{"id":"https://openalex.org/W4389518330","doi":"https://doi.org/10.18653/v1/2023.arabicnlp-1.30","title":"Arabic dialect identification: An in-depth error analysis on the MADAR parallel corpus","display_name":"Arabic dialect identification: An in-depth error analysis on the MADAR parallel corpus","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4389518330","doi":"https://doi.org/10.18653/v1/2023.arabicnlp-1.30"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2023.arabicnlp-1.30","doi":"https://doi.org/10.18653/v1/2023.arabicnlp-1.30","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2023.arabicnlp-1.30","pdf_url":"https://aclanthology.org/2023.arabicnlp-1.30.pdf","source":{"id":"https://openalex.org/S7407104720","display_name":"Arabic Natural Language Processing Conference (ArabicNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of ArabicNLP 2023","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://aclanthology.org/2023.arabicnlp-1.30.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5080292445","display_name":"Helene Olsen","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I184942183","display_name":"University of Oslo","ror":"https://ror.org/01xtthb56","country_code":"NO","type":"education","lineage":["https://openalex.org/I184942183"]}],"countries":["NO"],"is_corresponding":false,"raw_author_name":"Helene Olsen","raw_affiliation_strings":["University of Oslo"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Oslo","institution_ids":["https://openalex.org/I184942183"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057619458","display_name":"Samia Touileb","orcid":"https://orcid.org/0000-0003-4584-2554","observed_orcids":["https://orcid.org/0000-0003-4584-2554"]},"institutions":[{"id":"https://openalex.org/I4432739","display_name":"University of Bergen","ror":"https://ror.org/03zga2b32","country_code":"NO","type":"education","lineage":["https://openalex.org/I4432739"]}],"countries":["NO"],"is_corresponding":false,"raw_author_name":"Samia Touileb","raw_affiliation_strings":["University of Bergen"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Bergen","institution_ids":["https://openalex.org/I4432739"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5080146945","display_name":"Erik Velldal","orcid":"https://orcid.org/0009-0008-6479-4512","observed_orcids":["https://orcid.org/0009-0008-6479-4512"]},"institutions":[{"id":"https://openalex.org/I184942183","display_name":"University of Oslo","ror":"https://ror.org/01xtthb56","country_code":"NO","type":"education","lineage":["https://openalex.org/I184942183"]}],"countries":["NO"],"is_corresponding":false,"raw_author_name":"Erik Velldal","raw_affiliation_strings":["University of Oslo"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Oslo","institution_ids":["https://openalex.org/I184942183"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.532,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.65900439,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"370","last_page":"384"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9032999873161316,"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":0.9032999873161316,"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":0.03200000151991844,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.012500000186264515,"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/arabic-dialect-identification","display_name":"Arabic dialect identification","score":0.9940000176429749},{"id":"https://openalex.org/keywords/error-analysis","display_name":"error analysis","score":0.8090000152587891},{"id":"https://openalex.org/keywords/naive-bayes","display_name":"naive Bayes","score":0.7770000100135803}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8108245134353638},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7497117519378662},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6774108409881592},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.6221782565116882},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.5987430214881897},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.5822465419769287},{"id":"https://openalex.org/C96455323","wikidata":"https://www.wikidata.org/wiki/Q13955","display_name":"Arabic","level":2,"score":0.558729350566864},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5167252421379089},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4611632227897644},{"id":"https://openalex.org/C63882131","wikidata":"https://www.wikidata.org/wiki/Q17122954","display_name":"Strengths and weaknesses","level":2,"score":0.45732489228248596},{"id":"https://openalex.org/C52001869","wikidata":"https://www.wikidata.org/wiki/Q812530","display_name":"Naive Bayes classifier","level":3,"score":0.433459609746933},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.26464664936065674},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.06682729721069336},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.18653/v1/2023.arabicnlp-1.30","doi":"https://doi.org/10.18653/v1/2023.arabicnlp-1.30","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2023.arabicnlp-1.30","pdf_url":"https://aclanthology.org/2023.arabicnlp-1.30.pdf","source":{"id":"https://openalex.org/S7407104720","display_name":"Arabic Natural Language Processing Conference (ArabicNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of ArabicNLP 2023","raw_type":"proceedings-article"},{"id":"pmh:oai:www.duo.uio.no:10852/108235","doi":null,"is_oa":true,"landing_page_url":"http://hdl.handle.net/10852/108235","pdf_url":null,"source":{"id":"https://openalex.org/S7407064446","display_name":"NORA - Norwegian Open Research Archives","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"978-1-959429-27-2","raw_type":"info:eu-repo/semantics/bookPart"}],"best_oa_location":{"id":"doi:10.18653/v1/2023.arabicnlp-1.30","doi":"https://doi.org/10.18653/v1/2023.arabicnlp-1.30","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2023.arabicnlp-1.30","pdf_url":"https://aclanthology.org/2023.arabicnlp-1.30.pdf","source":{"id":"https://openalex.org/S7407104720","display_name":"Arabic Natural Language Processing Conference (ArabicNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of ArabicNLP 2023","raw_type":"proceedings-article"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[{"score":0.8199999928474426,"id":"https://metadata.un.org/sdg/4","display_name":"Quality education"}],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4389518330.pdf","grobid_xml":"https://content.openalex.org/works/W4389518330.grobid-xml"},"referenced_works_count":37,"referenced_works":["https://openalex.org/W1978174332","https://openalex.org/W2109704865","https://openalex.org/W2115295410","https://openalex.org/W2160802179","https://openalex.org/W2210153255","https://openalex.org/W2250278916","https://openalex.org/W2250783208","https://openalex.org/W2251986002","https://openalex.org/W2295824561","https://openalex.org/W2329255937","https://openalex.org/W2527936838","https://openalex.org/W2805089673","https://openalex.org/W2806092253","https://openalex.org/W2806962830","https://openalex.org/W2812315852","https://openalex.org/W2914220664","https://openalex.org/W2963341956","https://openalex.org/W2970511310","https://openalex.org/W2970513828","https://openalex.org/W2971130934","https://openalex.org/W3008110149","https://openalex.org/W3032746405","https://openalex.org/W3119566336","https://openalex.org/W3119989085","https://openalex.org/W3120439194","https://openalex.org/W3120535942","https://openalex.org/W3134155512","https://openalex.org/W3135784975","https://openalex.org/W3154100567","https://openalex.org/W3154301048","https://openalex.org/W3176169354","https://openalex.org/W4211260480","https://openalex.org/W4385572802","https://openalex.org/W4385573366","https://openalex.org/W4386566370","https://openalex.org/W4394657514","https://openalex.org/W7131817604"],"related_works":["https://openalex.org/W7056921136","https://openalex.org/W4224289022","https://openalex.org/W7217839369","https://openalex.org/W4318567029","https://openalex.org/W2971355343","https://openalex.org/W4288273224","https://openalex.org/W2971261861","https://openalex.org/W2978948973","https://openalex.org/W2971054893","https://openalex.org/W2970072401"],"abstract_inverted_index":{"This":[0],"paper":[1],"provides":[2],"a":[3,42,48],"systematic":[4],"analysis":[5,79],"and":[6,60,73],"comparison":[7],"of":[8,11,17,45,62,77,94,107],"the":[9,15,23,58,91,95,108,112],"performance":[10],"state-of-theart":[12],"models":[13,34,40],"on":[14,30],"task":[16],"fine-grained":[18],"Arabic":[19],"dialect":[20,88],"identification":[21],"using":[22],"MADAR":[24],"parallel":[25],"corpus.We":[26],"test":[27,92],"approaches":[28,110],"based":[29],"pretrained":[31],"transformer":[32],"language":[33],"in":[35,90],"addition":[36],"to":[37,71],"Naive":[38],"Bayes":[39],"with":[41,84],"rich":[43],"set":[44,93],"various":[46],"features.Through":[47],"comprehensive":[49],"data-and":[50],"error":[51],"analysis,":[52],"we":[53],"provide":[54],"valuable":[55],"insights":[56],"into":[57],"strengths":[59],"weaknesses":[61],"both":[63],"approaches.We":[64],"discuss":[65],"which":[66,98],"dialects":[67],"are":[68],"more":[69],"challenging":[70],"differentiate,":[72],"identify":[74],"potential":[75],"sources":[76],"errors.Our":[78],"reveals":[80],"an":[81],"important":[82],"problem":[83],"identical":[85],"sentences":[86],"across":[87],"classes":[89],"MADAR-26":[96],"corpus,":[97],"may":[99],"confuse":[100],"any":[101],"classifier.We":[102],"also":[103],"show":[104],"that":[105],"none":[106],"tested":[109],"captures":[111],"subtle":[113],"distinctions":[114],"between":[115],"closely":[116],"related":[117],"dialects.":[118]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-10-27T15:51:10.671819","created_date":"2023-12-10T00:00:00"}