{"id":"https://openalex.org/W7224907603","doi":"https://doi.org/10.1109/ubmk71847.2026.11745378","title":"A Rule-Based Pipeline for Digitizing and Mapping Karluk Lexical Units in Uzbek Dialects","display_name":"A Rule-Based Pipeline for Digitizing and Mapping Karluk Lexical Units in Uzbek Dialects","publication_year":2026,"publication_date":"2026-09-01","ids":{"openalex":"https://openalex.org/W7224907603","doi":"https://doi.org/10.1109/ubmk71847.2026.11745378"},"language":"en","primary_location":{"id":"doi:10.1109/ubmk71847.2026.11745378","doi":"https://doi.org/10.1109/ubmk71847.2026.11745378","is_oa":true,"landing_page_url":"https://doi.org/10.1109/ubmk71847.2026.11745378","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"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1109/ubmk71847.2026.11745378","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5160191763","display_name":"Sodiqjon Yoqubov","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210139342","display_name":"Navoi State University","ror":"https://ror.org/04q8yne12","country_code":"UZ","type":"education","lineage":["https://openalex.org/I4210139342"]}],"countries":["UZ"],"is_corresponding":false,"raw_author_name":"Sodiqjon Yoqubov","raw_affiliation_strings":["Navoi State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Navoi State University","institution_ids":["https://openalex.org/I4210139342"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5133575817","display_name":"Gulnoza Salimova","orcid":"https://orcid.org/0009-0008-3773-0898","observed_orcids":["https://orcid.org/0009-0008-3773-0898"]},"institutions":[{"id":"https://openalex.org/I4210098011","display_name":"Bukhara State Medical Institute named after Abu Ali ibn Sino","ror":"https://ror.org/00swkht58","country_code":"UZ","type":"healthcare","lineage":["https://openalex.org/I4210098011"]}],"countries":["UZ"],"is_corresponding":false,"raw_author_name":"Gulnoza Salimova","raw_affiliation_strings":["Bukhara State Medical Institute"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bukhara State Medical Institute","institution_ids":["https://openalex.org/I4210098011"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"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":"1161","last_page":"1166"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13122","display_name":"Turkic and Altaic Linguistics","score":0.6615999937057495,"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"}},"topics":[{"id":"https://openalex.org/T13122","display_name":"Turkic and Altaic Linguistics","score":0.6615999937057495,"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"}},{"id":"https://openalex.org/T12377","display_name":"Digital Humanities and Scholarship","score":0.24120000004768372,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.05469999834895134,"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-dialects","display_name":"Uzbek dialects","score":0.8560000061988831},{"id":"https://openalex.org/keywords/dialect-vocabulary","display_name":"dialect vocabulary","score":0.6600000262260437},{"id":"https://openalex.org/keywords/dialectal-variants","display_name":"dialectal variants","score":0.5870000123977661},{"id":"https://openalex.org/keywords/dialect-mapping","display_name":"dialect mapping","score":0.4659999907016754},{"id":"https://openalex.org/keywords/georeferencing","display_name":"georeferencing","score":0.7400000095367432},{"id":"https://openalex.org/keywords/language-classification","display_name":"language classification","score":0.6079999804496765},{"id":"https://openalex.org/keywords/unicode-normalization","display_name":"Unicode normalization","score":0.6100000143051147},{"id":"https://openalex.org/keywords/linguistic-atlas","display_name":"linguistic atlas","score":0.5379999876022339},{"id":"https://openalex.org/keywords/areal-linguistics","display_name":"areal linguistics","score":0.6539999842643738},{"id":"https://openalex.org/keywords/quality-control","display_name":"quality control","score":0.4359999895095825}],"concepts":[{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.6863999962806702},{"id":"https://openalex.org/C2778718127","wikidata":"https://www.wikidata.org/wiki/Q9264","display_name":"Uzbek","level":2,"score":0.6373999714851379},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5813000202178955},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.413100004196167},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4106000065803528},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.3244999945163727},{"id":"https://openalex.org/C2776092919","wikidata":"https://www.wikidata.org/wiki/Q9072","display_name":"Estonian","level":2,"score":0.27230000495910645},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.2337999939918518},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.21240000426769257},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.2069000005722046}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ubmk71847.2026.11745378","doi":"https://doi.org/10.1109/ubmk71847.2026.11745378","is_oa":true,"landing_page_url":"https://doi.org/10.1109/ubmk71847.2026.11745378","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/ubmk71847.2026.11745378","doi":"https://doi.org/10.1109/ubmk71847.2026.11745378","is_oa":true,"landing_page_url":"https://doi.org/10.1109/ubmk71847.2026.11745378","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":3,"referenced_works":["https://openalex.org/W2109052424","https://openalex.org/W2342249984","https://openalex.org/W3094140582"],"related_works":["https://openalex.org/W7224962599","https://openalex.org/W7224885119","https://openalex.org/W7224886804","https://openalex.org/W6960019109","https://openalex.org/W7224745566","https://openalex.org/W6922862428","https://openalex.org/W2599717616","https://openalex.org/W7224872353","https://openalex.org/W7104054234","https://openalex.org/W7131818199"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"a":[3,84,191,197],"transparent":[4],"rule-based":[5],"pipeline":[6],"for":[7,20],"converting":[8],"heterogeneous":[9],"Uzbek":[10,88],"dialectological":[11,173],"records":[12],"into":[13],"normalized,":[14],"linguistically":[15],"annotated,":[16],"and":[17,46,112],"georeferenced":[18],"data":[19],"the":[21,78,95,125,171,176],"areal":[22],"analysis":[23],"of":[24,65,72,77,115,134,158],"Karluk":[25],"lexical":[26,54],"units.":[27],"The":[28,49,153],"workflow":[29],"comprises":[30],"source-preserving":[31],"transcription,":[32],"Unicode":[33],"normalization,":[34],"deterministic":[35],"matching,":[36],"three-criterion":[37],"linguistic":[38],"classification,":[39],"WGS84-based":[40],"geographic":[41,116],"linking,":[42],"targeted":[43,142],"expert":[44],"validation,":[45],"map":[47,168],"generation.":[48],"pilot":[50],"dataset":[51],"contains":[52],"57":[53],"concepts":[55],"represented":[56],"by":[57,83],"260":[58],"dialectal":[59],"variants,":[60,74],"corresponding":[61],"to":[62],"an":[63,119,131],"average":[64],"4.56":[66],"variants":[67],"per":[68],"concept.":[69],"A":[70],"sample":[71],"20":[73],"representing":[75],"7.7%":[76],"dataset,":[79],"was":[80],"independently":[81],"audited":[82],"linguist":[85],"specializing":[86],"in":[87,94],"dialectology":[89],"who":[90],"had":[91],"not":[92],"participated":[93],"initial":[96],"classification.":[97],"Sixteen":[98],"entries":[99],"required":[100,106],"no":[101],"correction":[102],"(80%),":[103],"while":[104,180],"four":[105],"revision":[107],"(20%):":[108],"one":[109],"dialect-origin":[110],"reassignment":[111],"three":[113],"restrictions":[114],"scope.":[117],"In":[118],"exploratory":[120,187],"two-sided":[121],"exact":[122],"binomial":[123],"test,":[124],"observed":[126],"no-correction":[127],"proportion":[128],"differed":[129],"from":[130,170],"equal-probability":[132],"benchmark":[133],"0.50":[135],"(p=0.0118);":[136],"this":[137],"result":[138],"is":[139],"interpreted":[140],"as":[141,147,186,190],"quality-control":[143],"evidence":[144],"rather":[145,188],"than":[146,189],"full-corpus":[148],"accuracy":[149],"or":[150,196],"inter-annotator":[151],"agreement.":[152],"computational":[154],"subset":[155],"covers":[156],"10":[157],"Uzbekistan\u2019s":[159],"14":[160],"first-level":[161],"administrative":[162],"units":[163],"(71.4%).":[164],"An":[165],"illustrative":[166],"settlement-level":[167],"derived":[169],"broader":[172],"corpus":[174],"demonstrates":[175],"intended":[177],"spatial":[178],"output,":[179],"all":[181],"findings":[182],"are":[183],"explicitly":[184],"presented":[185],"complete":[192],"national":[193],"dialect":[194],"atlas":[195],"trained":[198],"NLP":[199],"model.":[200]},"counts_by_year":[],"updated_date":"2026-11-10T11:39:43.021295","created_date":"2026-10-31T00:00:00"}
