{"id":"https://openalex.org/W7225167376","doi":"https://doi.org/10.3390/data11110293","title":"UzAlign v1.1.1: A Morphologically Annotated Uzbek\u2013English Parallel Corpus with Model-Assisted Word Alignment","display_name":"UzAlign v1.1.1: A Morphologically Annotated Uzbek\u2013English Parallel Corpus with Model-Assisted Word Alignment","publication_year":2026,"publication_date":"2026-11-03","ids":{"openalex":"https://openalex.org/W7225167376","doi":"https://doi.org/10.3390/data11110293"},"language":"en","primary_location":{"id":"doi:10.3390/data11110293","doi":"https://doi.org/10.3390/data11110293","is_oa":true,"landing_page_url":"https://doi.org/10.3390/data11110293","pdf_url":null,"source":{"id":"https://openalex.org/S4210226510","display_name":"Data","issn_l":"2306-5729","issn":["2306-5729"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["anvur-scientific","cwts-core","doaj","jufo-1","norway-1","poland-20","russia-white-list-2","vabb-shw"],"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Data","raw_type":"journal-article"},"volume":null,"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.3390/data11110293","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5024107020","display_name":"Shohida Shahabitdinova","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I1300976906","display_name":"Andijan State University","ror":"https://ror.org/00bad4666","country_code":"UZ","type":"education","lineage":["https://openalex.org/I1300976906"]}],"countries":["UZ"],"is_corresponding":false,"raw_author_name":"Shohida Shahabitdinova","raw_affiliation_strings":["Department of Uzbek Linguistics, Andijan State University, Andijan 170100, Uzbekistan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Uzbek Linguistics, Andijan State University, Andijan 170100, Uzbekistan","institution_ids":["https://openalex.org/I1300976906"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5117292013","display_name":"Dauletov Adilbek Yusupbayevich","orcid":"https://orcid.org/0000-0002-2829-1888","observed_orcids":["https://orcid.org/0000-0002-2829-1888"]},"institutions":[{"id":"https://openalex.org/I4405254406","display_name":"Alfraganus University","ror":"https://ror.org/01s7pfd33","country_code":"UZ","type":"education","lineage":["https://openalex.org/I4405254406"]}],"countries":["UZ"],"is_corresponding":true,"raw_author_name":"Adilbek Dauletov","raw_affiliation_strings":["Department of Digital Technologies, Alfraganus University, Tashkent 100190, Uzbekistan"],"raw_orcid":"https://orcid.org/0000-0002-2829-1888","affiliations":[{"raw_affiliation_string":"Department of Digital Technologies, Alfraganus University, Tashkent 100190, Uzbekistan","institution_ids":["https://openalex.org/I4405254406"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138653125","display_name":"Noila Matyakubova","orcid":"https://orcid.org/0009-0009-3154-723X","observed_orcids":["https://orcid.org/0009-0009-3154-723X","https://orcid.org/0000-0002-0518-3630"]},"institutions":[{"id":"https://openalex.org/I4405254406","display_name":"Alfraganus University","ror":"https://ror.org/01s7pfd33","country_code":"UZ","type":"education","lineage":["https://openalex.org/I4405254406"]}],"countries":["UZ"],"is_corresponding":true,"raw_author_name":"Noila Matyakubova","raw_affiliation_strings":["Department of Foreign Languages, University of Journalism and Mass Communications of Uzbekistan, Tashkent 100027, Uzbekistan","Department of Journalism and Languages, Alfraganus University, Tashkent 100190, Uzbekistan"],"raw_orcid":"https://orcid.org/0009-0009-3154-723X","affiliations":[{"raw_affiliation_string":"Department of Foreign Languages, University of Journalism and Mass Communications of Uzbekistan, Tashkent 100027, Uzbekistan","institution_ids":[]},{"raw_affiliation_string":"Department of Journalism and Languages, Alfraganus University, Tashkent 100190, Uzbekistan","institution_ids":["https://openalex.org/I4405254406"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5158951175","display_name":"Lolakhon Nigmatova","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":"Lolakhon Nigmatova","raw_affiliation_strings":["Department of Russian Language and Literature, Bukhara State University, Bukhara 705018, Uzbekistan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Russian Language and Literature, Bukhara State University, Bukhara 705018, Uzbekistan","institution_ids":["https://openalex.org/I3131790217"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5118277366","display_name":"Dildora PULATOVA","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4405255934","display_name":"Shakhrisabz State Pedagogical Institute","ror":"https://ror.org/03kb66j27","country_code":"UZ","type":"education","lineage":["https://openalex.org/I4405255934"]}],"countries":["UZ"],"is_corresponding":false,"raw_author_name":"Dildora Pulatova","raw_affiliation_strings":["Department of Uzbek Language and Literature, Shahrisabz State Pedagogical Institute, Shahrisabz 100054, Uzbekistan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Uzbek Language and Literature, Shahrisabz State Pedagogical Institute, Shahrisabz 100054, Uzbekistan","institution_ids":["https://openalex.org/I4405255934"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115582059","display_name":"\u0428\u043e\u0445\u0438\u0434\u0430 \u0410\u0442\u0430\u043d\u0430\u0437\u0430\u0440\u043e\u0432\u0430","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210102006","display_name":"Uzbek State University of World Languages","ror":"https://ror.org/017x26m02","country_code":"UZ","type":"education","lineage":["https://openalex.org/I4210102006"]}],"countries":["UZ"],"is_corresponding":false,"raw_author_name":"Shokhida Atanazarova","raw_affiliation_strings":["Department of Theoretical English, Uzbekistan State World Language University, Tashkent 100173, Uzbekistan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Theoretical English, Uzbekistan State World Language University, Tashkent 100173, Uzbekistan","institution_ids":["https://openalex.org/I4210102006"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5160559276","display_name":"Akhmedova Khusniya","orcid":"https://orcid.org/0009-0009-7804-6395","observed_orcids":["https://orcid.org/0009-0009-7804-6395"]},"institutions":[{"id":"https://openalex.org/I21256249","display_name":"Tashkent University of Information Technology","ror":"https://ror.org/05987a729","country_code":"UZ","type":"education","lineage":["https://openalex.org/I21256249"]}],"countries":["UZ"],"is_corresponding":false,"raw_author_name":"Akhmedova Khusniya","raw_affiliation_strings":["Department of Infocommunication Engineering, Tashkent University of Information Technologies Named After Muhammad al-Khwarizmi, Tashkent 100190, Uzbekistan"],"raw_orcid":"https://orcid.org/0009-0009-7804-6395","affiliations":[{"raw_affiliation_string":"Department of Infocommunication Engineering, Tashkent University of Information Technologies Named After Muhammad al-Khwarizmi, Tashkent 100190, Uzbekistan","institution_ids":["https://openalex.org/I21256249"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5117292013","https://openalex.org/A5138653125"],"corresponding_institution_ids":["https://openalex.org/I4405254406"],"apc_list":{"value":1600,"currency":"CHF","value_usd":1930},"apc_paid":{"value":1600,"currency":"CHF","value_usd":1930},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.831463,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"11","issue":"11","first_page":"293","last_page":"293"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9990000128746033,"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":0.9990000128746033,"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/T12353","display_name":"Lexicography and Language Studies","score":9.999999747378752e-05,"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/T10034","display_name":"Syntax, Semantics, Linguistic Variation","score":9.999999747378752e-05,"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":0.7670000195503235},{"id":"https://openalex.org/keywords/word-alignment","display_name":"word alignment","score":0.7620000243186951},{"id":"https://openalex.org/keywords/morphological-annotation","display_name":"morphological annotation","score":0.7559999823570251},{"id":"https://openalex.org/keywords/compound-verbs","display_name":"compound verbs","score":0.5239999890327454},{"id":"https://openalex.org/keywords/universal-dependencies","display_name":"Universal Dependencies","score":0.6499999761581421},{"id":"https://openalex.org/keywords/morpheme-segmentation","display_name":"morpheme segmentation","score":0.7749999761581421}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7401000261306763},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7178000211715698},{"id":"https://openalex.org/C165297611","wikidata":"https://www.wikidata.org/wiki/Q43249","display_name":"Morpheme","level":2,"score":0.6453999876976013},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6420000195503235},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.6395999789237976},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.5230000019073486},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5199999809265137},{"id":"https://openalex.org/C2778718127","wikidata":"https://www.wikidata.org/wiki/Q9264","display_name":"Uzbek","level":2,"score":0.511900007724762},{"id":"https://openalex.org/C17618745","wikidata":"https://www.wikidata.org/wiki/Q207509","display_name":"Copula (linguistics)","level":2,"score":0.4553999900817871},{"id":"https://openalex.org/C137546455","wikidata":"https://www.wikidata.org/wiki/Q3213474","display_name":"Trigram","level":2,"score":0.438400000333786},{"id":"https://openalex.org/C2985367798","wikidata":"https://www.wikidata.org/wiki/Q1346592","display_name":"Parallel corpora","level":3,"score":0.3589000105857849},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.3540000021457672},{"id":"https://openalex.org/C2776818064","wikidata":"https://www.wikidata.org/wiki/Q829903","display_name":"Agreement","level":2,"score":0.3346000015735626},{"id":"https://openalex.org/C58642233","wikidata":"https://www.wikidata.org/wiki/Q8269924","display_name":"Taxonomy (biology)","level":2,"score":0.3005000054836273},{"id":"https://openalex.org/C2781181686","wikidata":"https://www.wikidata.org/wiki/Q4226068","display_name":"Coherence (philosophical gambling strategy)","level":2,"score":0.29280000925064087},{"id":"https://openalex.org/C155092808","wikidata":"https://www.wikidata.org/wiki/Q182557","display_name":"Computational linguistics","level":2,"score":0.29100000858306885},{"id":"https://openalex.org/C197129107","wikidata":"https://www.wikidata.org/wiki/Q1921621","display_name":"Merge (version control)","level":2,"score":0.27469998598098755},{"id":"https://openalex.org/C40993552","wikidata":"https://www.wikidata.org/wiki/Q514654","display_name":"Gold standard (test)","level":2,"score":0.26649999618530273},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.2648000121116638},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.2522999942302704}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.3390/data11110293","doi":"https://doi.org/10.3390/data11110293","is_oa":true,"landing_page_url":"https://doi.org/10.3390/data11110293","pdf_url":null,"source":{"id":"https://openalex.org/S4210226510","display_name":"Data","issn_l":"2306-5729","issn":["2306-5729"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["anvur-scientific","cwts-core","doaj","jufo-1","norway-1","poland-20","russia-white-list-2","vabb-shw"],"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Data","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.3390/data11110293","doi":"https://doi.org/10.3390/data11110293","is_oa":true,"landing_page_url":"https://doi.org/10.3390/data11110293","pdf_url":null,"source":{"id":"https://openalex.org/S4210226510","display_name":"Data","issn_l":"2306-5729","issn":["2306-5729"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["anvur-scientific","cwts-core","doaj","jufo-1","norway-1","poland-20","russia-white-list-2","vabb-shw"],"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Data","raw_type":"journal-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W2574614314","https://openalex.org/W3013389657","https://openalex.org/W3016973796","https://openalex.org/W3155609600","https://openalex.org/W3204541790","https://openalex.org/W3205277539","https://openalex.org/W4386259824","https://openalex.org/W4386566584","https://openalex.org/W4401044196","https://openalex.org/W4405787938","https://openalex.org/W4410735829","https://openalex.org/W4415524166","https://openalex.org/W4417509327","https://openalex.org/W7134888641","https://openalex.org/W7147700144","https://openalex.org/W7164860127","https://openalex.org/W7167206116","https://openalex.org/W7172496133"],"related_works":["https://openalex.org/W7213555236","https://openalex.org/W3177226480","https://openalex.org/W7225221386","https://openalex.org/W2574822723","https://openalex.org/W237286434","https://openalex.org/W7161663674","https://openalex.org/W7099919547","https://openalex.org/W2888854498","https://openalex.org/W2251150542","https://openalex.org/W6911405380"],"abstract_inverted_index":{"The":[0,104,191],"scarcity":[1],"of":[2,71,78,82,88,140,147,166,193,200],"token-level":[3,66],"verified":[4],"bilingual":[5,73],"word-alignment":[6,29],"resources":[7],"for":[8,14,31,222],"the":[9,25,32,69,86,121,126,145,150,154,182,197],"Uzbek":[10,205],"language":[11,34],"limits":[12],"opportunities":[13],"evaluating":[15],"alignment":[16,128,199,212,224],"models":[17],"and":[18,49,55,85,116,137,153,158,225],"advancing":[19],"cross-linguistic":[20,227],"research.":[21,229],"In":[22],"this":[23],"study,":[24],"UzAlign":[26,208],"Gold":[27,124,156],"Standard":[28],"corpus":[30,105],"English\u2013Uzbek":[33],"pair":[35],"was":[36,62,106,172,186],"created;":[37],"it":[38],"comprises":[39],"1471":[40],"parallel":[41],"sentence":[42],"pairs":[43],"sourced":[44],"from":[45,196],"three":[46],"different":[47],"origins":[48],"is":[50],"divided":[51],"into":[52],"TRAIN,":[53],"DEV,":[54],"TEST":[56],"sets.":[57],"A":[58],"five-stage":[59],"annotation":[60,215],"process":[61],"employed":[63],"to":[64,216],"verify":[65],"correspondences,":[67],"involving":[68],"use":[70],"a":[72,218],"dictionary,":[74],"morphological":[75,114,214],"analysis,":[76],"identification":[77],"compound":[79],"verbs,":[80],"verification":[81],"low-confidence":[83],"links,":[84],"recovery":[87],"missing":[89],"alignments.":[90],"Model-proposed":[91],"alignments":[92],"were":[93],"reviewed":[94],"by":[95],"two":[96],"independent":[97,164],"annotators,":[98],"with":[99,108,120,204,213],"disagreements":[100],"resolved":[101],"through":[102],"adjudication.":[103],"enriched":[107],"lemmas,":[109],"UPOS":[110],"tags,":[111],"Universal":[112],"Dependencies":[113],"features,":[115],"morpheme":[117],"segmentation.":[118],"Compared":[119],"final":[122],"adjudicated":[123],"reference,":[125],"initial":[127,151],"proposals":[129,152],"showed":[130],"98.38%":[131],"Precision,":[132],"99.86%":[133],"Recall,":[134],"99.12%":[135],"F1,":[136],"an":[138,163],"AER":[139],"0.88%.":[141],"These":[142],"values":[143],"reflect":[144],"degree":[146],"agreement":[148,171,180],"between":[149],"human-verified":[155],"reference":[157,220],"are":[159],"not":[160],"interpreted":[161],"as":[162],"evaluation":[165],"model":[167],"generalization.":[168],"Pair-level":[169],"decision":[170],"97.96%":[173],"(Cohen\u2019s":[174],"\u03ba":[175],"=":[176,189],"0.9579),":[177],"while":[178],"link-level":[179],"over":[181],"defined":[183],"candidate-link":[184],"universe":[185],"99.88%":[187],"(Dice":[188],"0.9994).":[190],"majority":[192],"errors":[194],"stemmed":[195],"incorrect":[198],"English":[201],"copula":[202],"units":[203],"linking":[206],"elements.":[207],"combines":[209],"Uzbek\u2013English":[210],"token":[211],"provide":[217],"reusable":[219],"resource":[221],"word":[223],"other":[226],"NLP":[228]},"counts_by_year":[],"updated_date":"2026-11-05T12:25:35.769452","created_date":"2026-11-04T00:00:00"}
