{"id":"https://openalex.org/W7139916336","doi":"https://doi.org/10.1016/j.procs.2026.01.114","title":"Saudi Dialects to MSA Machine Translation: A Systematic Evaluation of LLMs","display_name":"Saudi Dialects to MSA Machine Translation: A Systematic Evaluation of LLMs","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7139916336","doi":"https://doi.org/10.1016/j.procs.2026.01.114"},"language":"en","primary_location":{"id":"doi:10.1016/j.procs.2026.01.114","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.procs.2026.01.114","pdf_url":null,"source":{"id":"https://openalex.org/S120348307","display_name":"Procedia Computer Science","issn_l":"1877-0509","issn":["1877-0509"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Procedia Computer Science","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.1016/j.procs.2026.01.114","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5075423176","display_name":"Ghada Alharbi","orcid":"https://orcid.org/0009-0005-4871-455X"},"institutions":[{"id":"https://openalex.org/I23075662","display_name":"Taibah University","ror":"https://ror.org/01xv1nn60","country_code":"SA","type":"education","lineage":["https://openalex.org/I23075662"]}],"countries":["SA"],"is_corresponding":true,"raw_author_name":"Ghada Alharbi","raw_affiliation_strings":["Taibah University, Department of Artificial Intelligence and Data Science, Medina, 42353, KSA"],"affiliations":[{"raw_affiliation_string":"Taibah University, Department of Artificial Intelligence and Data Science, Medina, 42353, KSA","institution_ids":["https://openalex.org/I23075662"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5075423176"],"corresponding_institution_ids":["https://openalex.org/I23075662"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.93021693,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":null,"biblio":{"volume":"275","issue":null,"first_page":"464","last_page":"473"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.8676999807357788,"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":0.8676999807357788,"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":0.02250000089406967,"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":0.010099999606609344,"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":[],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6937000155448914},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.38659998774528503},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.32600000500679016},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3154999911785126},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.27720001339912415},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2538999915122986},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.2345999926328659},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.22669999301433563},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.22450000047683716},{"id":"https://openalex.org/C42475967","wikidata":"https://www.wikidata.org/wiki/Q194292","display_name":"Operations research","level":1,"score":0.22050000727176666}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1016/j.procs.2026.01.114","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.procs.2026.01.114","pdf_url":null,"source":{"id":"https://openalex.org/S120348307","display_name":"Procedia Computer Science","issn_l":"1877-0509","issn":["1877-0509"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Procedia Computer Science","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1016/j.procs.2026.01.114","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.procs.2026.01.114","pdf_url":null,"source":{"id":"https://openalex.org/S120348307","display_name":"Procedia Computer Science","issn_l":"1877-0509","issn":["1877-0509"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Procedia Computer Science","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.6701900362968445,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W2471147443","https://openalex.org/W3001434439","https://openalex.org/W4240298715","https://openalex.org/W4412494174","https://openalex.org/W7125401531","https://openalex.org/W7131776457","https://openalex.org/W7131780096","https://openalex.org/W7131786946","https://openalex.org/W7131787181"],"related_works":[],"abstract_inverted_index":{"Converting":[0],"Dialectal":[1,102],"Arabic":[2,8,25,103],"(DA)":[3],"texts":[4,77],"into":[5],"Modern":[6],"Standard":[7],"(MSA)":[9],"is":[10,19],"considered":[11],"an":[12,183],"important":[13],"step":[14],"in":[15,60],"downstream":[16],"applications.":[17],"This":[18,106,123],"because":[20],"the":[21,55,72,91,96,132],"huge":[22],"diversity":[23],"of":[24,32,54,74,93,98,187],"dialects":[26],"leads":[27],"to":[28,70,78,104],"limited":[29],"available":[30],"resources":[31],"such":[33,82],"data.":[34],"Besides,":[35],"dealing":[36],"directly":[37],"with":[38,182],"DA":[39,76],"involves":[40],"multiple":[41],"complexities,":[42],"as":[43],"there":[44],"are":[45],"no":[46],"specialized":[47],"preprocessing":[48],"tools":[49],"designed":[50],"for":[51,81,131],"this":[52,87],"form":[53],"language.":[56],"The":[57,135,155],"recent":[58],"advances":[59],"Large":[61],"Language":[62],"Models":[63],"(LLMs)":[64],"sound":[65],"like":[66],"a":[67,83,127],"promising":[68],"technology":[69],"ease":[71],"process":[73,124],"translating":[75,99],"MSA,":[79],"particularly":[80],"low-resource":[84],"task.":[85],"In":[86],"paper,":[88],"we":[89],"evaluate":[90],"efficacy":[92],"LLMs":[94],"on":[95,139,175,191],"task":[97],"fine-grained":[100],"Saudi":[101,142,180],"MSA.":[105],"was":[107],"done":[108],"using":[109,159],"two":[110,140],"LLM-based":[111],"models,":[112],"namely":[113],"ALLaM":[114,171],"(a":[115,120,146,152],"multidialectal":[116],"model)":[117],"and":[118,150,165,189,193],"GPT-3.5":[119,174],"multilingual":[121],"model).":[122],"involved":[125],"designing":[126],"specific":[128],"prompt":[129],"framework":[130],"LLM":[133],"models.":[134],"experiments":[136],"were":[137,157],"conducted":[138],"different":[141,179],"dialect":[143],"datasets:":[144],"SauDial":[145,192],"newly":[147],"developed":[148],"dataset)":[149],"MADAR":[151],"benchmark":[153],"dataset).":[154],"results":[156],"evaluated":[158],"four":[160],"metrics:":[161],"BLEU,":[162],"TER,":[163],"METEOR,":[164],"COMET.":[166],"Our":[167],"findings":[168],"indicate":[169],"that":[170],"significantly":[172],"outperforms":[173],"both":[176],"datasets":[177],"across":[178],"dialects,":[181],"average":[184],"BLEU":[185],"score":[186],"53.17%":[188],"35.02%":[190],"MADAR,":[194],"respectively.":[195]},"counts_by_year":[],"updated_date":"2026-03-22T06:25:25.174409","created_date":"2026-03-21T00:00:00"}