{"id":"https://openalex.org/W7139946877","doi":"https://doi.org/10.1016/j.procs.2026.01.051","title":"Towards Better Machine Translation of Saudi Arabian Dialects: A Parallel Corpus and Comparative Evaluation of Different PLMs","display_name":"Towards Better Machine Translation of Saudi Arabian Dialects: A Parallel Corpus and Comparative Evaluation of Different PLMs","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7139946877","doi":"https://doi.org/10.1016/j.procs.2026.01.051"},"language":"en","primary_location":{"id":"doi:10.1016/j.procs.2026.01.051","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.procs.2026.01.051","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.2026.01.051","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5130236815","display_name":"Salwa Alahmari","orcid":null},"institutions":[{"id":"https://openalex.org/I130828816","display_name":"University of Leeds","ror":"https://ror.org/024mrxd33","country_code":"GB","type":"education","lineage":["https://openalex.org/I130828816"]},{"id":"https://openalex.org/I4210112337","display_name":"University of Hafr Al-Batin","ror":"https://ror.org/021jt1927","country_code":"SA","type":"education","lineage":["https://openalex.org/I4210112337"]}],"countries":["GB","SA"],"is_corresponding":true,"raw_author_name":"Salwa Alahmari","raw_affiliation_strings":["University of Hafr Albatain, Hafr Albatain, 31991, Saudi Arabia","University of Leeds, Woodhouse, Leeds, LS2 9JT, UK"],"affiliations":[{"raw_affiliation_string":"University of Hafr Albatain, Hafr Albatain, 31991, Saudi Arabia","institution_ids":["https://openalex.org/I4210112337"]},{"raw_affiliation_string":"University of Leeds, Woodhouse, Leeds, LS2 9JT, UK","institution_ids":["https://openalex.org/I130828816"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074817028","display_name":"Eric Atwell","orcid":"https://orcid.org/0000-0001-9395-3764"},"institutions":[{"id":"https://openalex.org/I130828816","display_name":"University of Leeds","ror":"https://ror.org/024mrxd33","country_code":"GB","type":"education","lineage":["https://openalex.org/I130828816"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Eric Atwell","raw_affiliation_strings":["University of Leeds, Woodhouse, Leeds, LS2 9JT, UK"],"affiliations":[{"raw_affiliation_string":"University of Leeds, Woodhouse, Leeds, LS2 9JT, UK","institution_ids":["https://openalex.org/I130828816"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130242964","display_name":"Ammar Alsalka","orcid":null},"institutions":[{"id":"https://openalex.org/I130828816","display_name":"University of Leeds","ror":"https://ror.org/024mrxd33","country_code":"GB","type":"education","lineage":["https://openalex.org/I130828816"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Ammar Alsalka","raw_affiliation_strings":["University of Leeds, Woodhouse, Leeds, LS2 9JT, UK"],"affiliations":[{"raw_affiliation_string":"University of Leeds, Woodhouse, Leeds, LS2 9JT, UK","institution_ids":["https://openalex.org/I130828816"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5087475658","display_name":"Hadeel Saadany","orcid":"https://orcid.org/0000-0002-2620-1842"},"institutions":[{"id":"https://openalex.org/I12870472","display_name":"Birmingham City University","ror":"https://ror.org/00t67pt25","country_code":"GB","type":"education","lineage":["https://openalex.org/I12870472"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Hadeel Saadany","raw_affiliation_strings":["Birmingham City University, Cardigan Street, Birmingham, B4 7BD, UK"],"affiliations":[{"raw_affiliation_string":"Birmingham City University, Cardigan Street, Birmingham, B4 7BD, UK","institution_ids":["https://openalex.org/I12870472"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5130236815"],"corresponding_institution_ids":["https://openalex.org/I130828816","https://openalex.org/I4210112337"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.72668495,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"275","issue":null,"first_page":"420","last_page":"428"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.6258999705314636,"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":0.6258999705314636,"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/T13912","display_name":"Language, Linguistics, Cultural Analysis","score":0.15129999816417694,"subfield":{"id":"https://openalex.org/subfields/1203","display_name":"Language and Linguistics"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T13629","display_name":"Text Readability and Simplification","score":0.02810000069439411,"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/machine-translation","display_name":"Machine translation","score":0.7328000068664551},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.47679999470710754},{"id":"https://openalex.org/keywords/parallel-corpora","display_name":"Parallel corpora","score":0.37470000982284546},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.3449000120162964},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.3021000027656555}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8978999853134155},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.7328000068664551},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6445000171661377},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6140999794006348},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.47679999470710754},{"id":"https://openalex.org/C2985367798","wikidata":"https://www.wikidata.org/wiki/Q1346592","display_name":"Parallel corpora","level":3,"score":0.37470000982284546},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3490000069141388},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3449000120162964},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3021000027656555},{"id":"https://openalex.org/C622187","wikidata":"https://www.wikidata.org/wiki/Q3500773","display_name":"BLEU","level":3,"score":0.2842000126838684},{"id":"https://openalex.org/C155092808","wikidata":"https://www.wikidata.org/wiki/Q182557","display_name":"Computational linguistics","level":2,"score":0.2639000117778778}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1016/j.procs.2026.01.051","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.procs.2026.01.051","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.2026.01.051","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.procs.2026.01.051","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":[{"display_name":"Quality Education","score":0.5037254691123962,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320317414","display_name":"University of Hafr Al Batin","ror":"https://ror.org/021jt1927"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W1984708705","https://openalex.org/W2101105183","https://openalex.org/W2250342921","https://openalex.org/W2739351760","https://openalex.org/W2915357442","https://openalex.org/W2970513828","https://openalex.org/W3114901634","https://openalex.org/W3202437782","https://openalex.org/W4291008710","https://openalex.org/W4404824230","https://openalex.org/W4412494174","https://openalex.org/W7131786946"],"related_works":[],"abstract_inverted_index":{"In":[0],"this":[1,28],"work":[2],"we":[3,30,66],"have":[4],"introduced":[5],"the":[6,14,60,84,99,104,115],"SADSLyC-E-MSA":[7,61],"corpus.":[8,62],"It":[9],"is":[10],"a":[11,120],"subset":[12],"of":[13,107,123],"SADSLyC":[15],"corpus":[16],"that":[17],"provides":[18],"English":[19],"and":[20,56,76,118],"Modern":[21],"Standard":[22],"Arabic":[23],"(MSA)":[24],"translations.":[25],"Based":[26],"on":[27,59],"corpus,":[29],"evaluated":[31],"three":[32],"Pretrained":[33],"Language":[34],"Models":[35],"(PLMs)":[36],"to":[37,41,48,103],"measure":[38],"their":[39],"ability":[40],"translate":[42],"textual":[43],"data":[44],"from":[45],"Saudi":[46,108],"Arabian":[47],"English.":[49],"The":[50,90,110],"evaluation":[51,82],"was":[52],"carried":[53],"out":[54],"before":[55],"after":[57],"fine-tuning":[58],"For":[63],"automatic":[64],"evaluation,":[65],"used":[67],"standard":[68],"Machine":[69],"translation":[70,96],"(MT)":[71],"metrics,":[72],"including":[73],"BLEU,":[74],"TER,":[75],"CHRF.":[77],"We":[78],"also":[79],"conducted":[80],"human":[81],"using":[83],"Multidimensional":[85],"Quality":[86],"Metrics":[87],"(MQM)":[88],"framework.":[89],"results":[91,117],"showed":[92],"clear":[93],"improvements":[94],"in":[95],"quality":[97],"once":[98],"models":[100],"were":[101],"adapted":[102],"linguistic":[105],"features":[106],"dialects.":[109],"Facebook":[111],"M2ML":[112],"model":[113],"produced":[114],"best":[116],"reached":[119],"BLEU":[121],"score":[122],"44.58.":[124]},"counts_by_year":[],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2026-03-21T00:00:00"}
