{"id":"https://openalex.org/W4406302399","doi":"https://doi.org/10.1145/3712060","title":"Natural Language Processing for Dialects of a Language: A Survey","display_name":"Natural Language Processing for Dialects of a Language: A Survey","publication_year":2025,"publication_date":"2025-01-13","ids":{"openalex":"https://openalex.org/W4406302399","doi":"https://doi.org/10.1145/3712060"},"language":"en","primary_location":{"id":"doi:10.1145/3712060","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3712060","pdf_url":null,"source":{"id":"https://openalex.org/S157921468","display_name":"ACM Computing Surveys","issn_l":"0360-0300","issn":["0360-0300","1557-7341"],"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-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Computing Surveys","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1145/3712060","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5059529586","display_name":"Aditya Joshi","orcid":"https://orcid.org/0000-0003-2200-9703"},"institutions":[{"id":"https://openalex.org/I31746571","display_name":"UNSW Sydney","ror":"https://ror.org/03r8z3t63","country_code":"AU","type":"education","lineage":["https://openalex.org/I31746571"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Aditya Joshi","raw_affiliation_strings":["University of New South Wales, Sydney, Australia","School of Computer Science and Engineering, University of New South Wales, Sydney, Australia"],"raw_orcid":"https://orcid.org/0000-0003-2200-9703","affiliations":[{"raw_affiliation_string":"University of New South Wales, Sydney, Australia","institution_ids":["https://openalex.org/I31746571"]},{"raw_affiliation_string":"School of Computer Science and Engineering, University of New South Wales, Sydney, Australia","institution_ids":["https://openalex.org/I31746571"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077362985","display_name":"Raj Dabre","orcid":"https://orcid.org/0000-0003-0664-3421"},"institutions":[{"id":"https://openalex.org/I90023481","display_name":"National Institute of Information and Communications Technology","ror":"https://ror.org/016bgq349","country_code":"JP","type":"facility","lineage":["https://openalex.org/I90023481"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Raj Dabre","raw_affiliation_strings":["National Institute of Information and Communications Technology, Koganei, Japan"],"raw_orcid":"https://orcid.org/0000-0003-0664-3421","affiliations":[{"raw_affiliation_string":"National Institute of Information and Communications Technology, Koganei, Japan","institution_ids":["https://openalex.org/I90023481"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054401662","display_name":"Diptesh Kanojia","orcid":"https://orcid.org/0000-0001-8814-0080"},"institutions":[{"id":"https://openalex.org/I28290843","display_name":"University of Surrey","ror":"https://ror.org/00ks66431","country_code":"GB","type":"education","lineage":["https://openalex.org/I28290843"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Diptesh Kanojia","raw_affiliation_strings":["University of Surrey, Guildford, United Kingdom of Great Britain and Northern Ireland"],"raw_orcid":"https://orcid.org/0000-0001-8814-0080","affiliations":[{"raw_affiliation_string":"University of Surrey, Guildford, United Kingdom of Great Britain and Northern Ireland","institution_ids":["https://openalex.org/I28290843"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078198028","display_name":"Zhuang Li","orcid":"https://orcid.org/0000-0002-9808-9992"},"institutions":[{"id":"https://openalex.org/I56590836","display_name":"Monash University","ror":"https://ror.org/02bfwt286","country_code":"AU","type":"education","lineage":["https://openalex.org/I56590836"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Zhuang Li","raw_affiliation_strings":["Monash University, Clayton, Australia"],"raw_orcid":"https://orcid.org/0000-0002-9808-9992","affiliations":[{"raw_affiliation_string":"Monash University, Clayton, Australia","institution_ids":["https://openalex.org/I56590836"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043429023","display_name":"Haolan Zhan","orcid":"https://orcid.org/0000-0001-9628-5992"},"institutions":[{"id":"https://openalex.org/I56590836","display_name":"Monash University","ror":"https://ror.org/02bfwt286","country_code":"AU","type":"education","lineage":["https://openalex.org/I56590836"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Haolan Zhan","raw_affiliation_strings":["Monash University, Clayton, Australia"],"raw_orcid":"https://orcid.org/0000-0001-9628-5992","affiliations":[{"raw_affiliation_string":"Monash University, Clayton, Australia","institution_ids":["https://openalex.org/I56590836"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081525024","display_name":"Gholamreza Haffari","orcid":"https://orcid.org/0000-0001-7326-8380"},"institutions":[{"id":"https://openalex.org/I56590836","display_name":"Monash University","ror":"https://ror.org/02bfwt286","country_code":"AU","type":"education","lineage":["https://openalex.org/I56590836"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Gholamreza Haffari","raw_affiliation_strings":["Information Technology, Monash University, Clayton, Australia"],"raw_orcid":"https://orcid.org/0000-0001-7326-8380","affiliations":[{"raw_affiliation_string":"Information Technology, Monash University, Clayton, Australia","institution_ids":["https://openalex.org/I56590836"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5028615011","display_name":"Doris Dippold","orcid":"https://orcid.org/0000-0001-6193-4710"},"institutions":[{"id":"https://openalex.org/I28290843","display_name":"University of Surrey","ror":"https://ror.org/00ks66431","country_code":"GB","type":"education","lineage":["https://openalex.org/I28290843"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Doris Dippold","raw_affiliation_strings":["University of Surrey, Guildford, United Kingdom of Great Britain and Northern Ireland","University of Surrey, Guildford United Kingdom of Great Britain and Northern Ireland"],"raw_orcid":"https://orcid.org/0000-0001-6193-4710","affiliations":[{"raw_affiliation_string":"University of Surrey, Guildford, United Kingdom of Great Britain and Northern Ireland","institution_ids":["https://openalex.org/I28290843"]},{"raw_affiliation_string":"University of Surrey, Guildford United Kingdom of Great Britain and Northern Ireland","institution_ids":["https://openalex.org/I28290843"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":47.5772,"has_fulltext":false,"cited_by_count":37,"citation_normalized_percentile":{"value":0.99837037,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"57","issue":"6","first_page":"1","last_page":"37"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9991999864578247,"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/T12031","display_name":"Speech and dialogue systems","score":0.9958999752998352,"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/computer-science","display_name":"Computer science","score":0.8976185321807861},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.521125853061676},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.46316421031951904},{"id":"https://openalex.org/keywords/universal-networking-language","display_name":"Universal Networking Language","score":0.43836066126823425},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.4080498516559601},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3707868158817291},{"id":"https://openalex.org/keywords/comprehension-approach","display_name":"Comprehension approach","score":0.14149940013885498}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8976185321807861},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.521125853061676},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.46316421031951904},{"id":"https://openalex.org/C83479923","wikidata":"https://www.wikidata.org/wiki/Q2063748","display_name":"Universal Networking Language","level":4,"score":0.43836066126823425},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.4080498516559601},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3707868158817291},{"id":"https://openalex.org/C129353971","wikidata":"https://www.wikidata.org/wiki/Q5156949","display_name":"Comprehension approach","level":3,"score":0.14149940013885498}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3712060","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3712060","pdf_url":null,"source":{"id":"https://openalex.org/S157921468","display_name":"ACM Computing Surveys","issn_l":"0360-0300","issn":["0360-0300","1557-7341"],"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-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Computing Surveys","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1145/3712060","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3712060","pdf_url":null,"source":{"id":"https://openalex.org/S157921468","display_name":"ACM Computing Surveys","issn_l":"0360-0300","issn":["0360-0300","1557-7341"],"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-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Computing Surveys","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.8299999833106995}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":162,"referenced_works":["https://openalex.org/W39243977","https://openalex.org/W389873184","https://openalex.org/W617010958","https://openalex.org/W1565004263","https://openalex.org/W1995117577","https://openalex.org/W2019049145","https://openalex.org/W2027249790","https://openalex.org/W2040522630","https://openalex.org/W2040809579","https://openalex.org/W2064334160","https://openalex.org/W2071638553","https://openalex.org/W2082621521","https://openalex.org/W2123777430","https://openalex.org/W2149609556","https://openalex.org/W2155939044","https://openalex.org/W2162019804","https://openalex.org/W2168576900","https://openalex.org/W2168677000","https://openalex.org/W2187074748","https://openalex.org/W2250224884","https://openalex.org/W2250378459","https://openalex.org/W2250929644","https://openalex.org/W2251882277","https://openalex.org/W2252027930","https://openalex.org/W2321588627","https://openalex.org/W2560280095","https://openalex.org/W2568775501","https://openalex.org/W2581304338","https://openalex.org/W2740303418","https://openalex.org/W2740432722","https://openalex.org/W2740452944","https://openalex.org/W2741636242","https://openalex.org/W2742019041","https://openalex.org/W2753894810","https://openalex.org/W2766894774","https://openalex.org/W2773205243","https://openalex.org/W2788190679","https://openalex.org/W2799060650","https://openalex.org/W2799159261","https://openalex.org/W2889983522","https://openalex.org/W2945836255","https://openalex.org/W2946940662","https://openalex.org/W2948433920","https://openalex.org/W2949429724","https://openalex.org/W2949678053","https://openalex.org/W2956292147","https://openalex.org/W2962937786","https://openalex.org/W2963764322","https://openalex.org/W2964085300","https://openalex.org/W2964235839","https://openalex.org/W2964291542","https://openalex.org/W2971281071","https://openalex.org/W2983778987","https://openalex.org/W3011554092","https://openalex.org/W3015124543","https://openalex.org/W3019239186","https://openalex.org/W3022161378","https://openalex.org/W3023579893","https://openalex.org/W3032380180","https://openalex.org/W3032388710","https://openalex.org/W3035283133","https://openalex.org/W3035522762","https://openalex.org/W3049565363","https://openalex.org/W3087927280","https://openalex.org/W3088435620","https://openalex.org/W3099559062","https://openalex.org/W3101509145","https://openalex.org/W3109540321","https://openalex.org/W3113440070","https://openalex.org/W3115583443","https://openalex.org/W3118036215","https://openalex.org/W3118871174","https://openalex.org/W3119259767","https://openalex.org/W3119993964","https://openalex.org/W3130792169","https://openalex.org/W3132753207","https://openalex.org/W3133980122","https://openalex.org/W3137109387","https://openalex.org/W3149627794","https://openalex.org/W3154491711","https://openalex.org/W3155756977","https://openalex.org/W3165977309","https://openalex.org/W3168046227","https://openalex.org/W3170666909","https://openalex.org/W3172917028","https://openalex.org/W3173785189","https://openalex.org/W3199226759","https://openalex.org/W3205231356","https://openalex.org/W4206375159","https://openalex.org/W4206735990","https://openalex.org/W4213093409","https://openalex.org/W4213173126","https://openalex.org/W4220713074","https://openalex.org/W4226069095","https://openalex.org/W4226263264","https://openalex.org/W4241945531","https://openalex.org/W4283165820","https://openalex.org/W4283168161","https://openalex.org/W4285060468","https://openalex.org/W4285123703","https://openalex.org/W4300167661","https://openalex.org/W4313953038","https://openalex.org/W4360764659","https://openalex.org/W4367677331","https://openalex.org/W4376122741","https://openalex.org/W4382202606","https://openalex.org/W4383212185","https://openalex.org/W4384642442","https://openalex.org/W4385566981","https://openalex.org/W4385570044","https://openalex.org/W4385570741","https://openalex.org/W4385570931","https://openalex.org/W4385572447","https://openalex.org/W4385572518","https://openalex.org/W4385572553","https://openalex.org/W4385572903","https://openalex.org/W4385572938","https://openalex.org/W4385573024","https://openalex.org/W4385573029","https://openalex.org/W4385573226","https://openalex.org/W4385573229","https://openalex.org/W4385573366","https://openalex.org/W4385573620","https://openalex.org/W4385823406","https://openalex.org/W4386566352","https://openalex.org/W4386566378","https://openalex.org/W4386576673","https://openalex.org/W4386579991","https://openalex.org/W4389518436","https://openalex.org/W4389518652","https://openalex.org/W4389518885","https://openalex.org/W4389519034","https://openalex.org/W4389519066","https://openalex.org/W4389520516","https://openalex.org/W4389523697","https://openalex.org/W4389524079","https://openalex.org/W4389954479","https://openalex.org/W4390740007","https://openalex.org/W4391987896","https://openalex.org/W4392428647","https://openalex.org/W4401042168","https://openalex.org/W4401043309","https://openalex.org/W4401044106","https://openalex.org/W4402227506","https://openalex.org/W4402671267","https://openalex.org/W4402671319","https://openalex.org/W4403172489","https://openalex.org/W4404781065","https://openalex.org/W4404781215","https://openalex.org/W4404781252","https://openalex.org/W4404781528","https://openalex.org/W4404782299","https://openalex.org/W4404782409","https://openalex.org/W4404782614","https://openalex.org/W4404782765","https://openalex.org/W4404782906","https://openalex.org/W4404782954","https://openalex.org/W4404792927","https://openalex.org/W6684503276","https://openalex.org/W6747891361","https://openalex.org/W6775573524","https://openalex.org/W6854475153"],"related_works":["https://openalex.org/W3204019825","https://openalex.org/W3213549959","https://openalex.org/W4226226396","https://openalex.org/W2913520953","https://openalex.org/W4310801723","https://openalex.org/W3153750606","https://openalex.org/W2383292628","https://openalex.org/W4308854837","https://openalex.org/W2551652406","https://openalex.org/W2401646948"],"abstract_inverted_index":{"State-of-the-art":[0],"natural":[1,82,99],"language":[2,53,83,100,171,188],"processing":[3],"(NLP)":[4],"models":[5,42],"are":[6],"trained":[7],"on":[8,17,169],"massive":[9],"training":[10],"corpora,":[11],"and":[12,46,67,95,98,107,142,147,194],"report":[13],"a":[14,33,71],"superlative":[15],"performance":[16,38],"evaluation":[18],"datasets.":[19],"This":[20],"survey":[21,56,111,177],"delves":[22],"into":[23],"an":[24],"important":[25],"attribute":[26],"of":[27,32,40,52,65,74,79,118],"these":[28,151],"datasets:":[29],"the":[30,37,50,163],"dialect":[31,90,140],"language.":[34],"Motivated":[35],"by":[36,190],"degradation":[39],"NLP":[41,60,75,133,182],"for":[43,49,61],"dialectal":[44],"datasets":[45],"its":[47,116],"implications":[48],"equity":[51],"technologies,":[54],"we":[55,153],"past":[57,130],"research":[58],"in":[59,63,77,115,132,185],"dialects":[62,135],"terms":[64,78],"datasets,":[66],"approaches.":[68],"We":[69,127,173],"describe":[70,154],"wide":[72],"range":[73],"tasks":[76,87],"two":[80],"categories:":[81],"understanding":[84],"(NLU)":[85],"(for":[86,103],"such":[88],"as":[89],"classification,":[91,141],"sentiment":[92],"analysis,":[93],"parsing,":[94],"NLU":[96,146],"benchmarks)":[97],"generation":[101],"(NLG)":[102],"summarisation,":[104],"machine":[105,156],"translation,":[106],"dialogue":[108],"systems).":[109],"The":[110],"is":[112],"also":[113],"broad":[114],"coverage":[117],"languages":[119],"which":[120],"include":[121],"English,":[122],"Arabic,":[123],"German,":[124],"among":[125],"others.":[126],"observe":[128],"that":[129,175],"work":[131],"concerning":[134],"goes":[136],"deeper":[137],"than":[138],"mere":[139],"extends":[143],"to":[144,181],"several":[145],"NLG":[148],"tasks.":[149],"For":[150],"tasks,":[152],"classical":[155],"learning":[157],"using":[158],"statistical":[159],"models,":[160],"along":[161],"with":[162],"recent":[164],"deep":[165],"learning-based":[166],"approaches":[167],"based":[168],"pre-trained":[170],"models.":[172],"expect":[174],"this":[176],"will":[178],"be":[179],"useful":[180],"researchers":[183],"interested":[184],"building":[186],"equitable":[187],"technologies":[189],"rethinking":[191],"LLM":[192],"benchmarks":[193],"model":[195],"architectures.":[196]},"counts_by_year":[{"year":2026,"cited_by_count":17},{"year":2025,"cited_by_count":20}],"updated_date":"2026-07-18T07:39:51.176621","created_date":"2025-10-10T00:00:00"}