{"id":"https://openalex.org/W4414909563","doi":"https://doi.org/10.1063/5.0299776","title":"A comparative study of annotation schemes for named entity recognition in Uzbek legal texts","display_name":"A comparative study of annotation schemes for named entity recognition in Uzbek legal texts","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4414909563","doi":"https://doi.org/10.1063/5.0299776"},"language":"en","primary_location":{"id":"doi:10.1063/5.0299776","doi":"https://doi.org/10.1063/5.0299776","is_oa":false,"landing_page_url":"https://doi.org/10.1063/5.0299776","pdf_url":null,"source":{"id":"https://openalex.org/S2764696622","display_name":"AIP conference proceedings","issn_l":"0094-243X","issn":["0094-243X","1551-7616","1935-0465"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","jufo-1","norway-1"],"host_organization":"https://openalex.org/P4310320257","host_organization_name":"American Institute of Physics","host_organization_lineage":["https://openalex.org/P4310320257"],"host_organization_lineage_names":["American Institute of Physics"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"AIP Conference Proceedings","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5088054360","display_name":"Davlatyor B. Mengliev","orcid":"https://orcid.org/0000-0003-3969-1710","observed_orcids":["https://orcid.org/0000-0003-3969-1710"]},"institutions":[{"id":"https://openalex.org/I188973947","display_name":"Novosibirsk State University","ror":"https://ror.org/04t2ss102","country_code":"RU","type":"education","lineage":["https://openalex.org/I188973947"]},{"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":["RU","UZ"],"is_corresponding":true,"raw_author_name":"Davlatyor Mengliev","raw_affiliation_strings":["Novosibirsk State University, Novosibirsk, Russia","Urgench branch of Tashkent University of Information Technologies named after Muhammad al-Khwarizmi, Urgench, Uzbekistan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Novosibirsk State University, Novosibirsk, Russia","institution_ids":["https://openalex.org/I188973947"]},{"raw_affiliation_string":"Urgench branch of Tashkent University of Information Technologies named after Muhammad al-Khwarizmi, Urgench, Uzbekistan","institution_ids":["https://openalex.org/I21256249"]}]},{"author_position":"middle","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/A5018230757","display_name":"Raima Kh. Shirinova","orcid":"https://orcid.org/0000-0003-3860-6684","observed_orcids":["https://orcid.org/0000-0003-3860-6684"]},"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":"Raima Shirinova","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/A5092712782","display_name":"Bahodir B. Ibragimov","orcid":"https://orcid.org/0009-0000-9518-7397","observed_orcids":["https://orcid.org/0009-0000-9518-7397"]},"institutions":[{"id":"https://openalex.org/I14916453","display_name":"Urgench State University","ror":"https://ror.org/0593kfr97","country_code":"UZ","type":"education","lineage":["https://openalex.org/I14916453"]}],"countries":["UZ"],"is_corresponding":false,"raw_author_name":"Bahodir Ibragimov","raw_affiliation_strings":["Urgench State University, Urgench, Uzbekistan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Urgench State University, Urgench, Uzbekistan","institution_ids":["https://openalex.org/I14916453"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109821148","display_name":"Khudayberganova Dildora Kulmamatovna","orcid":"https://orcid.org/0000-0003-1358-6218","observed_orcids":["https://orcid.org/0000-0003-1358-6218"]},"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":"Dildora Khudayberganova","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":"last","author":{"id":"https://openalex.org/A5066812121","display_name":"Mohinur Ilhom qizi Suyunova","orcid":null,"observed_orcids":[]},"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":"Mohinur Suyunova","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"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5088054360"],"corresponding_institution_ids":["https://openalex.org/I188973947","https://openalex.org/I21256249"],"apc_list":null,"apc_paid":null,"fwci":0.3567,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.54602513,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"3377","issue":null,"first_page":"070005","last_page":"070005"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9970999956130981,"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":0.9970999956130981,"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":0.0019000000320374966,"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/T13643","display_name":"Artificial Intelligence in Law","score":0.0003000000142492354,"subfield":{"id":"https://openalex.org/subfields/3308","display_name":"Law"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/named-entity-recognition","display_name":"named entity recognition","score":0.9990000128746033},{"id":"https://openalex.org/keywords/annotation-scheme","display_name":"annotation scheme","score":0.9210000038146973},{"id":"https://openalex.org/keywords/uzbek-language","display_name":"Uzbek language","score":0.9190000295639038},{"id":"https://openalex.org/keywords/legal-documents","display_name":"legal documents","score":0.7990000247955322},{"id":"https://openalex.org/keywords/legislative-texts","display_name":"legislative texts","score":0.8240000009536743},{"id":"https://openalex.org/keywords/low-resource-languages","display_name":"low-resource languages","score":0.8429999947547913},{"id":"https://openalex.org/keywords/bios","display_name":"bios","score":0.5519999861717224},{"id":"https://openalex.org/keywords/ios","display_name":"iOS","score":0.8420000076293945},{"id":"https://openalex.org/keywords/multilingual-bert","display_name":"multilingual BERT","score":0.6660000085830688},{"id":"https://openalex.org/keywords/annotated-corpora","display_name":"annotated corpus","score":0.46299999952316284}],"concepts":[{"id":"https://openalex.org/C2779135771","wikidata":"https://www.wikidata.org/wiki/Q403574","display_name":"Named-entity recognition","level":3,"score":0.7731999754905701},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6967999935150146},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.6775000095367432},{"id":"https://openalex.org/C2778718127","wikidata":"https://www.wikidata.org/wiki/Q9264","display_name":"Uzbek","level":2,"score":0.6614000201225281},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6556000113487244},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6069999933242798},{"id":"https://openalex.org/C96711827","wikidata":"https://www.wikidata.org/wiki/Q17012245","display_name":"Entity linking","level":3,"score":0.5390999913215637},{"id":"https://openalex.org/C2777889803","wikidata":"https://www.wikidata.org/wiki/Q25047676","display_name":"Named entity","level":2,"score":0.4887000024318695},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.44429999589920044},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3199000060558319},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.28049999475479126},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2556000053882599},{"id":"https://openalex.org/C155092808","wikidata":"https://www.wikidata.org/wiki/Q182557","display_name":"Computational linguistics","level":2,"score":0.2513999938964844}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1063/5.0299776","doi":"https://doi.org/10.1063/5.0299776","is_oa":false,"landing_page_url":"https://doi.org/10.1063/5.0299776","pdf_url":null,"source":{"id":"https://openalex.org/S2764696622","display_name":"AIP conference proceedings","issn_l":"0094-243X","issn":["0094-243X","1551-7616","1935-0465"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","jufo-1","norway-1"],"host_organization":"https://openalex.org/P4310320257","host_organization_name":"American Institute of Physics","host_organization_lineage":["https://openalex.org/P4310320257"],"host_organization_lineage_names":["American Institute of Physics"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"AIP Conference Proceedings","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W2008830554","https://openalex.org/W3133575378","https://openalex.org/W3199079847","https://openalex.org/W4282036308","https://openalex.org/W4388660106","https://openalex.org/W4394859529","https://openalex.org/W4401329253","https://openalex.org/W4404739953","https://openalex.org/W4404740268","https://openalex.org/W4404740695","https://openalex.org/W4404791425","https://openalex.org/W4405143238"],"related_works":["https://openalex.org/W7167574813","https://openalex.org/W7163878427","https://openalex.org/W7125837380","https://openalex.org/W4387430429","https://openalex.org/W6963138449","https://openalex.org/W4415524839","https://openalex.org/W4417472193","https://openalex.org/W7084035521","https://openalex.org/W7084129356","https://openalex.org/W4417471304"],"abstract_inverted_index":{"Developing":[0],"effective":[1,144],"named":[2,31,196],"entity":[3,32,57,164,197],"extraction":[4],"systems":[5,184],"for":[6,185,192],"the":[7,17,41,49,54,79,85,105,112,115,142,149,167,173],"Uzbek":[8,44,186],"language":[9],"is":[10],"complicated":[11],"by":[12],"low":[13],"resource":[14],"availability":[15],"and":[16,38,90,128,139,188],"lack":[18],"of":[19,28,43,51,56,61,84,107,114,151,163,175,178],"standard":[20,96],"tools.":[21],"This":[22,170],"paper":[23],"presents":[24],"a":[25,59,74,152,190],"comparative":[26],"analysis":[27],"four":[29,65,82],"different":[30],"annotation":[33,52,108,157,179],"schemes":[34,158],"(BIO,":[35],"BIOES,":[36],"IO,":[37],"BILOU)":[39],"in":[40,64,148,195],"context":[42,150],"legislative":[45],"texts.":[46],"To":[47],"assess":[48],"impact":[50],"on":[53,78],"quality":[55,113,136],"extraction,":[58],"corpus":[60],"3,000":[62],"sentences":[63],"copies":[66],"was":[67,71,93,141],"formed.":[68],"Each":[69],"copy":[70],"annotated":[72],"using":[73,95,124],"separate":[75],"scheme.":[76],"Based":[77],"obtained":[80],"data,":[81],"instances":[83],"mBERT":[86],"model":[87],"were":[88,122],"trained,":[89],"their":[91],"performance":[92],"assessed":[94],"metrics":[97],"(Precision,":[98],"Recall,":[99],"F1-score).":[100,146],"The":[101,119],"results":[102,121],"showed":[103],"that":[104,159],"choice":[106,177],"scheme":[109,180],"significantly":[110],"affects":[111],"resulting":[116],"NER":[117,183],"models.":[118],"best":[120],"achieved":[123],"BIOES":[125],"(\u223c94%":[126],"F1-score)":[127,138],"BILOU":[129],"(\u223c92%":[130],"F1-score),":[131],"while":[132],"BIO-scheme":[133],"demonstrated":[134],"intermediate":[135],"(\u223c81%":[137],"IO-scheme":[140],"least":[143],"(\u223c75%":[145],"Thus,":[147],"custom":[153],"corpus,":[154],"more":[155],"detailed":[156],"allow":[160],"explicit":[161],"identification":[162],"boundaries":[165],"are":[166],"preferred":[168],"solution.":[169],"study":[171],"highlights":[172],"importance":[174],"careful":[176],"when":[181],"developing":[182],"texts":[187],"provides":[189],"basis":[191],"further":[193],"improvements":[194],"recognition":[198],"quality.":[199]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-11-08T12:12:28.789561","created_date":"2025-10-10T00:00:00"}
