{"id":"https://openalex.org/W7225812534","doi":"https://doi.org/10.3389/frai.2026.1986970","title":"Trustworthy confidence in Kazakh POS tagging: calibration and selective decisions in a low-resource text-correction pipeline","display_name":"Trustworthy confidence in Kazakh POS tagging: calibration and selective decisions in a low-resource text-correction pipeline","publication_year":2026,"publication_date":"2026-11-11","ids":{"openalex":"https://openalex.org/W7225812534","doi":"https://doi.org/10.3389/frai.2026.1986970"},"language":"en","primary_location":{"id":"doi:10.3389/frai.2026.1986970","doi":"https://doi.org/10.3389/frai.2026.1986970","is_oa":true,"landing_page_url":"https://doi.org/10.3389/frai.2026.1986970","pdf_url":null,"source":{"id":"https://openalex.org/S4210197006","display_name":"Frontiers in Artificial Intelligence","issn_l":"2624-8212","issn":["2624-8212"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["anvur-class-a","anvur-scientific","cwts-core","doaj","jufo-1","ki-jl-1","norway-1","poland-20","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310320527","host_organization_name":"Frontiers Media","host_organization_lineage":["https://openalex.org/P4310320527"],"host_organization_lineage_names":["Frontiers Media"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence","raw_type":"journal-article"},"volume":null,"type":"article","is_traditional":true,"indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.3389/frai.2026.1986970","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5001024392","display_name":"Laura M. Baitenova","orcid":"https://orcid.org/0000-0002-1591-2235","observed_orcids":["https://orcid.org/0000-0002-1591-2235"]},"institutions":[{"id":"https://openalex.org/I3130777500","display_name":"Turan University","ror":"https://ror.org/045mxyc94","country_code":"KZ","type":"education","lineage":["https://openalex.org/I3130777500"]}],"countries":["KZ"],"is_corresponding":false,"raw_author_name":"Laura Baitenova","raw_affiliation_strings":["Department of Information Technology, Turan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Information Technology, Turan University","institution_ids":["https://openalex.org/I3130777500"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120266278","display_name":"Akhmed Baikhojayev","orcid":"https://orcid.org/0009-0005-5757-0519","observed_orcids":["https://orcid.org/0009-0005-5757-0519"]},"institutions":[{"id":"https://openalex.org/I3130577743","display_name":"Narxoz University","ror":"https://ror.org/0523w7v09","country_code":"KZ","type":"education","lineage":["https://openalex.org/I3130577743"]}],"countries":["KZ"],"is_corresponding":false,"raw_author_name":"Akhmed Baikhojayev","raw_affiliation_strings":["School of Digital Technologies, Narxoz University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Digital Technologies, Narxoz University","institution_ids":["https://openalex.org/I3130577743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115695995","display_name":"Gulnar Mukhamejanova","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I3130577743","display_name":"Narxoz University","ror":"https://ror.org/0523w7v09","country_code":"KZ","type":"education","lineage":["https://openalex.org/I3130577743"]},{"id":"https://openalex.org/I3130777500","display_name":"Turan University","ror":"https://ror.org/045mxyc94","country_code":"KZ","type":"education","lineage":["https://openalex.org/I3130777500"]}],"countries":["KZ"],"is_corresponding":true,"raw_author_name":"Gulnar Mukhamejanova","raw_affiliation_strings":["Department of Information Technology, Turan University","School of Digital Technologies, Narxoz University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Information Technology, Turan University","institution_ids":["https://openalex.org/I3130777500"]},{"raw_affiliation_string":"School of Digital Technologies, Narxoz University","institution_ids":["https://openalex.org/I3130577743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120780272","display_name":"Gauhar Munaitbas","orcid":"https://orcid.org/0009-0008-7142-5723","observed_orcids":["https://orcid.org/0009-0008-7142-5723"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gauhar Munaitbas","raw_affiliation_strings":["Home Credit Bank JSC"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Home Credit Bank JSC","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120284814","display_name":"Saule Tussupova","orcid":"https://orcid.org/0000-0001-8280-1837","observed_orcids":["https://orcid.org/0000-0001-8280-1837"]},"institutions":[{"id":"https://openalex.org/I3130777500","display_name":"Turan University","ror":"https://ror.org/045mxyc94","country_code":"KZ","type":"education","lineage":["https://openalex.org/I3130777500"]}],"countries":["KZ"],"is_corresponding":false,"raw_author_name":"Saule Tussupova","raw_affiliation_strings":["Department of Information Technology, Turan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Information Technology, Turan University","institution_ids":["https://openalex.org/I3130777500"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5155957129","display_name":"Daryn Nurtaza","orcid":"https://orcid.org/0009-0007-8804-6896","observed_orcids":["https://orcid.org/0009-0007-8804-6896"]},"institutions":[{"id":"https://openalex.org/I3130777500","display_name":"Turan University","ror":"https://ror.org/045mxyc94","country_code":"KZ","type":"education","lineage":["https://openalex.org/I3130777500"]}],"countries":["KZ"],"is_corresponding":false,"raw_author_name":"Daryn Nurtaza","raw_affiliation_strings":["Department of Information Technology, Turan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Information Technology, Turan University","institution_ids":["https://openalex.org/I3130777500"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5115695995"],"corresponding_institution_ids":["https://openalex.org/I3130577743","https://openalex.org/I3130777500"],"apc_list":{"value":1950,"currency":"CHF","value_usd":2353},"apc_paid":{"value":1950,"currency":"CHF","value_usd":2353},"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":"9","issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9926999807357788,"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":0.9926999807357788,"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":0.003700000001117587,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.0005000000237487257,"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":[],"concepts":[{"id":"https://openalex.org/C44249647","wikidata":"https://www.wikidata.org/wiki/Q208498","display_name":"Confidence interval","level":2,"score":0.6284999847412109},{"id":"https://openalex.org/C140529851","wikidata":"https://www.wikidata.org/wiki/Q5160083","display_name":"Confidence and prediction bands","level":3,"score":0.5616000294685364},{"id":"https://openalex.org/C165838908","wikidata":"https://www.wikidata.org/wiki/Q736777","display_name":"Calibration","level":2,"score":0.48410001397132874},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4778999984264374},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.4668000042438507},{"id":"https://openalex.org/C153701036","wikidata":"https://www.wikidata.org/wiki/Q659974","display_name":"Trustworthiness","level":2,"score":0.40950000286102295},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.38499999046325684},{"id":"https://openalex.org/C200601418","wikidata":"https://www.wikidata.org/wiki/Q2193887","display_name":"Reliability engineering","level":1,"score":0.32409998774528503},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.3206000030040741},{"id":"https://openalex.org/C96865113","wikidata":"https://www.wikidata.org/wiki/Q2946816","display_name":"Certificate","level":2,"score":0.3181000053882599},{"id":"https://openalex.org/C132964779","wikidata":"https://www.wikidata.org/wiki/Q2110223","display_name":"Raw data","level":2,"score":0.31450000405311584},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3003000020980835},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.29980000853538513},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.28619998693466187},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2741999924182892},{"id":"https://openalex.org/C2781297163","wikidata":"https://www.wikidata.org/wiki/Q9252","display_name":"Kazakh","level":2,"score":0.271699994802475},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.27160000801086426}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.3389/frai.2026.1986970","doi":"https://doi.org/10.3389/frai.2026.1986970","is_oa":true,"landing_page_url":"https://doi.org/10.3389/frai.2026.1986970","pdf_url":null,"source":{"id":"https://openalex.org/S4210197006","display_name":"Frontiers in Artificial Intelligence","issn_l":"2624-8212","issn":["2624-8212"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["anvur-class-a","anvur-scientific","cwts-core","doaj","jufo-1","ki-jl-1","norway-1","poland-20","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310320527","host_organization_name":"Frontiers Media","host_organization_lineage":["https://openalex.org/P4310320527"],"host_organization_lineage_names":["Frontiers Media"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.3389/frai.2026.1986970","doi":"https://doi.org/10.3389/frai.2026.1986970","is_oa":true,"landing_page_url":"https://doi.org/10.3389/frai.2026.1986970","pdf_url":null,"source":{"id":"https://openalex.org/S4210197006","display_name":"Frontiers in Artificial Intelligence","issn_l":"2624-8212","issn":["2624-8212"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["anvur-class-a","anvur-scientific","cwts-core","doaj","jufo-1","ki-jl-1","norway-1","poland-20","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310320527","host_organization_name":"Frontiers Media","host_organization_lineage":["https://openalex.org/P4310320527"],"host_organization_lineage_names":["Frontiers Media"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W2251290832","https://openalex.org/W2254249950","https://openalex.org/W2983040767","https://openalex.org/W4385718070","https://openalex.org/W4404782267","https://openalex.org/W4417263192","https://openalex.org/W7152013015"],"related_works":[],"abstract_inverted_index":{"Confidence":[0],"is":[1,32,84,98,122,161,189],"often":[2],"treated":[3],"as":[4,177],"a":[5,9,13,30,65,144,200,214],"secondary":[6],"output":[7],"of":[8,21,43,243],"POS":[10,245],"tagger.":[11],"In":[12],"deployed":[14],"text-correction":[15],"system,":[16],"however,":[17],"confidence":[18,126,204,237],"becomes":[19],"part":[20],"the":[22,41,73,80,99,153,156,167,184,228,241],"decision-making":[23],"process":[24],"because":[25],"fixed":[26,215],"thresholds":[27],"determine":[28],"whether":[29],"prediction":[31],"handled":[33],"automatically":[34],"or":[35],"referred":[36],"for":[37,46,166,194],"review.":[38],"We":[39],"examine":[40],"reliability":[42],"this":[44,208],"signal":[45],"Kazakh":[47],"using":[48],"UD_Kazakh-KTB":[49],"(1,078":[50],"sentences,":[51],"10,536":[52],"syntactic":[53],"words).":[54],"Three":[55],"transformer":[56,134,172],"taggers,":[57],"KazBERT,":[58],"KazRoBERTa,":[59],"and":[60,89,112,121],"XLM-R,":[61],"are":[62,92],"compared":[63,163,191],"with":[64],"feature-based":[66],"CRF\u2014the":[67],"correction":[68,230],"pipeline\u2019s":[69],"two-stage":[70],"tagger\u2014retrained":[71],"under":[72],"same":[74,81],"data":[75],"conditions.":[76],"All":[77],"models":[78],"use":[79],"split;":[82],"temperature":[83,202],"fitted":[85],"on":[86],"development":[87],"data,":[88],"neural":[90],"results":[91],"reported":[93],"over":[94],"three":[95],"seeds.":[96],"XLM-R":[97],"strongest":[100],"model":[101,181],"(92.83%":[102],"accuracy,":[103],"raw":[104,128,157,168],"ECE":[105,129,135,149],"5.45%),":[106],"followed":[107],"by":[108,136,150],"KazBERT":[109],"(91.05%,":[110],"6.43%)":[111],"KazRoBERTa":[113],"(90.90%,":[114],"6.51%).":[115],"The":[116],"CRF":[117,148],"reaches":[118],"83.31%":[119],"accuracy":[120],"sharply":[123],"over-confident":[124],"(mean":[125],"0.97,":[127],"13.66%).":[130],"Temperature":[131],"scaling":[132],"reduces":[133,147],"57\u201367%":[137],"without":[138],"changing":[139],"predicted":[140],"labels":[141],"and,":[142],"in":[143],"sensitivity":[145],"analysis,":[146],"71%.":[151],"At":[152],"0.85":[154],"threshold,":[155,216],"CRF\u2019s":[158],"selective":[159],"risk":[160,173],"13.91%,":[162],"to":[164,175,192],"5.5\u20136.5%":[165],"transformers.":[169],"After":[170],"calibration,":[171],"falls":[174],"3.9\u20135.1%,":[176],"77\u2013131":[178],"predictions":[179,212],"per":[180],"move":[182],"below":[183],"threshold;":[185],"their":[186],"error":[187],"rate":[188],"31\u201333%,":[190],"4\u20135%":[193],"those":[195],"remaining":[196],"above":[197],"it.":[198],"Because":[199],"scalar":[201],"leaves":[203],"ranking":[205],"essentially":[206],"unchanged,":[207],"gain":[209],"reflects":[210],"fewer":[211],"clearing":[213],"not":[217,223],"better":[218],"selection.":[219],"These":[220],"findings":[221],"do":[222],"show":[224],"that":[225,235],"calibration":[226],"improves":[227],"final":[229],"output.":[231],"Rather,":[232],"they":[233],"demonstrate":[234],"recalibrating":[236],"alone":[238],"can":[239],"alter":[240],"routing":[242],"identical":[244],"predictions.":[246]},"counts_by_year":[],"updated_date":"2026-11-12T12:28:57.059296","created_date":"2026-11-12T00:00:00"}