{"id":"https://openalex.org/W4415524165","doi":"https://doi.org/10.1109/ubmk67458.2025.11206879","title":"Human-Annotated NER Dataset for the Kyrgyz Language","display_name":"Human-Annotated NER Dataset for the Kyrgyz Language","publication_year":2025,"publication_date":"2025-09-17","ids":{"openalex":"https://openalex.org/W4415524165","doi":"https://doi.org/10.1109/ubmk67458.2025.11206879"},"language":"en","primary_location":{"id":"doi:10.1109/ubmk67458.2025.11206879","doi":"https://doi.org/10.1109/ubmk67458.2025.11206879","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ubmk67458.2025.11206879","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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 10th International Conference on Computer Science and Engineering (UBMK)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2509.19109","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5114653591","display_name":"Timur Turatali","orcid":"https://orcid.org/0009-0001-6778-460X","observed_orcids":["https://orcid.org/0009-0001-6778-460X"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Timur Turatali","raw_affiliation_strings":["The Cramer Project,Bishkek,Kyrgyzstan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Cramer Project,Bishkek,Kyrgyzstan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042713027","display_name":"Anton Alekseev","orcid":"https://orcid.org/0000-0001-6456-3329","observed_orcids":["https://orcid.org/0000-0001-6456-3329"]},"institutions":[{"id":"https://openalex.org/I172901346","display_name":"St Petersburg University","ror":"https://ror.org/023znxa73","country_code":"RU","type":"education","lineage":["https://openalex.org/I172901346"]},{"id":"https://openalex.org/I2800906181","display_name":"St. Petersburg Department of Steklov Institute of Mathematics","ror":"https://ror.org/030h9s280","country_code":"RU","type":"facility","lineage":["https://openalex.org/I1313323035","https://openalex.org/I2800906181","https://openalex.org/I4210124601"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Anton Alekseev","raw_affiliation_strings":["PDMI RAS, SPbU, KFU,St. Petersburg/Kazan,Russia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"PDMI RAS, SPbU, KFU,St. Petersburg/Kazan,Russia","institution_ids":["https://openalex.org/I172901346","https://openalex.org/I2800906181"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040078298","display_name":"Gulira Jumalieva","orcid":"https://orcid.org/0000-0002-1320-8981","observed_orcids":["https://orcid.org/0000-0002-1320-8981"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gulira Jumalieva","raw_affiliation_strings":["KSTU n. a. I. Razzakov,Dep. of Computer Linguistics,Bishkek,Kyrgyzstan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KSTU n. a. I. Razzakov,Dep. of Computer Linguistics,Bishkek,Kyrgyzstan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5092819705","display_name":"Gulnara Kabaeva","orcid":"https://orcid.org/0000-0003-3001-7201","observed_orcids":["https://orcid.org/0000-0003-3001-7201"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gulnara Kabaeva","raw_affiliation_strings":["Information Technology Institute KSTU n.a. I. Razzakov,Bishkek,Kyrgyzstan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Information Technology Institute KSTU n.a. I. Razzakov,Bishkek,Kyrgyzstan","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5045523675","display_name":"Sergey Nikolenko","orcid":"https://orcid.org/0000-0001-7787-2251","observed_orcids":["https://orcid.org/0000-0001-7787-2251"]},"institutions":[{"id":"https://openalex.org/I172901346","display_name":"St Petersburg University","ror":"https://ror.org/023znxa73","country_code":"RU","type":"education","lineage":["https://openalex.org/I172901346"]},{"id":"https://openalex.org/I2800906181","display_name":"St. Petersburg Department of Steklov Institute of Mathematics","ror":"https://ror.org/030h9s280","country_code":"RU","type":"facility","lineage":["https://openalex.org/I1313323035","https://openalex.org/I2800906181","https://openalex.org/I4210124601"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Sergey Nikolenko","raw_affiliation_strings":["St. Petersburg State University,St. Petersburg Dep. of Steklov Math. Institute,St. Petersburg,Russia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"St. Petersburg State University,St. Petersburg Dep. of Steklov Math. Institute,St. Petersburg,Russia","institution_ids":["https://openalex.org/I172901346","https://openalex.org/I2800906181"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.8681,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.86802544,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1607","last_page":"1612"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9976000189781189,"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":0.9976000189781189,"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":0.002099999925121665,"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":0.0,"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/named-entity-recognition","display_name":"named entity recognition","score":0.9769999980926514},{"id":"https://openalex.org/keywords/kyrgyz-language","display_name":"Kyrgyz language","score":0.9990000128746033},{"id":"https://openalex.org/keywords/news-articles","display_name":"news articles","score":0.6970000267028809},{"id":"https://openalex.org/keywords/low-resource-languages","display_name":"low-resource languages","score":0.8109999895095825},{"id":"https://openalex.org/keywords/annotation-scheme","display_name":"annotation scheme","score":0.7649999856948853},{"id":"https://openalex.org/keywords/conditional-random-fields","display_name":"conditional random fields","score":0.800000011920929},{"id":"https://openalex.org/keywords/sequence-labeling","display_name":"sequence labeling","score":0.6650000214576721}],"concepts":[{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.8299999833106995},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8205000162124634},{"id":"https://openalex.org/C2779135771","wikidata":"https://www.wikidata.org/wiki/Q403574","display_name":"Named-entity recognition","level":3,"score":0.786300003528595},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7585999965667725},{"id":"https://openalex.org/C152565575","wikidata":"https://www.wikidata.org/wiki/Q1124538","display_name":"Conditional random field","level":2,"score":0.7534999847412109},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6259999871253967},{"id":"https://openalex.org/C35639132","wikidata":"https://www.wikidata.org/wiki/Q7452468","display_name":"Sequence labeling","level":3,"score":0.5146999955177307},{"id":"https://openalex.org/C96711827","wikidata":"https://www.wikidata.org/wiki/Q17012245","display_name":"Entity linking","level":3,"score":0.4832000136375427},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.39800000190734863},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.39160001277923584},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.38690000772476196},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.37400001287460327},{"id":"https://openalex.org/C155092808","wikidata":"https://www.wikidata.org/wiki/Q182557","display_name":"Computational linguistics","level":2,"score":0.31540000438690186},{"id":"https://openalex.org/C2780035574","wikidata":"https://www.wikidata.org/wiki/Q30081","display_name":"Multilingualism","level":2,"score":0.30160000920295715},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.30070000886917114},{"id":"https://openalex.org/C2777889803","wikidata":"https://www.wikidata.org/wiki/Q25047676","display_name":"Named entity","level":2,"score":0.26930001378059387}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/ubmk67458.2025.11206879","doi":"https://doi.org/10.1109/ubmk67458.2025.11206879","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ubmk67458.2025.11206879","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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 10th International Conference on Computer Science and Engineering (UBMK)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2509.19109","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2509.19109","pdf_url":"https://arxiv.org/pdf/2509.19109","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},{"id":"doi:10.48550/arxiv.2509.19109","doi":"https://doi.org/10.48550/arxiv.2509.19109","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2509.19109","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2509.19109","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2509.19109","pdf_url":"https://arxiv.org/pdf/2509.19109","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320324099","display_name":"Russian Science Foundation","ror":"https://ror.org/03y2gwe85"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W2047477415","https://openalex.org/W2144578941","https://openalex.org/W2610748790","https://openalex.org/W2951053127","https://openalex.org/W2983040767","https://openalex.org/W3015281440","https://openalex.org/W3034744126","https://openalex.org/W3094140582","https://openalex.org/W3119242074","https://openalex.org/W3133331992","https://openalex.org/W3169483174","https://openalex.org/W4362459826","https://openalex.org/W4385570202","https://openalex.org/W4389518863","https://openalex.org/W4392956687","https://openalex.org/W4394859529","https://openalex.org/W4404783253","https://openalex.org/W4409407510","https://openalex.org/W4411120260"],"related_works":["https://openalex.org/W3216501378","https://openalex.org/W7106797254","https://openalex.org/W4392956687","https://openalex.org/W4316128004","https://openalex.org/W2898744494","https://openalex.org/W4405272826","https://openalex.org/W4226108130","https://openalex.org/W4416033799","https://openalex.org/W4405586136","https://openalex.org/W4405713898"],"abstract_inverted_index":{"We":[0,38,56],"introduce":[1],"KyrgyzNER,":[2],"the":[3,12,20,24,44,48,53,95,119,135],"first":[4],"manually":[5],"annotated":[6],"named":[7,35,60],"entity":[8,31,36,61,90],"recognition":[9,62],"dataset":[10,25],"for":[11,128,161],"Kyrgyz":[13,162],"language.":[14],"Comprising":[15],"1,499":[16],"news":[17,22],"articles":[18],"from":[19],"24.KG":[21],"portal,":[23],"contains":[26],"10,900":[27],"sentences":[28],"and":[29,51,74,113,121],"39,075":[30],"mentions":[32],"across":[33,104],"27":[34],"classes.":[37],"show":[39,86],"our":[40,81],"annotation":[41,49,155],"scheme,":[42],"discuss":[43],"challenges":[45,120],"encountered":[46],"in":[47],"process,":[50],"present":[52],"descriptive":[54],"statistics.":[55],"also":[57],"evaluate":[58],"several":[59],"models,":[63],"including":[64],"traditional":[65],"sequence":[66],"labeling":[67],"approaches":[68],"based":[69],"on":[70,80,100],"conditional":[71],"random":[72],"fields":[73],"state-of-the-art":[75],"multilingual":[76,96,125,136,142],"transformer-based":[77],"models":[78,85,92,127,143],"fine-tuned":[79],"dataset.":[82],"While":[83],"all":[84],"difficulties":[87],"with":[88,131],"rare":[89],"categories,":[91],"such":[93],"as":[94],"RoBERTa":[97,137],"variant":[98],"pretrained":[99,126],"a":[101,108],"large":[102],"corpus":[103],"many":[105],"languages":[106,130],"achieve":[107],"promising":[109],"balance":[110],"between":[111],"precision":[112],"recall.":[114],"These":[115],"findings":[116],"emphasize":[117],"both":[118],"opportunities":[122],"of":[123],"using":[124],"processing":[129,164],"limited":[132],"resources.":[133],"Although":[134],"model":[138],"performed":[139],"best,":[140],"other":[141],"yielded":[144],"comparable":[145],"results.":[146],"This":[147],"suggests":[148],"that":[149],"future":[150],"work":[151],"exploring":[152],"more":[153],"granular":[154],"schemes":[156],"may":[157],"offer":[158],"deeper":[159],"insights":[160],"language":[163],"pipelines":[165],"evaluation.":[166]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-11-03T10:50:19.383937","created_date":"2025-10-24T00:00:00"}