{"id":"https://openalex.org/W7167229294","doi":"https://doi.org/10.1109/usbereit70063.2026.11580975","title":"Punctuation Correction in Uzbek: A Lightweight Machine Learning Approach","display_name":"Punctuation Correction in Uzbek: A Lightweight Machine Learning Approach","publication_year":2026,"publication_date":"2026-05-14","ids":{"openalex":"https://openalex.org/W7167229294","doi":"https://doi.org/10.1109/usbereit70063.2026.11580975"},"language":"en","primary_location":{"id":"doi:10.1109/usbereit70063.2026.11580975","doi":"https://doi.org/10.1109/usbereit70063.2026.11580975","is_oa":true,"landing_page_url":"https://doi.org/10.1109/usbereit70063.2026.11580975","pdf_url":null,"source":{"id":"https://openalex.org/S4306498746","display_name":"Ural Symposium on Biomedical Engineering, Radioelectronics and Information Technology (USBEREIT)","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 IEEE Ural-Siberian Conference on Biomedical Engineering, Radioelectronics and Information Technology (USBEREIT)","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/usbereit70063.2026.11580975","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5002784346","display_name":"Nilufar Z. Abdurakhmonova","orcid":"https://orcid.org/0000-0001-9195-5723","observed_orcids":["https://orcid.org/0000-0001-9195-5723"]},"institutions":[{"id":"https://openalex.org/I47151758","display_name":"National University of Uzbekistan","ror":"https://ror.org/011647w73","country_code":"UZ","type":"education","lineage":["https://openalex.org/I47151758"]}],"countries":["UZ"],"is_corresponding":false,"raw_author_name":"Nilufar Abdurakhmonova","raw_affiliation_strings":["National University of Uzbekistan named after Mirzo Ulugbek,Tashkent,Uzbekistan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Uzbekistan named after Mirzo Ulugbek,Tashkent,Uzbekistan","institution_ids":["https://openalex.org/I47151758"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139981478","display_name":"Hamid Khusinov","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hamid Khusinov","raw_affiliation_strings":["Cyber University,Nurafshon,Uzbekistan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Cyber University,Nurafshon,Uzbekistan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133546475","display_name":"Ilhom Jumayev","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4405254457","display_name":"Termez University of Economics and Service","ror":"https://ror.org/01tts0094","country_code":"UZ","type":"education","lineage":["https://openalex.org/I4405254457"]}],"countries":["UZ"],"is_corresponding":false,"raw_author_name":"Ilhom Jumayev","raw_affiliation_strings":["Termez University of Economics and Service,Termez,Uzbekistan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Termez University of Economics and Service,Termez,Uzbekistan","institution_ids":["https://openalex.org/I4405254457"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069584935","display_name":"Raufjon Mahmudov","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Raufjon Mahmudov","raw_affiliation_strings":["Khorezm Mamun Academy,Khiva,Uzbekistan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Khorezm Mamun Academy,Khiva,Uzbekistan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012902751","display_name":"Rakhmatullayeva Dilrabo Alimjanovna","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dilrabo Rakhmatullayeva","raw_affiliation_strings":["Angren University,Angren,Uzbekistan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Angren University,Angren,Uzbekistan","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5139990217","display_name":"Jakhongir Khujaniyozov","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4405255828","display_name":"Mamun University","ror":"https://ror.org/03fatne33","country_code":"UZ","type":"education","lineage":["https://openalex.org/I4405255828"]}],"countries":["UZ"],"is_corresponding":false,"raw_author_name":"Jakhongir Khujaniyozov","raw_affiliation_strings":["Mamun university,Khiva,Uzbekistan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mamun university,Khiva,Uzbekistan","institution_ids":["https://openalex.org/I4405255828"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"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":"1","last_page":"4"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9955999851226807,"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":0.9955999851226807,"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/T10028","display_name":"Topic Modeling","score":0.0017000000225380063,"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.0005000000237487257,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/punctuation-correction","display_name":"punctuation correction","score":0.8859999775886536},{"id":"https://openalex.org/keywords/uzbek-language","display_name":"Uzbek language","score":0.968999981880188},{"id":"https://openalex.org/keywords/conditional-random-fields","display_name":"conditional random fields","score":0.8349999785423279},{"id":"https://openalex.org/keywords/catboost","display_name":"CatBoost","score":0.9879999756813049},{"id":"https://openalex.org/keywords/genre-variation","display_name":"genre variation","score":0.40299999713897705}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6965000033378601},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6358000040054321},{"id":"https://openalex.org/C540372491","wikidata":"https://www.wikidata.org/wiki/Q82622","display_name":"Punctuation","level":2,"score":0.6312999725341797},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4652999937534332},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.37630000710487366},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3449000120162964},{"id":"https://openalex.org/C2778751112","wikidata":"https://www.wikidata.org/wiki/Q835016","display_name":"Window (computing)","level":2,"score":0.2578999996185303},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.23569999635219574},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.2353000044822693},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.23199999332427979}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/usbereit70063.2026.11580975","doi":"https://doi.org/10.1109/usbereit70063.2026.11580975","is_oa":true,"landing_page_url":"https://doi.org/10.1109/usbereit70063.2026.11580975","pdf_url":null,"source":{"id":"https://openalex.org/S4306498746","display_name":"Ural Symposium on Biomedical Engineering, Radioelectronics and Information Technology (USBEREIT)","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 IEEE Ural-Siberian Conference on Biomedical Engineering, Radioelectronics and Information Technology (USBEREIT)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1109/usbereit70063.2026.11580975","doi":"https://doi.org/10.1109/usbereit70063.2026.11580975","is_oa":true,"landing_page_url":"https://doi.org/10.1109/usbereit70063.2026.11580975","pdf_url":null,"source":{"id":"https://openalex.org/S4306498746","display_name":"Ural Symposium on Biomedical Engineering, Radioelectronics and Information Technology (USBEREIT)","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 IEEE Ural-Siberian Conference on Biomedical Engineering, Radioelectronics and Information Technology (USBEREIT)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W2123343069","https://openalex.org/W2765151029","https://openalex.org/W2765924178","https://openalex.org/W3183246637","https://openalex.org/W4282036308","https://openalex.org/W4309463436","https://openalex.org/W4317425824","https://openalex.org/W4318472777","https://openalex.org/W4386259824","https://openalex.org/W4389666963","https://openalex.org/W4401329501","https://openalex.org/W4401329587","https://openalex.org/W4404740434","https://openalex.org/W4404790645","https://openalex.org/W4404791358","https://openalex.org/W4405152888","https://openalex.org/W4405586136","https://openalex.org/W4405787598","https://openalex.org/W4406657465","https://openalex.org/W4410735829","https://openalex.org/W4411936755","https://openalex.org/W4415524107","https://openalex.org/W4415524331","https://openalex.org/W4417471339","https://openalex.org/W4417471514","https://openalex.org/W4417472272","https://openalex.org/W4417472420","https://openalex.org/W4417472462","https://openalex.org/W4417472899","https://openalex.org/W7084047293","https://openalex.org/W7084065925","https://openalex.org/W7084070925","https://openalex.org/W7084136556"],"related_works":["https://openalex.org/W7167275365","https://openalex.org/W7167229483","https://openalex.org/W7167235118","https://openalex.org/W7167261202","https://openalex.org/W7202282955","https://openalex.org/W7167264975","https://openalex.org/W7167221168","https://openalex.org/W7167241433","https://openalex.org/W7167208663","https://openalex.org/W7167259797"],"abstract_inverted_index":{"This":[0,70,116],"paper":[1,71,131],"examines":[2],"the":[3,73,81,119,218],"problem":[4,74,120],"of":[5,14,103,127,181],"punctuation":[6,53,189,233],"checking":[7,54],"in":[8,23,75,91],"Uzbek":[9,25],"texts.":[10,213],"Punctuation":[11],"affects":[12],"understanding":[13],"meaning,":[15],"thought":[16],"boundaries,":[17],"and":[18,36,62,67,85,113,122,150,166,188,203,209,226,245,265],"readability.":[19],"Errors":[20],"are":[21,44],"common":[22],"real-world":[24],"texts":[26,43,180,260],"because":[27],"people":[28],"write":[29],"quickly,":[30],"mix":[31],"styles,":[32],"use":[33,160],"colloquial":[34],"forms,":[35],"don\u2019t":[37],"always":[38],"follow":[39],"rules.":[40],"Furthermore,":[41],"many":[42,262],"published":[45],"without":[46],"an":[47],"editor,":[48],"especially":[49],"online.":[50],"Therefore,":[51],"automatic":[52],"can":[55],"be":[56],"useful":[57],"both":[58],"for":[59,63,124],"regular":[60],"users":[61],"organizations":[64],"that":[65,92,217],"prepare":[66],"publish":[68],"materials.":[69],"formulates":[72],"a":[76,100,139,146,151,161],"simple":[77,135],"way:":[78],"it":[79],"considers":[80],"position":[82],"between":[83],"words":[84],"determines":[86],"which":[87],"character":[88],"should":[89],"appear":[90],"position.":[93],"The":[94,130,214,239],"model":[95,141,153,241],"selects":[96],"one":[97],"option":[98],"from":[99,211],"small":[101],"set":[102],"classes,":[104],"such":[105],"as":[106,185],"\u201cno":[107],"character,\u201d":[108],"\u201ccomma,\u201d":[109],"\u201cperiod,\u201d":[110],"\u201cquestion":[111],"mark,\u201d":[112],"\u201cexclamation":[114],"mark.\u201d":[115],"format":[117],"makes":[118],"understandable":[121],"allows":[123],"easy":[125],"comparison":[126],"different":[128],"methods.":[129],"also":[132],"compares":[133],"three":[134],"machine":[136],"learning":[137],"approaches:":[138],"linear":[140,240],"based":[142,154],"on":[143,155,179,198,221,248,258],"text":[144],"features,":[145],"sequential":[147,219],"CRF":[148],"model,":[149,220],"CatBoost":[152,251],"tabular":[156],"features.":[157],"All":[158],"approaches":[159],"unified":[162],"data":[163],"preparation":[164],"logic":[165],"similar":[167,243],"features":[168],"to":[169,177,230,236],"ensure":[170],"fair":[171],"comparison.":[172],"Special":[173],"attention":[174],"is":[175,227],"paid":[176],"testing":[178],"various":[182],"subject":[183],"areas,":[184],"writing":[186],"style":[187],"quality":[190],"vary":[191],"greatly":[192],"by":[193],"genre.":[194],"We":[195],"test":[196],"models":[197],"news,":[199],"official":[200],"texts,":[201],"educational":[202],"scientific":[204],"materials,":[205],"social":[206],"media":[207],"posts,":[208],"dialogues":[210],"literary":[212],"results":[215,244],"show":[216],"average,":[222],"better":[223],"maintains":[224],"consistency":[225],"less":[228],"likely":[229],"place":[231],"\u201crandom\u201d":[232],"marks":[234],"next":[235],"each":[237],"other.":[238],"produces":[242],"performs":[246],"well":[247],"\u201ccleaner\u201d":[249],"genres.":[250],"shows":[252],"consistent":[253],"results,":[254],"but":[255],"often":[256],"underperforms":[257],"\u201cdirtier\u201d":[259],"with":[261],"non-standard":[263],"forms":[264],"free-flowing":[266],"styles.":[267]},"counts_by_year":[],"updated_date":"2026-11-08T12:12:28.789561","created_date":"2026-07-04T00:00:00"}
