{"id":"https://openalex.org/W4413164016","doi":"https://doi.org/10.3390/computers14080323","title":"Multilingual Named Entity Recognition in Arabic and Urdu Tweets Using Pretrained Transfer Learning Models","display_name":"Multilingual Named Entity Recognition in Arabic and Urdu Tweets Using Pretrained Transfer Learning Models","publication_year":2025,"publication_date":"2025-08-11","ids":{"openalex":"https://openalex.org/W4413164016","doi":"https://doi.org/10.3390/computers14080323"},"language":"en","primary_location":{"id":"doi:10.3390/computers14080323","is_oa":true,"landing_page_url":"https://doi.org/10.3390/computers14080323","pdf_url":null,"source":{"id":"https://openalex.org/S4210228075","display_name":"Computers","issn_l":"2073-431X","issn":["2073-431X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"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":"Computers","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.3390/computers14080323","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5061232021","display_name":"Fida Ullah","orcid":null},"institutions":[{"id":"https://openalex.org/I59361560","display_name":"Instituto Polit\u00e9cnico Nacional","ror":"https://ror.org/059sp8j34","country_code":"MX","type":"education","lineage":["https://openalex.org/I59361560"]}],"countries":["MX"],"is_corresponding":false,"raw_author_name":"Fida Ullah","raw_affiliation_strings":["Centro de Investigaci\u00f3n en Computaci\u00f3n (CIC), Instituto Polit\u00e9cnico Nacional (IPN), Mexico City 07700, Mexico"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centro de Investigaci\u00f3n en Computaci\u00f3n (CIC), Instituto Polit\u00e9cnico Nacional (IPN), Mexico City 07700, Mexico","institution_ids":["https://openalex.org/I59361560"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110017583","display_name":"Muhammad Ahmad","orcid":"https://orcid.org/0009-0003-8799-8212"},"institutions":[{"id":"https://openalex.org/I59361560","display_name":"Instituto Polit\u00e9cnico Nacional","ror":"https://ror.org/059sp8j34","country_code":"MX","type":"education","lineage":["https://openalex.org/I59361560"]}],"countries":["MX"],"is_corresponding":false,"raw_author_name":"Muhammad Ahmad","raw_affiliation_strings":["Centro de Investigaci\u00f3n en Computaci\u00f3n (CIC), Instituto Polit\u00e9cnico Nacional (IPN), Mexico City 07700, Mexico"],"raw_orcid":"https://orcid.org/0009-0003-8799-8212","affiliations":[{"raw_affiliation_string":"Centro de Investigaci\u00f3n en Computaci\u00f3n (CIC), Instituto Polit\u00e9cnico Nacional (IPN), Mexico City 07700, Mexico","institution_ids":["https://openalex.org/I59361560"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008287867","display_name":"Grigori Sidorov","orcid":"https://orcid.org/0000-0003-3901-3522"},"institutions":[{"id":"https://openalex.org/I59361560","display_name":"Instituto Polit\u00e9cnico Nacional","ror":"https://ror.org/059sp8j34","country_code":"MX","type":"education","lineage":["https://openalex.org/I59361560"]}],"countries":["MX"],"is_corresponding":false,"raw_author_name":"Grigori Sidorov","raw_affiliation_strings":["Centro de Investigaci\u00f3n en Computaci\u00f3n (CIC), Instituto Polit\u00e9cnico Nacional (IPN), Mexico City 07700, Mexico"],"raw_orcid":"https://orcid.org/0000-0003-3901-3522","affiliations":[{"raw_affiliation_string":"Centro de Investigaci\u00f3n en Computaci\u00f3n (CIC), Instituto Polit\u00e9cnico Nacional (IPN), Mexico City 07700, Mexico","institution_ids":["https://openalex.org/I59361560"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010915932","display_name":"Ildar Batyrshin","orcid":"https://orcid.org/0000-0003-0241-7902"},"institutions":[{"id":"https://openalex.org/I59361560","display_name":"Instituto Polit\u00e9cnico Nacional","ror":"https://ror.org/059sp8j34","country_code":"MX","type":"education","lineage":["https://openalex.org/I59361560"]}],"countries":["MX"],"is_corresponding":false,"raw_author_name":"Ildar Batyrshin","raw_affiliation_strings":["Centro de Investigaci\u00f3n en Computaci\u00f3n (CIC), Instituto Polit\u00e9cnico Nacional (IPN), Mexico City 07700, Mexico"],"raw_orcid":"https://orcid.org/0000-0003-0241-7902","affiliations":[{"raw_affiliation_string":"Centro de Investigaci\u00f3n en Computaci\u00f3n (CIC), Instituto Polit\u00e9cnico Nacional (IPN), Mexico City 07700, Mexico","institution_ids":["https://openalex.org/I59361560"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037099886","display_name":"Edgardo M. Felipe\u2010River\u00f3n","orcid":"https://orcid.org/0000-0002-9828-3568"},"institutions":[{"id":"https://openalex.org/I59361560","display_name":"Instituto Polit\u00e9cnico Nacional","ror":"https://ror.org/059sp8j34","country_code":"MX","type":"education","lineage":["https://openalex.org/I59361560"]}],"countries":["MX"],"is_corresponding":false,"raw_author_name":"Edgardo Manuel Felipe River\u00f3n","raw_affiliation_strings":["Centro de Investigaci\u00f3n en Computaci\u00f3n (CIC), Instituto Polit\u00e9cnico Nacional (IPN), Mexico City 07700, Mexico"],"raw_orcid":"https://orcid.org/0000-0002-9828-3568","affiliations":[{"raw_affiliation_string":"Centro de Investigaci\u00f3n en Computaci\u00f3n (CIC), Instituto Polit\u00e9cnico Nacional (IPN), Mexico City 07700, Mexico","institution_ids":["https://openalex.org/I59361560"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049701126","display_name":"Alexander Gelbukh","orcid":"https://orcid.org/0000-0001-7845-9039"},"institutions":[{"id":"https://openalex.org/I59361560","display_name":"Instituto Polit\u00e9cnico Nacional","ror":"https://ror.org/059sp8j34","country_code":"MX","type":"education","lineage":["https://openalex.org/I59361560"]}],"countries":["MX"],"is_corresponding":true,"raw_author_name":"Alexander Gelbukh","raw_affiliation_strings":["Centro de Investigaci\u00f3n en Computaci\u00f3n (CIC), Instituto Polit\u00e9cnico Nacional (IPN), Mexico City 07700, Mexico"],"raw_orcid":"https://orcid.org/0000-0001-7845-9039","affiliations":[{"raw_affiliation_string":"Centro de Investigaci\u00f3n en Computaci\u00f3n (CIC), Instituto Polit\u00e9cnico Nacional (IPN), Mexico City 07700, Mexico","institution_ids":["https://openalex.org/I59361560"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5049701126"],"corresponding_institution_ids":["https://openalex.org/I59361560"],"apc_list":{"value":1600,"currency":"CHF","value_usd":1732},"apc_paid":{"value":1600,"currency":"CHF","value_usd":1732},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.09651836,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"14","issue":"8","first_page":"323","last_page":"323"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9990000128746033,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9958000183105469,"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/urdu","display_name":"Urdu","score":0.8314756751060486},{"id":"https://openalex.org/keywords/arabic","display_name":"Arabic","score":0.6642726063728333},{"id":"https://openalex.org/keywords/named-entity-recognition","display_name":"Named-entity recognition","score":0.6568973064422607},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6532304286956787},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6081639528274536},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5869959592819214},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.5567342638969421},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.3573025166988373},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08510562777519226}],"concepts":[{"id":"https://openalex.org/C2777350258","wikidata":"https://www.wikidata.org/wiki/Q1617","display_name":"Urdu","level":2,"score":0.8314756751060486},{"id":"https://openalex.org/C96455323","wikidata":"https://www.wikidata.org/wiki/Q13955","display_name":"Arabic","level":2,"score":0.6642726063728333},{"id":"https://openalex.org/C2779135771","wikidata":"https://www.wikidata.org/wiki/Q403574","display_name":"Named-entity recognition","level":3,"score":0.6568973064422607},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6532304286956787},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6081639528274536},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5869959592819214},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.5567342638969421},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.3573025166988373},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08510562777519226},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.3390/computers14080323","is_oa":true,"landing_page_url":"https://doi.org/10.3390/computers14080323","pdf_url":null,"source":{"id":"https://openalex.org/S4210228075","display_name":"Computers","issn_l":"2073-431X","issn":["2073-431X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"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":"Computers","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:46c07e687a2346f780a60f3d2cc36a09","is_oa":true,"landing_page_url":"https://doaj.org/article/46c07e687a2346f780a60f3d2cc36a09","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Computers, Vol 14, Iss 8, p 323 (2025)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.3390/computers14080323","is_oa":true,"landing_page_url":"https://doi.org/10.3390/computers14080323","pdf_url":null,"source":{"id":"https://openalex.org/S4210228075","display_name":"Computers","issn_l":"2073-431X","issn":["2073-431X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"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":"Computers","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W2219661736","https://openalex.org/W2480904509","https://openalex.org/W2756253150","https://openalex.org/W2790214503","https://openalex.org/W2890224137","https://openalex.org/W2905014578","https://openalex.org/W2961231993","https://openalex.org/W4225768509","https://openalex.org/W4385573966","https://openalex.org/W4386126687","https://openalex.org/W4388221123","https://openalex.org/W4392271377","https://openalex.org/W4392925731","https://openalex.org/W4393134187","https://openalex.org/W4393253971","https://openalex.org/W4400276960","https://openalex.org/W4401134129","https://openalex.org/W4402075294","https://openalex.org/W4402671102","https://openalex.org/W4403304337","https://openalex.org/W4404030556","https://openalex.org/W4404599758","https://openalex.org/W4406228183","https://openalex.org/W4406300032","https://openalex.org/W4406658888","https://openalex.org/W4407049645","https://openalex.org/W4407572863","https://openalex.org/W4408362844","https://openalex.org/W4408365762","https://openalex.org/W4408471868","https://openalex.org/W4408472883","https://openalex.org/W4409174650","https://openalex.org/W4409382605","https://openalex.org/W4411055214","https://openalex.org/W4411708715","https://openalex.org/W6744350038","https://openalex.org/W6857796846","https://openalex.org/W6863222608","https://openalex.org/W6871509536"],"related_works":["https://openalex.org/W135458787","https://openalex.org/W4285154531","https://openalex.org/W2250347524","https://openalex.org/W3149011051","https://openalex.org/W3017222382","https://openalex.org/W3128216712","https://openalex.org/W3136915866","https://openalex.org/W4390279576","https://openalex.org/W2886890203","https://openalex.org/W4313535650"],"abstract_inverted_index":{"The":[0,152],"increasing":[1],"use":[2],"of":[3,26,71,227,274],"Arabic":[4,131,228],"and":[5,30,69,84,96,119,132,148,179,187,199,207,224,229,245],"Urdu":[6],"on":[7,232],"social":[8,44,284],"media":[9,45,285],"platforms,":[10],"particularly":[11],"Twitter,":[12],"has":[13],"created":[14],"a":[15,60,144,149,161,185,209,215,251,261,265],"growing":[16],"need":[17],"for":[18,116,221,279],"robust":[19],"Named":[20],"Entity":[21],"Recognition":[22],"(NER)":[23],"systems":[24],"capable":[25],"handling":[27],"noisy,":[28],"informal,":[29],"code-mixed":[31,283],"content.":[32],"However,":[33],"both":[34,117,157],"languages":[35],"remain":[36],"significantly":[37],"underrepresented":[38],"in":[39,43,130,134,281],"NER":[40,280],"research,":[41],"especially":[42],"contexts.":[46],"To":[47],"address":[48],"this":[49,51],"gap,":[50],"study":[52],"makes":[53],"four":[54],"key":[55],"contributions:":[56],"(1)":[57],"We":[58,101,122,183,204],"introduced":[59],"manual":[61,194],"entity":[62,73],"consolidation":[63],"step":[64],"to":[65,106,140,159,172],"enhance":[66],"the":[67,76,104,166,222,233,272],"consistency":[68],"accuracy":[70,241],"named":[72],"annotations.":[74],"In":[75],"original":[77],"datasets,":[78,175],"entities":[79],"such":[80],"as":[81],"person":[82],"names":[83,86],"organization":[85],"were":[87],"often":[88],"split":[89],"into":[90,110],"multiple":[91],"tokens":[92],"(e.g.,":[93],"first":[94],"name":[95,98],"last":[97],"labeled":[99],"separately).":[100],"manually":[102],"refined":[103],"annotations":[105],"merge":[107],"these":[108],"segments":[109],"unified":[111,162],"entities,":[112],"ensuring":[113],"improved":[114],"coherence":[115],"training":[118],"evaluation.":[120],"(2)":[121],"selected":[123],"two":[124,137],"publicly":[125],"available":[126],"datasets":[127,158],"from":[128],"GitHub\u2014one":[129],"one":[133],"Urdu\u2014and":[135],"applied":[136],"novel":[138,216],"strategies":[139],"tackle":[141],"low-resource":[142],"challenges:":[143],"joint":[145,153],"multilingual":[146,163,200,246],"approach":[147,154,168,278],"translation-based":[150,167],"approach.":[151],"involved":[155],"merging":[156],"create":[160],"corpus,":[164],"while":[165],"utilized":[169],"automatic":[170],"translation":[171],"generate":[173],"cross-lingual":[174],"enhancing":[176],"linguistic":[177],"diversity":[178],"model":[180,201,212,237],"generalizability.":[181],"(3)":[182],"presented":[184],"comprehensive":[186],"reproducible":[188],"pseudocode-driven":[189],"framework":[190],"that":[191],"integrates":[192],"translation,":[193],"refinement,":[195],"dataset":[196],"merging,":[197],"preprocessing,":[198],"fine-tuning.":[202],"(4)":[203],"designed,":[205],"implemented,":[206],"evaluated":[208],"customized":[210],"XLM-RoBERTa":[211],"integrated":[213],"with":[214],"attention":[217],"mechanism,":[218],"specifically":[219],"optimized":[220],"morphological":[223],"syntactic":[225],"complexities":[226],"Urdu.":[230],"Based":[231],"experiments,":[234],"our":[235,275],"proposed":[236],"(XLM-RoBERTa)":[238],"achieves":[239,260],"0.98":[240],"across":[242],"Arabic,":[243],"Urdu,":[244],"datasets.":[247],"While":[248],"it":[249,258],"shows":[250],"7\u20138%":[252],"improvement":[253,263],"over":[254,264],"traditional":[255],"baselines":[256],"(RF),":[257],"also":[259],"2.08%":[262],"deep":[266],"learning":[267],"(BiLSTM":[268],"=":[269],"0.96),":[270],"highlighting":[271],"effectiveness":[273],"cross-lingual,":[276],"resource-efficient":[277],"low-resource,":[282],"text.":[286]},"counts_by_year":[],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}
