{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000176715,0.0000913472,0.00008592365,0.0001072294,0.00009335134,0.0001826189,0.0003020987,0.00004963369,0.000001378923],"category_scores_gemma":[0.00009278045,0.00007094081,0.00002960095,0.0002370665,0.0000160357,0.0005100144,0.0001530369,0.00007296513,0.000007151588],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001829188,"about_ca_system_score_gemma":0.00002295596,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001760441,"about_ca_topic_score_gemma":0.00002691796,"domain_scores_codex":[0.9993083,0.00001056324,0.0001053776,0.0002789684,0.0001152573,0.0001815135],"domain_scores_gemma":[0.999609,0.00004647412,0.00003019822,0.0002218779,0.00005795854,0.00003448312],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001123072,0.00003034487,0.00005216816,0.0001044168,0.00002052071,0.00002213945,0.003823451,0.0003787789,0.3992247,0.2092243,0.02398503,0.3631229],"study_design_scores_gemma":[0.0001400462,0.00001761928,0.00001736574,0.000006795606,0.000002315364,0.000005704977,0.00002207549,0.9631481,0.02679289,0.009658184,0.00007288084,0.0001160463],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.08070219,0.0016537,0.9141267,0.001168881,0.0001481926,0.0003002312,0.000005411044,0.001798714,0.00009597075],"genre_scores_gemma":[0.4941852,0.000006802011,0.5038333,0.0003492942,0.00004423958,0.00003342636,0.00001338861,0.000005620116,0.001528695],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9627693,"threshold_uncertainty_score":0.2892883,"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."}}