{"id":"https://openalex.org/W4412886684","doi":"https://doi.org/10.18653/v1/2025.acl-long.166","title":"Revisiting Common Assumptions about Arabic Dialects in NLP","display_name":"Revisiting Common Assumptions about Arabic Dialects in NLP","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412886684","doi":"https://doi.org/10.18653/v1/2025.acl-long.166"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.acl-long.166","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.166","pdf_url":"https://aclanthology.org/2025.acl-long.166.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 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.acl-long.166.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5057409392","display_name":"Amr Keleg","orcid":"https://orcid.org/0000-0001-5772-9626"},"institutions":[{"id":"https://openalex.org/I4210107233","display_name":"Language Science (South Korea)","ror":"https://ror.org/01h9v1373","country_code":"KR","type":"company","lineage":["https://openalex.org/I4210107233"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Amr Keleg","raw_affiliation_strings":["Institute for Language , Cognition and Computation School of Informatics , University of Edinburgh"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Language , Cognition and Computation School of Informatics , University of Edinburgh","institution_ids":["https://openalex.org/I4210107233"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075564798","display_name":"Sharon Goldwater","orcid":"https://orcid.org/0000-0002-7298-0947"},"institutions":[{"id":"https://openalex.org/I4210107233","display_name":"Language Science (South Korea)","ror":"https://ror.org/01h9v1373","country_code":"KR","type":"company","lineage":["https://openalex.org/I4210107233"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Sharon Goldwater","raw_affiliation_strings":["Institute for Language , Cognition and Computation School of Informatics , University of Edinburgh"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Language , Cognition and Computation School of Informatics , University of Edinburgh","institution_ids":["https://openalex.org/I4210107233"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070783596","display_name":"Walid Magdy","orcid":"https://orcid.org/0000-0001-9676-1338"},"institutions":[{"id":"https://openalex.org/I4210107233","display_name":"Language Science (South Korea)","ror":"https://ror.org/01h9v1373","country_code":"KR","type":"company","lineage":["https://openalex.org/I4210107233"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Walid Magdy","raw_affiliation_strings":["Institute for Language , Cognition and Computation School of Informatics , University of Edinburgh"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Language , Cognition and Computation School of Informatics , University of Edinburgh","institution_ids":["https://openalex.org/I4210107233"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.75,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.876904,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"3309","last_page":"3327"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9957000017166138,"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":0.9957000017166138,"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":0.9455000162124634,"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/natural-language-processing","display_name":"Natural language processing","score":0.773833155632019},{"id":"https://openalex.org/keywords/arabic","display_name":"Arabic","score":0.7288214564323425},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7214822769165039},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7139822840690613},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.5512852072715759},{"id":"https://openalex.org/keywords/philosophy","display_name":"Philosophy","score":0.09190675616264343}],"concepts":[{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.773833155632019},{"id":"https://openalex.org/C96455323","wikidata":"https://www.wikidata.org/wiki/Q13955","display_name":"Arabic","level":2,"score":0.7288214564323425},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7214822769165039},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7139822840690613},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.5512852072715759},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.09190675616264343}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/v1/2025.acl-long.166","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.166","pdf_url":"https://aclanthology.org/2025.acl-long.166.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 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.ed.ac.uk:openaire/5e2dbdf0-93a6-4833-8257-303abe6baca1","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/5e2dbdf0-93a6-4833-8257-303abe6baca1","pdf_url":"https://www.research.ed.ac.uk/files/530937371/KelegEtalACL25RevisitingCommon.pdf","source":{"id":"https://openalex.org/S4406922455","display_name":"Edinburgh Research Explorer","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Keleg, A, Goldwater, S & Magdy, W 2025, Revisiting common assumptions about Arabic dialects in NLP. in W Che, J Nabende, E Shutova & M T Pilehvar (eds), Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics - Volume 1 : Long Papers. Annual Meeting of the Association for Computational Linguistics, Kerrville, TX, USA, pp. 3309-3327, The 63rd Annual Meeting of the Association for Computational Linguistics, Vienna, Austria, 27/07/25. < https://aclanthology.org/2025.acl-long.166/ >","raw_type":"contributionToPeriodical"},{"id":"pmh:oai:pure.ed.ac.uk:publications/5e2dbdf0-93a6-4833-8257-303abe6baca1","is_oa":true,"landing_page_url":"https://hdl.handle.net/20.500.11820/5e2dbdf0-93a6-4833-8257-303abe6baca1","pdf_url":"https://www.pure.ed.ac.uk/ws/files/530937371/KelegEtalACL25RevisitingCommon.pdf","source":{"id":"https://openalex.org/S4406922455","display_name":"Edinburgh Research Explorer","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Keleg, A, Goldwater, S & Magdy, W 2025, Revisiting common assumptions about Arabic dialects in NLP. in W Che, J Nabende, E Shutova & M T Pilehvar (eds), Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics - Volume 1 : Long Papers. Annual Meeting of the Association for Computational Linguistics, Kerrville, TX, USA, pp. 3309-3327, The 63rd Annual Meeting of the Association for Computational Linguistics, Vienna, Austria, 27/07/25. < https://aclanthology.org/2025.acl-long.166/ >","raw_type":"contributionToPeriodical"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.acl-long.166","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.166","pdf_url":"https://aclanthology.org/2025.acl-long.166.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 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.4300000071525574}],"awards":[{"id":"https://openalex.org/G373773752","display_name":null,"funder_award_id":"EP/S022481/1","funder_id":"https://openalex.org/F4320314731","funder_display_name":"UK Research and Innovation"}],"funders":[{"id":"https://openalex.org/F4320314731","display_name":"UK Research and Innovation","ror":"https://ror.org/001aqnf71"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412886684.pdf","grobid_xml":"https://content.openalex.org/works/W4412886684.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"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":{"Arabic":[0,44,113],"has":[1],"diverse":[2],"dialects,":[3],"where":[4,69],"one":[5],"dialect":[6],"can":[7,28],"be":[8,29,107],"substantially":[9],"different":[10,39,77,112],"from":[11],"the":[12,14,70,91],"others.In":[13],"NLP":[15,114],"literature,":[16],"some":[17,97],"assumptions":[18,49,58,93],"about":[19],"these":[20,48,57,86],"dialects":[21,27,79],"are":[22,36,50,100],"widely":[23],"adopted":[24],"(e.g.,":[25],"\"Arabic":[26],"grouped":[30],"into":[31],"distinguishable":[32],"regional":[33],"dialects\")":[34],"and":[35,59,64,96],"manifested":[37],"in":[38,75,104,111],"computational":[40],"tasks":[41],"such":[42],"as":[43],"Dialect":[45],"Identification":[46],"(ADI).However,":[47],"not":[51,101],"quantitatively":[52],"verified.We":[53],"identify":[54],"four":[55,92],"of":[56,72,85,98],"examine":[60],"them":[61,99],"by":[62,83],"extending":[63],"analyzing":[65],"a":[66],"multi-label":[67],"dataset,":[68],"validity":[71],"each":[73],"sentence":[74],"11":[76],"country-level":[78],"is":[80],"manually":[81],"assessed":[82],"speakers":[84],"dialects.Our":[87],"analysis":[88],"indicates":[89],"that":[90],"oversimplify":[94],"reality,":[95],"always":[102],"accurate.This":[103],"turn":[105],"might":[106],"hindering":[108],"further":[109],"progress":[110],"tasks.":[115]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-06-12T08:23:45.883708","created_date":"2025-10-10T00:00:00"}