453"]}],"countries":["UZ"],"is_corresponding":false,"raw_author_name":"Surayyo Khajibaeva","raw_affiliation_strings":["Urgench State University named after Abu Rayhan Biruni , 14 , Kh. Alimdjan str , Urgench , 220100 , Uzbekistan"],"raw_orcid":"https://orcid.org/0009-0004-8482-0395","affiliations":[{"raw_affiliation_string":"Urgench State University named after Abu Rayhan Biruni , 14 , Kh. Alimdjan str , Urgench , 220100 , Uzbekistan","institution_ids":["https://openalex.org/I14916453"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5026395165","display_name":"Jernej Vi\u010di\u010d","orcid":"https://orcid.org/0000-0002-7876-5009","observed_orcids":["https://orcid.org/0000-0002-7876-5009"]},"institutions":[{"id":"https://openalex.org/I118905719","display_name":"University of Primorska","ror":"https://ror.org/05xefg082","country_code":"SI","type":"education","lineage":["https://openalex.org/I118905719"]}],"countries":["SI"],"is_corresponding":false,"raw_author_name":"Jernej Vi\u010di\u010d","raw_affiliation_strings":["University of Primorska , FAMNIT , Glagoljaska 8 , Koper , 6000 , Slovenia"],"raw_orcid":"https://orcid.org/0000-0002-7876-5009","affiliations":[{"raw_affiliation_string":"University of Primorska , FAMNIT , Glagoljaska 8 , Koper , 6000 , Slovenia","institution_ids":["https://openalex.org/I118905719"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9785000085830688,"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":0.9785000085830688,"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":0.01899999938905239,"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":0.0003000000142492354,"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/uzbek-language","display_name":"Uzbek language","score":0.9990000128746033},{"id":"https://openalex.org/keywords/word-embeddings","display_name":"word embeddings","score":0.9269999861717224},{"id":"https://openalex.org/keywords/word2vec","display_name":"Word2Vec","score":0.8859999775886536},{"id":"https://openalex.org/keywords/fasttext","display_name":"FastText","score":1.0},{"id":"https://openalex.org/keywords/web-corpus","display_name":"web corpus","score":0.7860000133514404},{"id":"https://openalex.org/keywords/lemmatization","display_name":"lemmatization","score":0.8970000147819519},{"id":"https://openalex.org/keywords/semantic-similarity","display_name":"semantic similarity","score":0.8090000152587891},{"id":"https://openalex.org/keywords/synonym-recognition","display_name":"synonym recognition","score":0.9269999861717224},{"id":"https://openalex.org/keywords/low-resource-languages","display_name":"low-resource languages","score":0.8209999799728394}],"concepts":[{"id":"https://openalex.org/C2776461190","wikidata":"https://www.wikidata.org/wiki/Q22673982","display_name":"Word2vec","level":3,"score":0.9014000296592712},{"id":"https://openalex.org/C2778718127","wikidata":"https://www.wikidata.org/wiki/Q9264","display_name":"Uzbek","level":2,"score":0.8896999955177307},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7143999934196472},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6696000099182129},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6640999913215637},{"id":"https://openalex.org/C89686163","wikidata":"https://www.wikidata.org/wiki/Q1187982","display_name":"Vector space model","level":2,"score":0.43860000371932983},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.42399999499320984},{"id":"https://openalex.org/C2777462759","wikidata":"https://www.wikidata.org/wiki/Q18395344","display_name":"Word embedding","level":3,"score":0.39899998903274536},{"id":"https://openalex.org/C2474386","wikidata":"https://www.wikidata.org/wiki/Q461183","display_name":"Text corpus","level":2,"score":0.3702999949455261},{"id":"https://openalex.org/C2129575","wikidata":"https://www.wikidata.org/wiki/Q54837","display_name":"Semantic Web","level":2,"score":0.365200012922287},{"id":"https://openalex.org/C13336665","wikidata":"https://www.wikidata.org/wiki/Q125977","display_name":"Vector space","level":2,"score":0.3610999882221222},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.35519999265670776},{"id":"https://openalex.org/C121934690","wikidata":"https://www.wikidata.org/wiki/Q1084","display_name":"Noun","level":2,"score":0.35280001163482666},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.3481000065803528},{"id":"https://openalex.org/C2780403423","wikidata":"https://www.wikidata.org/wiki/Q6537700","display_name":"Lexical database","level":3,"score":0.3472999930381775},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.34439998865127563},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.32690000534057617},{"id":"https://openalex.org/C13672336","wikidata":"https://www.wikidata.org/wiki/Q3460803","display_name":"Bag-of-words model","level":2,"score":0.3084000051021576},{"id":"https://openalex.org/C2778828372","wikidata":"https://www.wikidata.org/wiki/Q5283209","display_name":"Distributional semantics","level":3,"score":0.3059000074863434},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.29660001397132874},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.2831999957561493},{"id":"https://openalex.org/C25810664","wikidata":"https://www.wikidata.org/wiki/Q44325","display_name":"Ontology","level":2,"score":0.2784000039100647},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2671999931335449},{"id":"https://openalex.org/C2986420190","wikidata":"https://www.wikidata.org/wiki/Q39045939","display_name":"Semantic space","level":2,"score":0.26649999618530273},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.263700008392334},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.2590999901294708},{"id":"https://openalex.org/C173483453","wikidata":"https://www.wikidata.org/wiki/Q1040689","display_name":"Synonym (taxonomy)","level":3,"score":0.25780001282691956},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.25699999928474426}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.2139/ssrn.7300078","doi":"https://doi.org/10.2139/ssrn.7300078","is_oa":true,"landing_page_url":"https://doi.org/10.2139/ssrn.7300078","pdf_url":"https://doi.org/10.2139/ssrn.7300078","source":{"id":"https://openalex.org/S4210172589","display_name":"SSRN Electronic Journal","issn_l":"1556-5068","issn":["1556-5068"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I1318003438","host_organization_name":"RELX Group (Netherlands)","host_organization_lineage":["https://openalex.org/I1318003438"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"posted-content"}],"best_oa_location":{"id":"doi:10.2139/ssrn.7300078","doi":"https://doi.org/10.2139/ssrn.7300078","is_oa":true,"landing_page_url":"https://doi.org/10.2139/ssrn.7300078","pdf_url":"https://doi.org/10.2139/ssrn.7300078","source":{"id":"https://openalex.org/S4210172589","display_name":"SSRN Electronic Journal","issn_l":"1556-5068","issn":["1556-5068"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I1318003438","host_organization_name":"RELX Group (Netherlands)","host_organization_lineage":["https://openalex.org/I1318003438"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"posted-content"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7203621887.pdf","grobid_xml":"https://content.openalex.org/works/W7203621887.grobid-xml"},"referenced_works_count":2,"referenced_works":["https://openalex.org/W4417472086","https://openalex.org/W7154846455"],"related_works":["https://openalex.org/W6976733090","https://openalex.org/W4405272622","https://openalex.org/W4285276702","https://openalex.org/W7207652609","https://openalex.org/W2806340291","https://openalex.org/W4280635369","https://openalex.org/W7168263706","https://openalex.org/W4411859424","https://openalex.org/W7203493897","https://openalex.org/W3130502449"],"abstract_inverted_index":null,"counts_by_year":[],"updated_date":"2026-11-09T13:22:03.289127","created_date":"2026-08-18T00:00:00"}
