{"id":"https://openalex.org/W4385572935","doi":"https://doi.org/10.18653/v1/2022.wanlp-1.53","title":"Building an Ensemble of Transformer Models for Arabic Dialect Classification and Sentiment Analysis","display_name":"Building an Ensemble of Transformer Models for Arabic Dialect Classification and Sentiment Analysis","publication_year":2022,"publication_date":"2022-01-01","ids":{"openalex":"https://openalex.org/W4385572935","doi":"https://doi.org/10.18653/v1/2022.wanlp-1.53"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2022.wanlp-1.53","doi":"https://doi.org/10.18653/v1/2022.wanlp-1.53","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2022.wanlp-1.53","pdf_url":"https://aclanthology.org/2022.wanlp-1.53.pdf","source":{"id":"https://openalex.org/S7407085968","display_name":"Arabic Natural Language Processing Workshop (WANLP)","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":"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 the Seventh Arabic Natural Language Processing Workshop (WANLP)","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/2022.wanlp-1.53.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5092596414","display_name":"Abdullah Khered","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I185163786","display_name":"King Abdulaziz University","ror":"https://ror.org/02ma4wv74","country_code":"SA","type":"education","lineage":["https://openalex.org/I185163786"]},{"id":"https://openalex.org/I28407311","display_name":"University of Manchester","ror":"https://ror.org/027m9bs27","country_code":"GB","type":"education","lineage":["https://openalex.org/I28407311"]}],"countries":["GB","SA"],"is_corresponding":false,"raw_author_name":"Abdullah Khered","raw_affiliation_strings":["King Abdulaziz University, Saudi Arabia","The University of Manchester, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"King Abdulaziz University, Saudi Arabia","institution_ids":["https://openalex.org/I185163786"]},{"raw_affiliation_string":"The University of Manchester, UK","institution_ids":["https://openalex.org/I28407311"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5092596233","display_name":"Ingy Abdelhalim","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I28407311","display_name":"University of Manchester","ror":"https://ror.org/027m9bs27","country_code":"GB","type":"education","lineage":["https://openalex.org/I28407311"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Ingy Abdelhalim Abdelhalim","raw_affiliation_strings":["The University of Manchester, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Manchester, UK","institution_ids":["https://openalex.org/I28407311"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5050960711","display_name":"Riza Batista-Navarro","orcid":"https://orcid.org/0000-0001-6693-7531","observed_orcids":["https://orcid.org/0000-0001-6693-7531"]},"institutions":[{"id":"https://openalex.org/I28407311","display_name":"University of Manchester","ror":"https://ror.org/027m9bs27","country_code":"GB","type":"education","lineage":["https://openalex.org/I28407311"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Riza Batista-Navarro","raw_affiliation_strings":["The University of Manchester, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Manchester, UK","institution_ids":["https://openalex.org/I28407311"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.6907,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":{"value":0.72881422,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"479","last_page":"484"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.7964000105857849,"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/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.7964000105857849,"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":0.15880000591278076,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.009800000116229057,"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":0.8820000290870667},{"id":"https://openalex.org/keywords/arabic-sentiment-analysis","display_name":"Arabic sentiment analysis","score":0.8730000257492065},{"id":"https://openalex.org/keywords/ensemble-learning","display_name":"ensemble learning","score":0.722000002861023},{"id":"https://openalex.org/keywords/undersampling","display_name":"undersampling","score":0.5249999761581421},{"id":"https://openalex.org/keywords/masked-language-modeling","display_name":"masked language modeling","score":0.7390000224113464},{"id":"https://openalex.org/keywords/sequence-classification","display_name":"sequence classification","score":0.5709999799728394},{"id":"https://openalex.org/keywords/arabic-tweets","display_name":"Arabic tweets","score":0.5960000157356262}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7354553937911987},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.715050458908081},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6416956186294556},{"id":"https://openalex.org/C96455323","wikidata":"https://www.wikidata.org/wiki/Q13955","display_name":"Arabic","level":2,"score":0.6352958083152771},{"id":"https://openalex.org/C166955791","wikidata":"https://www.wikidata.org/wiki/Q629579","display_name":"Macro","level":2,"score":0.6203703284263611},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5857061743736267},{"id":"https://openalex.org/C45942800","wikidata":"https://www.wikidata.org/wiki/Q245652","display_name":"Ensemble learning","level":2,"score":0.5475609302520752},{"id":"https://openalex.org/C8642999","wikidata":"https://www.wikidata.org/wiki/Q4171168","display_name":"Hyperparameter","level":2,"score":0.5335355997085571},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5015766620635986},{"id":"https://openalex.org/C119898033","wikidata":"https://www.wikidata.org/wiki/Q3433888","display_name":"Ensemble forecasting","level":2,"score":0.5014646053314209},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.4824831783771515},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3495272994041443},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.16533026099205017},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08359336853027344},{"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.18653/v1/2022.wanlp-1.53","doi":"https://doi.org/10.18653/v1/2022.wanlp-1.53","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2022.wanlp-1.53","pdf_url":"https://aclanthology.org/2022.wanlp-1.53.pdf","source":{"id":"https://openalex.org/S7407085968","display_name":"Arabic Natural Language Processing Workshop (WANLP)","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":"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 the Seventh Arabic Natural Language Processing Workshop (WANLP)","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.atira.dk:openaire_cris_publications/13e688ef-2ce4-4d7b-a467-fb0094d0e872","doi":null,"is_oa":false,"landing_page_url":"https://research.manchester.ac.uk/en/publications/13e688ef-2ce4-4d7b-a467-fb0094d0e872","pdf_url":null,"source":{"id":"https://openalex.org/S4306400662","display_name":"Research Explorer (The University of Manchester)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I28407311","host_organization_name":"University of Manchester","host_organization_lineage":["https://openalex.org/I28407311"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Khered, A, Abdelhalim, I & Batista-Navarro, R 2022, Building an Ensemble of Transformer Models for Arabic Dialect Classification and Sentiment Analysis. in Wanlp 2022 7th Arabic Natural Language Processing Proceedings of the Workshop. https://doi.org/10.18653/v1/2022.wanlp-1.53","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"doi:10.18653/v1/2022.wanlp-1.53","doi":"https://doi.org/10.18653/v1/2022.wanlp-1.53","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2022.wanlp-1.53","pdf_url":"https://aclanthology.org/2022.wanlp-1.53.pdf","source":{"id":"https://openalex.org/S7407085968","display_name":"Arabic Natural Language Processing Workshop (WANLP)","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":"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 the Seventh Arabic Natural Language Processing Workshop (WANLP)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4385572935.pdf","grobid_xml":"https://content.openalex.org/works/W4385572935.grobid-xml"},"referenced_works_count":12,"referenced_works":["https://openalex.org/W1766594731","https://openalex.org/W2626778328","https://openalex.org/W2908840880","https://openalex.org/W2963341956","https://openalex.org/W3011718307","https://openalex.org/W3027457715","https://openalex.org/W3119566336","https://openalex.org/W3136657289","https://openalex.org/W3176169354","https://openalex.org/W4285289306","https://openalex.org/W4385573366","https://openalex.org/W4394657514"],"related_works":["https://openalex.org/W4385567174","https://openalex.org/W4385573020","https://openalex.org/W4385573141","https://openalex.org/W4385573054","https://openalex.org/W4389518440","https://openalex.org/W4389518207","https://openalex.org/W3119989085","https://openalex.org/W3135784975","https://openalex.org/W4389518310","https://openalex.org/W4389518365"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,7,55,73],"describe":[4],"the":[5,10,24,38,45,62,76,81,96,124,134,150,153,169],"approaches":[6,36],"developed":[8,35],"for":[9,80,103,109,130],"Nuanced":[11],"Arabic":[12,28,92],"Dialect":[13],"Identification":[14],"(NADI)":[15],"2022":[16],"shared":[17],"task,":[18],"which":[19,41,122],"consists":[20],"of":[21,26,61,90,95,126,144,174],"two":[22,39],"subtasks:":[23],"identification":[25],"country-level":[27],"dialects":[29],"and":[30,114,171],"sentiment":[31],"analysis.Our":[32],"team,":[33],"UniManc,":[34],"to":[37,58],"subtasks":[40],"are":[42],"underpinned":[43],"by":[44],"same":[46],"model:":[47],"a":[48,66,87,98,142,163],"pre-trained":[49],"MAR-BERT":[50],"language":[51,83],"model.For":[52],"Subtask":[53,71],"1,":[54],"applied":[56],"undersampling":[57],"create":[59],"versions":[60],"training":[63],"data":[64],"with":[65],"balanced":[67],"distribution":[68],"across":[69],"classes.For":[70],"2,":[72],"further":[74],"trained":[75],"original":[77],"MARBERT":[78,99],"model":[79,100,120,129,140,158],"masked":[82],"modelling":[84],"objective":[85],"using":[86,106],"NADIprovided":[88],"dataset":[89],"unlabelled":[91],"tweets.For":[93],"each":[94,131],"subtasks,":[97],"was":[101],"fine-tuned":[102],"sequence":[104],"classification,":[105],"different":[107],"values":[108],"hyperparameters":[110],"such":[111],"as":[112],"seed":[113],"learning":[115],"rate.This":[116],"resulted":[117],"in":[118,149],"multiple":[119],"variants,":[121],"formed":[123],"basis":[125],"an":[127],"ensemble":[128,139,157],"subtask.Based":[132],"on":[133],"official":[135],"NADI":[136],"evaluation,":[137],"our":[138,156],"obtained":[141],"macro-F1-score":[143],"26.863,":[145],"ranking":[146],"second":[147,154],"overall":[148],"first":[151],"subtask.In":[152],"subtask,":[155],"also":[159],"ranked":[160],"second,":[161],"obtaining":[162],"macro-F1-PN":[164],"score":[165],"(macro-averaged":[166],"F1-score":[167],"over":[168],"Positive":[170],"Negative":[172],"classes)":[173],"73.544.":[175]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":4}],"updated_date":"2026-10-30T12:39:25.321706","created_date":"2023-08-05T00:00:00"}