{"id":"https://openalex.org/W4409560179","doi":"https://doi.org/10.1109/tai.2025.3562162","title":"ARDIAL-BERT: Advancing Multidialectal Arabic Named Entity Recognition Through Continual Pretraining","display_name":"ARDIAL-BERT: Advancing Multidialectal Arabic Named Entity Recognition Through Continual Pretraining","publication_year":2025,"publication_date":"2025-04-17","ids":{"openalex":"https://openalex.org/W4409560179","doi":"https://doi.org/10.1109/tai.2025.3562162"},"language":"en","primary_location":{"id":"doi:10.1109/tai.2025.3562162","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tai.2025.3562162","pdf_url":null,"source":{"id":"https://openalex.org/S4210169448","display_name":"IEEE Transactions on Artificial Intelligence","issn_l":"2691-4581","issn":["2691-4581"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Artificial Intelligence","raw_type":"journal-article"},"type":"article","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/A5116850707","display_name":"Tahar Alimi","orcid":"https://orcid.org/0009-0007-0541-0163"},"institutions":[{"id":"https://openalex.org/I142899784","display_name":"University of Sfax","ror":"https://ror.org/04d4sd432","country_code":"TN","type":"education","lineage":["https://openalex.org/I142899784"]}],"countries":["TN"],"is_corresponding":false,"raw_author_name":"Tahar Alimi","raw_affiliation_strings":["ANLP Research group - MIRACL Laboratory, University of Sfax, Sfax, Tunisia","ANLP Research group - MIRACL LabUniversity of Sfax Tunisia"],"raw_orcid":"https://orcid.org/0009-0007-0541-0163","affiliations":[{"raw_affiliation_string":"ANLP Research group - MIRACL Laboratory, University of Sfax, Sfax, Tunisia","institution_ids":["https://openalex.org/I142899784"]},{"raw_affiliation_string":"ANLP Research group - MIRACL LabUniversity of Sfax Tunisia","institution_ids":["https://openalex.org/I142899784"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5117199584","display_name":"Rahma Boujelbene","orcid":null},"institutions":[{"id":"https://openalex.org/I142899784","display_name":"University of Sfax","ror":"https://ror.org/04d4sd432","country_code":"TN","type":"education","lineage":["https://openalex.org/I142899784"]}],"countries":["TN"],"is_corresponding":false,"raw_author_name":"Rahma Boujelbene","raw_affiliation_strings":["ANLP Research group - MIRACL Laboratory, University of Sfax, Sfax, Tunisia","ANLP Research group - MIRACL LabUniversity of Sfax Tunisia"],"raw_orcid":"https://orcid.org/0000-0003-2314-6064","affiliations":[{"raw_affiliation_string":"ANLP Research group - MIRACL Laboratory, University of Sfax, Sfax, Tunisia","institution_ids":["https://openalex.org/I142899784"]},{"raw_affiliation_string":"ANLP Research group - MIRACL LabUniversity of Sfax Tunisia","institution_ids":["https://openalex.org/I142899784"]}]},{"author_position":"last","author":{"id":null,"display_name":"Lamia Hadrich Belguith","orcid":"https://orcid.org/0000-0002-5063-9246"},"institutions":[{"id":"https://openalex.org/I142899784","display_name":"University of Sfax","ror":"https://ror.org/04d4sd432","country_code":"TN","type":"education","lineage":["https://openalex.org/I142899784"]}],"countries":["TN"],"is_corresponding":false,"raw_author_name":"Lamia Hadrich Belguith","raw_affiliation_strings":["ANLP Research group - MIRACL Laboratory, University of Sfax, Sfax, Tunisia","ANLP Research group - MIRACL LabUniversity of Sfax Tunisia"],"raw_orcid":"https://orcid.org/0000-0002-5063-9246","affiliations":[{"raw_affiliation_string":"ANLP Research group - MIRACL Laboratory, University of Sfax, Sfax, Tunisia","institution_ids":["https://openalex.org/I142899784"]},{"raw_affiliation_string":"ANLP Research group - MIRACL LabUniversity of Sfax Tunisia","institution_ids":["https://openalex.org/I142899784"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I142899784"],"apc_list":null,"apc_paid":null,"fwci":1.396,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.83143036,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"7","issue":"4","first_page":"1883","last_page":"1892"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9991999864578247,"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":0.9991999864578247,"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":0.9991000294685364,"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/T13629","display_name":"Text Readability and Simplification","score":0.9959999918937683,"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/arabic","display_name":"Arabic","score":0.6977438926696777},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4616023898124695},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4468558132648468},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.43088480830192566},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3816475570201874},{"id":"https://openalex.org/keywords/philosophy","display_name":"Philosophy","score":0.15897956490516663}],"concepts":[{"id":"https://openalex.org/C96455323","wikidata":"https://www.wikidata.org/wiki/Q13955","display_name":"Arabic","level":2,"score":0.6977438926696777},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4616023898124695},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4468558132648468},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.43088480830192566},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3816475570201874},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.15897956490516663}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tai.2025.3562162","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tai.2025.3562162","pdf_url":null,"source":{"id":"https://openalex.org/S4210169448","display_name":"IEEE Transactions on Artificial Intelligence","issn_l":"2691-4581","issn":["2691-4581"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W1728883788","https://openalex.org/W2088911157","https://openalex.org/W2104608657","https://openalex.org/W2144578941","https://openalex.org/W2250598139","https://openalex.org/W3115462295","https://openalex.org/W4200176239","https://openalex.org/W4290928096","https://openalex.org/W4366525428","https://openalex.org/W4376279682","https://openalex.org/W4385572487","https://openalex.org/W4385572518","https://openalex.org/W4389518283","https://openalex.org/W4389518321","https://openalex.org/W4389518395","https://openalex.org/W4389519054","https://openalex.org/W4389520683","https://openalex.org/W4390623360","https://openalex.org/W4391138734","https://openalex.org/W4402671426","https://openalex.org/W4403221502","https://openalex.org/W4404783711","https://openalex.org/W4416310693"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Named":[0],"Entity":[1],"Recognition":[2],"(NER)":[3],"is":[4,15],"among":[5],"the":[6,61,67,75,88,90,125,255,264,273],"main":[7],"tasks":[8],"of":[9,69,77,129,172,175,257,267],"Natural":[10],"Language":[11],"Processing":[12],"(NLP).":[13],"NER":[14,37,81,93,139,162,201],"a":[16,70,78,99,104,170,184,196,239],"critical":[17],"and":[18,31,45,102,118,168,192,220,250,263],"fundamental":[19],"component":[20],"for":[21,39],"several":[22,36,134],"NLP":[23],"applications":[24],"including":[25],"Information":[26],"Retrieval":[27],"(IR),":[28],"Question-Answering":[29],"(QA)":[30],"Machine":[32],"Translation":[33],"(MT).":[34],"While":[35],"models":[38],"formal":[40],"languages":[41],"such":[42],"as":[43],"English":[44],"Modern":[46],"Standard":[47],"Arabic":[48,52,72,107,156,259],"(MSA)":[49],"have":[50],"emerged,":[51],"dialects":[53,260],"remain":[54],"in":[55],"their":[56],"infancy.":[57],"We":[58],"noted":[59],"that":[60,236,269],"most":[62],"recent":[63],"researches":[64],"focused":[65],"on":[66,106,136,147,198,222],"study":[68],"single":[71],"dialect,":[73],"hence":[74],"absence":[76],"perfect":[79],"multidialectal":[80,92],"model.":[82],"In":[83],"this":[84],"paper,":[85],"we":[86,152,182,194],"present":[87],"ARDIAL-BERT,":[89],"first":[91,151],"model":[94,121,214],"which":[95],"was":[96,122,165],"built":[97,123,153],"upon":[98,124],"continuous":[100,204],"pretraining":[101,186],"then":[103,193],"finetuning":[105,197],"dialect":[108],"publicly":[109],"available":[110],"datasets":[111],"grouped":[112],"by":[113,242,261],"region":[114,262],"(Levantine,":[115],"Maghrebi,":[116],"Egyptian":[117],"Gulf).":[119],"The":[120,203],"last":[126],"updated":[127],"version":[128],"BERT":[130,138],"transfer":[131],"transformers":[132],"after":[133],"experiments":[135],"various":[137],"models.":[140,252],"<p":[141],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[142],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">We":[143],"approached":[144],"our":[145],"contribution":[146],"two":[148],"different":[149,211],"tasks:":[150],"ARDIAL-NER,":[154],"an":[155],"multidialect":[157],"dataset":[158],"extracted":[159],"from":[160],"existing":[161],"datasets.":[163,202],"ARDIAL-NER":[164],"manually":[166],"annotated":[167,200],"contains":[169],"total":[171],"53,539":[173],"entities":[174],"369,372":[176],"tokens":[177],"composing":[178],"21683":[179],"sentences.":[180],"Second,":[181],"conducted":[183],"continual":[185],"process":[187],"using":[188],"additional":[189],"unannotated":[190],"data,":[191,219],"guided":[195],"new":[199,217,223],"learning":[205],"system":[206],"can":[207],"be":[208],"applied":[209],"at":[210],"levels:":[212],"updating":[213],"parameters,":[215],"incorporating":[216],"language":[218],"training":[221],"labels.":[224],"Our":[225,233],"results":[226,245],"demonstrate":[227],"its":[228],"effectiveness":[229],"to":[230],"varying":[231],"degrees.":[232],"approach":[234],"showed":[235],"it":[237],"exhibited":[238],"greater":[240],"ability":[241],"achieving":[243],"superior":[244],"compared":[246],"with":[247,272],"both":[248],"baselines":[249],"previous":[251],"This":[253],"demonstrates":[254],"capabilities":[256],"grouping":[258],"good":[265],"selection":[266],"data":[268],"matches":[270],"well":[271],"baseline":[274],"transformers.":[275]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-04-02T13:48:15.688549","created_date":"2025-10-10T00:00:00"}
