{"id":"W4389518279","doi":"10.18653/v1/2023.arabicnlp-1.20","title":"Octopus: A Multitask Model and Toolkit for Arabic Natural Language Generation","year":2023,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"Alliance de recherche numérique du Canada; Social Sciences and Humanities Research Council of Canada; Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Computer science; Python (programming language); Natural language processing; Arabic; Artificial intelligence; Transformer; Language model; Task (project management); Machine translation; Machine learning; Programming language; Linguistics","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001010964,0.001289731,0.0004777145,0.0007450046,0.0004902504,0.00100003,0.002429454,0.0008293375,0.01977515],"category_scores_gemma":[0.004559571,0.0006369202,0.001122433,0.0005273565,0.0003803431,0.001766327,0.001887127,0.002496041,0.01146813],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000789214,"about_ca_system_score_gemma":0.001808656,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00845233,"about_ca_topic_score_gemma":0.01466986,"domain_scores_codex":[0.9996536,0.0001071376,0.00002941866,0.00009452016,0.00007436618,0.00004100105],"domain_scores_gemma":[0.9991436,0.0004120097,0.00004330198,0.0001576018,0.0001693665,0.00007400148],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00118222,0.0003897557,0.003719279,0.001147924,0.0003100772,0.0005515539,0.0007488247,0.1581244,0.01444973,0.01655819,0.3641638,0.4386543],"study_design_scores_gemma":[0.00009994232,0.00008998185,0.0006142503,0.00004961291,0.0000297633,0.0001775599,0.00006959527,0.9251657,0.009121178,0.01348177,0.05104279,0.00005784394],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"software","genre_scores_codex":[0.01583008,0.0004673397,0.683236,0.0007659965,0.0005825094,0.0006446672,0.01645724,0.2727482,0.009267895],"genre_scores_gemma":[0.235323,0.0005616949,0.6703553,0.001005841,0.0001494399,0.002557171,0.047566,0.01967764,0.02280394],"genre_candidate":"software","genre_consensus":null,"teacher_disagreement_score":0.01977515,"threshold_uncertainty_score":0.06615448,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02493270767930455,"score_gpt":0.3017013230091579,"score_spread":0.2767686153298533,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}