{"id":"https://openalex.org/W4389518279","doi":"https://doi.org/10.18653/v1/2023.arabicnlp-1.20","title":"Octopus: A Multitask Model and Toolkit for Arabic Natural Language Generation","display_name":"Octopus: A Multitask Model and Toolkit for Arabic Natural Language Generation","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4389518279","doi":"https://doi.org/10.18653/v1/2023.arabicnlp-1.20"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2023.arabicnlp-1.20","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2023.arabicnlp-1.20","pdf_url":"https://aclanthology.org/2023.arabicnlp-1.20.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 ArabicNLP 2023","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2023.arabicnlp-1.20.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5025365353","display_name":"AbdelRahim Elmadany","orcid":null},"institutions":[{"id":"https://openalex.org/I141945490","display_name":"University of British Columbia","ror":"https://ror.org/03rmrcq20","country_code":"CA","type":"education","lineage":["https://openalex.org/I141945490"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"AbdelRahim Elmadany","raw_affiliation_strings":["\u03be Deep Learning & Natural Language Processing Group, The University of British Columbia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"\u03be Deep Learning & Natural Language Processing Group, The University of British Columbia","institution_ids":["https://openalex.org/I141945490"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041553790","display_name":"El Moatez Billah Nagoudi","orcid":null},"institutions":[{"id":"https://openalex.org/I141945490","display_name":"University of British Columbia","ror":"https://ror.org/03rmrcq20","country_code":"CA","type":"education","lineage":["https://openalex.org/I141945490"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"El Moatez Billah Nagoudi","raw_affiliation_strings":["\u03be Deep Learning & Natural Language Processing Group, The University of British Columbia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"\u03be Deep Learning & Natural Language Processing Group, The University of British Columbia","institution_ids":["https://openalex.org/I141945490"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004629670","display_name":"Muhammad Abdul-Mageed","orcid":"https://orcid.org/0000-0002-8590-2040"},"institutions":[{"id":"https://openalex.org/I4210113480","display_name":"Mohamed bin Zayed University of Artificial Intelligence","ror":"https://ror.org/0258gkt32","country_code":"AE","type":"education","lineage":["https://openalex.org/I4210113480"]}],"countries":["AE"],"is_corresponding":false,"raw_author_name":"Muhammad Abdul-Mageed","raw_affiliation_strings":["Department of Natural Language Processing & Department of Machine Learning, MBZUAI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Natural Language Processing & Department of Machine Learning, MBZUAI","institution_ids":["https://openalex.org/I4210113480"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.5065,"has_fulltext":true,"cited_by_count":12,"citation_normalized_percentile":{"value":0.91715568,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"232","last_page":"243"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9951000213623047,"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":0.9951000213623047,"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":0.9948999881744385,"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/T13629","display_name":"Text Readability and Simplification","score":0.9254999756813049,"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":0.8382681608200073},{"id":"https://openalex.org/keywords/python","display_name":"Python (programming language)","score":0.6776821613311768},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6397536396980286},{"id":"https://openalex.org/keywords/arabic","display_name":"Arabic","score":0.6166265606880188},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5640560388565063},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5610532164573669},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.45169496536254883},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.44964301586151123},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.4102649688720703},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.35009777545928955},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.17777979373931885},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.08622586727142334}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8382681608200073},{"id":"https://openalex.org/C519991488","wikidata":"https://www.wikidata.org/wiki/Q28865","display_name":"Python (programming language)","level":2,"score":0.6776821613311768},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6397536396980286},{"id":"https://openalex.org/C96455323","wikidata":"https://www.wikidata.org/wiki/Q13955","display_name":"Arabic","level":2,"score":0.6166265606880188},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5640560388565063},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5610532164573669},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.45169496536254883},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.44964301586151123},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.4102649688720703},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.35009777545928955},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.17777979373931885},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.08622586727142334},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2023.arabicnlp-1.20","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2023.arabicnlp-1.20","pdf_url":"https://aclanthology.org/2023.arabicnlp-1.20.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 ArabicNLP 2023","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2023.arabicnlp-1.20","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2023.arabicnlp-1.20","pdf_url":"https://aclanthology.org/2023.arabicnlp-1.20.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 ArabicNLP 2023","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.6800000071525574,"id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G2980479518","display_name":null,"funder_award_id":"RGPIN-2018","funder_id":"https://openalex.org/F4320334593","funder_display_name":"Natural Sciences and Engineering Research Council of Canada"},{"id":"https://openalex.org/G4097713262","display_name":"Conflict in Nova Scotia:  women organizations and institutionalized restorative justice","funder_award_id":"37771","funder_id":"https://openalex.org/F4320334617","funder_display_name":"Social Sciences and Humanities Research Council of Canada"},{"id":"https://openalex.org/G4998863085","display_name":null,"funder_award_id":"895\u20102020\u20101004","funder_id":"https://openalex.org/F4320334617","funder_display_name":"Social Sciences and Humanities Research Council of Canada"}],"funders":[{"id":"https://openalex.org/F4320320994","display_name":"Canada Research Chairs","ror":"https://ror.org/0517h6h17"},{"id":"https://openalex.org/F4320331257","display_name":"Alliance de recherche num\u00e9rique du Canada","ror":"https://ror.org/010r6td27"},{"id":"https://openalex.org/F4320334593","display_name":"Natural Sciences and Engineering Research Council of Canada","ror":"https://ror.org/01h531d29"},{"id":"https://openalex.org/F4320334617","display_name":"Social Sciences and Humanities Research Council of Canada","ror":"https://ror.org/04j5jqy92"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4389518279.pdf","grobid_xml":"https://content.openalex.org/works/W4389518279.grobid-xml"},"referenced_works_count":46,"referenced_works":["https://openalex.org/W2016589492","https://openalex.org/W2123442489","https://openalex.org/W2250816155","https://openalex.org/W2251851155","https://openalex.org/W2575598244","https://openalex.org/W2624871570","https://openalex.org/W2837112844","https://openalex.org/W2913340405","https://openalex.org/W2938704169","https://openalex.org/W2948902769","https://openalex.org/W2963096510","https://openalex.org/W2964573145","https://openalex.org/W2966083394","https://openalex.org/W2970814728","https://openalex.org/W2970960342","https://openalex.org/W2991784022","https://openalex.org/W3032746405","https://openalex.org/W3032819430","https://openalex.org/W3034469191","https://openalex.org/W3034999214","https://openalex.org/W3035497479","https://openalex.org/W3082928416","https://openalex.org/W3089057597","https://openalex.org/W3104196571","https://openalex.org/W3125348957","https://openalex.org/W3126159292","https://openalex.org/W3169483174","https://openalex.org/W3173360659","https://openalex.org/W3190730109","https://openalex.org/W3197876970","https://openalex.org/W3211848854","https://openalex.org/W3212499710","https://openalex.org/W4281717508","https://openalex.org/W4285077564","https://openalex.org/W4285104921","https://openalex.org/W4288076474","https://openalex.org/W4288089799","https://openalex.org/W4288286832","https://openalex.org/W4295312788","https://openalex.org/W4297663785","https://openalex.org/W4301188379","https://openalex.org/W4313908941","https://openalex.org/W4385571124","https://openalex.org/W4385573810","https://openalex.org/W4389519573","https://openalex.org/W4389519614"],"related_works":["https://openalex.org/W3176018525","https://openalex.org/W2903533908","https://openalex.org/W3026554633","https://openalex.org/W2903810591","https://openalex.org/W4289548192","https://openalex.org/W2888520903","https://openalex.org/W2963499882","https://openalex.org/W2903399267","https://openalex.org/W2949454572","https://openalex.org/W3098873988"],"abstract_inverted_index":{"Understanding":[0],"Arabic":[1,30,52,127],"text":[2],"and":[3,17,68,88,94,114,121,139],"generating":[4],"human-like":[5],"responses":[6],"is":[7,23,36,63],"a":[8,28,40,50,118,132],"challenging":[9],"endeavor.":[10],"While":[11],"many":[12],"researchers":[13],"have":[14],"proposed":[15],"models":[16,98,138],"solutions":[18],"for":[19,125],"individual":[20],"problems,":[21],"there":[22],"an":[24,72],"acute":[25],"shortage":[26],"of":[27,38,43,76],"comprehensive":[29],"natural":[31],"language":[32],"generation":[33,128],"toolkit":[34,123,141],"that":[35],"capable":[37],"handling":[39],"wide":[41],"range":[42],"tasks.":[44],"In":[45],"this":[46],"work,":[47],"we":[48],"present":[49],"novel":[51],"text-to-text":[53],"Transformer":[54],"model,":[55],"namely":[56],"AraT5":[57],"v2":[58],".":[59],"Our":[60,97],"new":[61],"model":[62],"methodically":[64],"trained":[65],"on":[66,142],"extensive":[67],"diverse":[69],"data,":[70],"utilizing":[71],"extended":[73],"sequence":[74],"length":[75],"2,":[77],"048":[78],"tokens.":[79],"We":[80,105,135],"explore":[81],"various":[82],"pretraining":[83],"strategies":[84],"including":[85],"unsupervised,":[86],"supervised,":[87],"joint":[89],"pertaining,":[90],"under":[91],"both":[92],"single":[93,133],"multitask":[95],"settings.":[96],"outperform":[99],"competitive":[100],"baselines":[101],"with":[102],"large":[103],"margins.":[104],"take":[106],"our":[107,143],"work":[108],"one":[109],"step":[110],"further":[111],"by":[112],"developing":[113],"publicly":[115],"releasing":[116],"OCTOPUS,":[117],"Pythonbased":[119],"package":[120],"command-line":[122],"tailored":[124],"eight":[126],"tasks":[129],"all":[130],"exploiting":[131],"model.":[134],"release":[136],"the":[137,140],"public":[144],"repository.":[145],"1":[146]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":6}],"updated_date":"2026-08-18T07:49:30.821534","created_date":"2025-10-10T00:00:00"}