{"id":"https://openalex.org/W4414909820","doi":"https://doi.org/10.1063/5.0299775","title":"From morphological rules to neural networks: A hybrid framework for medical entity extraction in Karakalpak","display_name":"From morphological rules to neural networks: A hybrid framework for medical entity extraction in Karakalpak","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4414909820","doi":"https://doi.org/10.1063/5.0299775"},"language":"en","primary_location":{"id":"doi:10.1063/5.0299775","doi":"https://doi.org/10.1063/5.0299775","is_oa":false,"landing_page_url":"https://doi.org/10.1063/5.0299775","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/A5119882162","display_name":"Hulkar Zokirova","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hulkar Zokirova","raw_affiliation_strings":["Angren University, Angren, Uzbekistan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Angren University, Angren, Uzbekistan","institution_ids":[]}]},{"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/A5119879001","display_name":"Madina Jurakulova","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":"Madina Jurakulova","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/A5119882164","display_name":"Maftuna Abdunazarova","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":"Maftuna Abdunazarova","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":0.621,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.64737794,"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":"070004","last_page":"070004"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9115999937057495,"subfield":{"id":"https://openalex.org/subfields/2718","display_name":"Health Informatics"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},"topics":[{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9115999937057495,"subfield":{"id":"https://openalex.org/subfields/2718","display_name":"Health Informatics"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.06960000097751617,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.0071000000461936,"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/clinical-named-entity-recognition","display_name":"medical named entity recognition","score":0.7429999709129333},{"id":"https://openalex.org/keywords/karakalpak-language","display_name":"Karakalpak language","score":0.9980000257492065},{"id":"https://openalex.org/keywords/morphological-analysis","display_name":"morphological analysis","score":0.9760000109672546},{"id":"https://openalex.org/keywords/stemming","display_name":"stemming","score":0.7710000276565552},{"id":"https://openalex.org/keywords/low-resource-languages","display_name":"low-resource languages","score":0.8090000152587891}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6406999826431274},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.633400022983551},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.37560001015663147},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.35120001435279846},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3249000012874603},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.305400013923645},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.26660001277923584},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.26159998774528503},{"id":"https://openalex.org/C4725764","wikidata":"https://www.wikidata.org/wiki/Q844704","display_name":"Extraction (chemistry)","level":2,"score":0.25839999318122864},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.2547000050544739},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.25369998812675476}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1063/5.0299775","doi":"https://doi.org/10.1063/5.0299775","is_oa":false,"landing_page_url":"https://doi.org/10.1063/5.0299775","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W2008830554","https://openalex.org/W3130834147","https://openalex.org/W3133575378","https://openalex.org/W3199079847","https://openalex.org/W4282036308","https://openalex.org/W4362636547","https://openalex.org/W4388660106","https://openalex.org/W4389666709","https://openalex.org/W4400449896","https://openalex.org/W4401329253","https://openalex.org/W4404739953","https://openalex.org/W4404740268","https://openalex.org/W4404791425","https://openalex.org/W4405787598"],"related_works":["https://openalex.org/W7221568854","https://openalex.org/W4415524501","https://openalex.org/W4404790645","https://openalex.org/W7084076548","https://openalex.org/W4404739953","https://openalex.org/W2032776027","https://openalex.org/W4310609041","https://openalex.org/W4226108130","https://openalex.org/W7160988468","https://openalex.org/W1153356764"],"abstract_inverted_index":{"This":[0,41],"paper":[1],"presents":[2],"a":[3,22,48,68,95,120,161],"hybrid":[4,113],"method":[5,24],"for":[6],"extracting":[7],"named":[8,77],"entities":[9,78],"from":[10],"medical":[11],"texts":[12],"in":[13,29,38,61,79],"the":[14,27,30,39,54,65,76,80,86,102,112,138,143,151,158,171],"Karakalpak":[15,172],"language.":[16,173],"The":[17,107,129],"approach":[18,114],"is":[19,43,132],"based":[20,44],"on":[21,45,170],"rule-oriented":[23],"that":[25,52,111],"preprocesses":[26],"text":[28,81],"form":[31],"of":[32,35,50,67,97,142,164],"morphological":[33],"analysis":[34,42,163],"word":[36,69],"forms":[37],"text.":[40],"rules":[46],"and":[47,123,140,147,150,167],"base":[49],"affixes":[51],"allow":[53],"stemming":[55],"process":[56],"to":[57,63],"be":[58],"carried":[59],"out":[60],"order":[62],"identify":[64],"root":[66],"or":[70],"correct":[71],"misspelled":[72],"words.":[73],"After":[74],"preprocessing,":[75],"are":[82],"directly":[83],"identified":[84],"using":[85,101],"multilingual":[87],"mBERT":[88],"model.":[89],"To":[90],"train":[91],"this":[92],"language":[93],"model,":[94],"sample":[96],"5,000":[98],"sentences":[99],"marked":[100],"BIOES":[103],"scheme":[104],"was":[105,153],"used.":[106],"test":[108],"results":[109],"showed":[110],"outperforms":[115],"both":[116],"rule-based":[117],"methods":[118],"without":[119,127],"neural":[121,124],"network":[122,125],"solutions":[126,166],"preprocessing.":[128],"high":[130],"score":[131],"supported":[133],"by":[134],"digital":[135],"indicators,":[136],"where":[137],"accuracy":[139],"recall":[141],"model":[144],"reached":[145],"90%":[146],"90%,":[148],"respectively,":[149],"F1-measure":[152],"about":[154],"91%.":[155],"In":[156],"addition,":[157],"authors":[159],"conducted":[160],"comparative":[162],"existing":[165],"provided":[168],"information":[169]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-11-08T12:12:28.789561","created_date":"2025-10-10T00:00:00"}