{"id":"https://openalex.org/W7125595396","doi":"https://doi.org/10.1145/3787497","title":"DarijaDB: Unlocking Text-to-SQL for Arabic Dialects","display_name":"DarijaDB: Unlocking Text-to-SQL for Arabic Dialects","publication_year":2026,"publication_date":"2026-01-24","ids":{"openalex":"https://openalex.org/W7125595396","doi":"https://doi.org/10.1145/3787497"},"language":"en","primary_location":{"id":"doi:10.1145/3787497","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3787497","pdf_url":null,"source":{"id":"https://openalex.org/S4306421405","display_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","issn_l":"2375-4699","issn":["2375-4699","2375-4702"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1145/3787497","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5116000547","display_name":"Salmane Chafik","orcid":null},"institutions":[{"id":"https://openalex.org/I4210120584","display_name":"The Polytechnic University of Japan","ror":"https://ror.org/02f0psx94","country_code":"JP","type":"education","lineage":["https://openalex.org/I4210120584"]},{"id":"https://openalex.org/I4210131560","display_name":"Universit\u00e9 Mohammed VI Polytechnique","ror":"https://ror.org/03xc55g68","country_code":"MA","type":"education","lineage":["https://openalex.org/I4210131560"]}],"countries":["JP","MA"],"is_corresponding":false,"raw_author_name":"Salmane Chafik","raw_affiliation_strings":["College of Computing, Mohammed VI Polytechnic University"],"raw_orcid":"https://orcid.org/0009-0002-9387-6847","affiliations":[{"raw_affiliation_string":"College of Computing, Mohammed VI Polytechnic University","institution_ids":["https://openalex.org/I4210120584","https://openalex.org/I4210131560"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009803558","display_name":"Saad Ezzini","orcid":"https://orcid.org/0000-0001-7657-4738"},"institutions":[{"id":"https://openalex.org/I134085113","display_name":"King Fahd University of Petroleum and Minerals","ror":"https://ror.org/03yez3163","country_code":"SA","type":"education","lineage":["https://openalex.org/I134085113"]}],"countries":["SA"],"is_corresponding":false,"raw_author_name":"Saad Ezzini","raw_affiliation_strings":["Information and Computer Science Department, King Fahd University of Petroleum & Minerals","Interdisciplinary Research Center for Intelligent Manufacturing and Robotics, King Fahd University of Petroleum & Minerals"],"raw_orcid":"https://orcid.org/0000-0001-7657-4738","affiliations":[{"raw_affiliation_string":"Information and Computer Science Department, King Fahd University of Petroleum & Minerals","institution_ids":["https://openalex.org/I134085113"]},{"raw_affiliation_string":"Interdisciplinary Research Center for Intelligent Manufacturing and Robotics, King Fahd University of Petroleum & Minerals","institution_ids":["https://openalex.org/I134085113"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5123458400","display_name":"Ismail Berrada","orcid":null},"institutions":[{"id":"https://openalex.org/I4210120584","display_name":"The Polytechnic University of Japan","ror":"https://ror.org/02f0psx94","country_code":"JP","type":"education","lineage":["https://openalex.org/I4210120584"]},{"id":"https://openalex.org/I4210131560","display_name":"Universit\u00e9 Mohammed VI Polytechnique","ror":"https://ror.org/03xc55g68","country_code":"MA","type":"education","lineage":["https://openalex.org/I4210131560"]}],"countries":["JP","MA"],"is_corresponding":false,"raw_author_name":"Ismail Berrada","raw_affiliation_strings":["College of Computing, Mohammed VI Polytechnic University"],"raw_orcid":"https://orcid.org/0000-0003-4225-911X","affiliations":[{"raw_affiliation_string":"College of Computing, Mohammed VI Polytechnic University","institution_ids":["https://openalex.org/I4210120584","https://openalex.org/I4210131560"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.09040407,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"25","issue":"2","first_page":"1","last_page":"19"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.4366999864578247,"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":0.4366999864578247,"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/T11640","display_name":"Linguistic Variation and Morphology","score":0.14159999787807465,"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":0.10360000282526016,"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/optimal-distinctiveness-theory","display_name":"Optimal distinctiveness theory","score":0.7750999927520752},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6018999814987183},{"id":"https://openalex.org/keywords/executable","display_name":"Executable","score":0.5600000023841858},{"id":"https://openalex.org/keywords/arabic","display_name":"Arabic","score":0.5579000115394592},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.43220001459121704},{"id":"https://openalex.org/keywords/sql","display_name":"SQL","score":0.37599998712539673}],"concepts":[{"id":"https://openalex.org/C47385372","wikidata":"https://www.wikidata.org/wiki/Q7098943","display_name":"Optimal distinctiveness theory","level":2,"score":0.7750999927520752},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7021999955177307},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6283000111579895},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6018999814987183},{"id":"https://openalex.org/C160145156","wikidata":"https://www.wikidata.org/wiki/Q778586","display_name":"Executable","level":2,"score":0.5600000023841858},{"id":"https://openalex.org/C96455323","wikidata":"https://www.wikidata.org/wiki/Q13955","display_name":"Arabic","level":2,"score":0.5579000115394592},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5424000024795532},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.45010000467300415},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.43220001459121704},{"id":"https://openalex.org/C510870499","wikidata":"https://www.wikidata.org/wiki/Q47607","display_name":"SQL","level":2,"score":0.37599998712539673},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.36480000615119934},{"id":"https://openalex.org/C5655090","wikidata":"https://www.wikidata.org/wiki/Q192588","display_name":"Relational database","level":2,"score":0.3495999872684479},{"id":"https://openalex.org/C2778243841","wikidata":"https://www.wikidata.org/wiki/Q56467","display_name":"Modern Standard Arabic","level":3,"score":0.34779998660087585},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.30649998784065247},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.28839999437332153},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.2784999907016754}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3787497","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3787497","pdf_url":null,"source":{"id":"https://openalex.org/S4306421405","display_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","issn_l":"2375-4699","issn":["2375-4699","2375-4702"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1145/3787497","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3787497","pdf_url":null,"source":{"id":"https://openalex.org/S4306421405","display_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","issn_l":"2375-4699","issn":["2375-4699","2375-4702"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.5152468085289001}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W2077302143","https://openalex.org/W2101105183","https://openalex.org/W2269738476","https://openalex.org/W2751448157","https://openalex.org/W2945102109","https://openalex.org/W2952032096","https://openalex.org/W3022196370","https://openalex.org/W3138381435","https://openalex.org/W3176134318","https://openalex.org/W3198685994","https://openalex.org/W4285104921","https://openalex.org/W4289494028","https://openalex.org/W4293819888","https://openalex.org/W4317716303","https://openalex.org/W4362571107","https://openalex.org/W4385574048","https://openalex.org/W4392182010","https://openalex.org/W4392414327","https://openalex.org/W4399213656","https://openalex.org/W4403796805"],"related_works":[],"abstract_inverted_index":{"Recent":[0],"advances":[1],"in":[2,192,199],"text-to-SQL":[3,92,127],"models,":[4,149],"which":[5,101],"translate":[6],"natural":[7],"language":[8,148],"questions":[9],"(NLQs)":[10],"into":[11],"executable":[12],"SQL":[13],"queries,":[14],"have":[15,68],"made":[16],"interacting":[17],"with":[18,26,36,144],"relational":[19],"databases":[20],"more":[21],"accessible,":[22],"even":[23],"for":[24,104,128],"those":[25,166],"limited":[27],"technical":[28],"ability.":[29],"This":[30],"task":[31],"has":[32],"seen":[33],"significant":[34],"improvement":[35],"the":[37,76,82,97,136,156,171,174,185],"release":[38],"of":[39,57,78,84,177],"multiple":[40],"English":[41,163],"datasets":[42,80,180],"and":[43,49,55,66,107,114,142,151,165,194],"benchmarks":[44],"such":[45,62],"as":[46,63],"WikiSQL,":[47],"SPIDER,":[48],"BIRD,":[50],"each":[51],"covering":[52],"different":[53,140],"domains":[54],"levels":[56],"complexity.":[58],"Non-English":[59],"high-resource":[60],"languages,":[61],"Chinese,":[64],"Russian,":[65],"Arabic,":[67],"also":[69],"benefited":[70],"from":[71,188,195],"these":[72],"advances,":[73],"either":[74],"through":[75],"translation":[77],"existing":[79],"or":[81],"creation":[83],"new":[85],"ones.":[86],"Dialect2SQL":[87,137],",":[88],"a":[89,123],"newly":[90],"released":[91],"dataset,":[93],"is":[94,102],"dedicated":[95],"to":[96,110,190,197],"Moroccan":[98],"dialect":[99],"(Darija),":[100],"known":[103],"its":[105],"complexity":[106],"distinctiveness":[108],"compared":[109],"other":[111],"Arabic":[112],"dialects":[113],"Modern":[115],"Standard":[116],"Arabic.":[117],"In":[118,183],"this":[119],"article,":[120],"we":[121],"conduct":[122],"comprehensive":[124],"study":[125],"on":[126,135,162,168],"Darija":[129],"by":[130],"conducting":[131],"several":[132],"experiments":[133,154],"mainly":[134],"dataset":[138],"using":[139],"approaches":[141],"configurations":[143],"two":[145],"code-based":[146],"large":[147],"StarCoder2":[150],"Qwen-2.5-Coder.":[152],"The":[153],"reveal":[155],"performance":[157],"gap":[158,186],"between":[159],"models":[160],"fine-tuned":[161,167],"data":[164],"Darija.":[169],"Additionally,":[170],"results":[172],"illustrate":[173],"positive":[175],"impact":[176],"incorporating":[178],"multi-language":[179],"during":[181],"training.":[182],"particular,":[184],"decreases":[187],"10.1%":[189],"6.7%":[191],"BLEU,":[193],"12.5%":[196],"5.7%":[198],"TSED.":[200]},"counts_by_year":[],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2026-01-25T00:00:00"}
