{"id":"https://openalex.org/W7140124422","doi":"https://doi.org/10.18653/v1/2026.vardial-1.22","title":"Curriculum Learning and Pseudo-Labeling Improve the Generalization of Multi-Label Arabic Dialect Identification Models","display_name":"Curriculum Learning and Pseudo-Labeling Improve the Generalization of Multi-Label Arabic Dialect Identification Models","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7140124422","doi":"https://doi.org/10.18653/v1/2026.vardial-1.22"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.vardial-1.22","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.vardial-1.22","pdf_url":"https://aclanthology.org/2026.vardial-1.22.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 13th Workshop on NLP for Similar Languages, Varieties and Dialects","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.vardial-1.22.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Ali Mekky","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ali Mekky","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Mohamed El Zeftawy","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mohamed El Zeftawy","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Lara Hassan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lara Hassan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Amr Keleg","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Amr Keleg","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Preslav Nakov","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Preslav Nakov","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.37070019,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"261","last_page":"274"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11640","display_name":"Linguistic Variation and Morphology","score":0.27639999985694885,"subfield":{"id":"https://openalex.org/subfields/3310","display_name":"Linguistics and Language"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11640","display_name":"Linguistic Variation and Morphology","score":0.27639999985694885,"subfield":{"id":"https://openalex.org/subfields/3310","display_name":"Linguistics and Language"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12380","display_name":"Authorship Attribution and Profiling","score":0.0820000022649765,"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/T11587","display_name":"Second Language Acquisition and Learning","score":0.04659999907016754,"subfield":{"id":"https://openalex.org/subfields/3204","display_name":"Developmental and Educational Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.6154000163078308},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.6083999872207642},{"id":"https://openalex.org/keywords/arabic","display_name":"Arabic","score":0.37130001187324524},{"id":"https://openalex.org/keywords/curriculum","display_name":"Curriculum","score":0.27549999952316284},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.2752000093460083}],"concepts":[{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.6154000163078308},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.6083999872207642},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5906999707221985},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5659000277519226},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5641999840736389},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.5174000263214111},{"id":"https://openalex.org/C96455323","wikidata":"https://www.wikidata.org/wiki/Q13955","display_name":"Arabic","level":2,"score":0.37130001187324524},{"id":"https://openalex.org/C47177190","wikidata":"https://www.wikidata.org/wiki/Q207137","display_name":"Curriculum","level":2,"score":0.27549999952316284},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2752000093460083},{"id":"https://openalex.org/C74672266","wikidata":"https://www.wikidata.org/wiki/Q815859","display_name":"Language acquisition","level":2,"score":0.23360000550746918}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.vardial-1.22","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.vardial-1.22","pdf_url":"https://aclanthology.org/2026.vardial-1.22.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 13th Workshop on NLP for Similar Languages, Varieties and Dialects","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.vardial-1.22","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.vardial-1.22","pdf_url":"https://aclanthology.org/2026.vardial-1.22.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 13th Workshop on NLP for Similar Languages, Varieties and Dialects","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.6460609436035156}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7140124422.pdf","grobid_xml":"https://content.openalex.org/works/W7140124422.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Being":[0],"modeled":[1],"as":[2,23,75,79],"a":[3,8,24,92,119,142],"single-label":[4,35],"classification":[5,26],"task":[6],"for":[7,43,62,150],"long":[9],"time,":[10],"recent":[11],"work":[12],"has":[13],"argued":[14],"that":[15,54],"Arabic":[16,64,112],"Dialect":[17,65],"Identification":[18,66],"(ADI)":[19],"should":[20],"be":[21,82],"framed":[22],"multi-label":[25,40,93,98,121],"task.However,":[27],"ADI":[28,50],"remains":[29],"constrained":[30],"by":[31,95,110],"the":[32,55,70,111,134,151],"availability":[33],"of":[34,72,114,145],"datasets,":[36],"with":[37,107,128],"no":[38],"largescale":[39],"resources":[41],"available":[42],"training.By":[44],"analyzing":[45],"models":[46],"trained":[47],"on":[48],"singlelabel":[49],"data,":[51],"we":[52,90,117],"show":[53],"main":[56],"difficulty":[57],"in":[58,69,84],"repurposing":[59],"such":[60],"datasets":[61],"Multi-Label":[63],"(MLADI)":[67],"lies":[68],"selection":[71],"negative":[73,80],"samples,":[74],"many":[76],"sentences":[77],"treated":[78],"could":[81],"acceptable":[83],"multiple":[85],"dialects.To":[86],"address":[87],"these":[88],"issues,":[89],"construct":[91],"dataset":[94],"generating":[96],"automatic":[97],"annotations":[99],"using":[100,123],"GPT-4o":[101],"and":[102,131],"binary":[103],"dialect":[104],"acceptability":[105],"classifiers,":[106],"aggregation":[108],"guided":[109],"Level":[113],"Dialectness":[115],"(ALDi).Afterward,":[116],"train":[118],"BERT-based":[120],"classifier":[122],"curriculum":[124],"learning":[125],"strategies":[126],"aligned":[127],"dialectal":[129],"complexity":[130],"label":[132],"cardinality.On":[133],"MLADI":[135],"leaderboard,":[136],"our":[137],"best-performing":[138],"LAHJATBERT":[139],"model":[140],"achieves":[141],"macro":[143],"F1":[144],"0.69,":[146],"compared":[147],"to":[148],"0.55":[149],"strongest":[152],"previously":[153],"reported":[154],"system.":[155]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-02-18T00:00:00"}