{"id":"W4387963603","doi":"10.48550/arxiv.2310.16127","title":"Octopus: A Multitask Model and Toolkit for Arabic Natural Language Generation","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Topic Modeling","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","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; Transformer; Artificial intelligence; Language model; Economic shortage; Machine learning; Programming language; Linguistics; Engineering","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001262159,0.001205265,0.0005136455,0.0008541872,0.0005096187,0.001039115,0.002382694,0.0008781177,0.01541914],"category_scores_gemma":[0.005273729,0.0006517253,0.001223851,0.0006413663,0.0003487017,0.001823581,0.0018944,0.002510171,0.009666408],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008404131,"about_ca_system_score_gemma":0.001780779,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00883431,"about_ca_topic_score_gemma":0.01473432,"domain_scores_codex":[0.9996195,0.0001360791,0.00002957869,0.00009804831,0.00007495418,0.000041802],"domain_scores_gemma":[0.9989613,0.0005308679,0.00004744678,0.0001767774,0.0001984806,0.00008513406],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001070799,0.0003678869,0.003929826,0.0008645444,0.0003172762,0.0004366561,0.0007090873,0.2282423,0.009118098,0.01933965,0.2844609,0.4511429],"study_design_scores_gemma":[0.00006615397,0.00005241646,0.0003660245,0.00003084675,0.00002210431,0.0001011359,0.00004284121,0.9542869,0.004345076,0.01210992,0.02854201,0.00003464824],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01522206,0.0005458454,0.8060336,0.0008639621,0.0005342104,0.00057158,0.01246459,0.1558143,0.007949895],"genre_scores_gemma":[0.252148,0.0006403453,0.6737924,0.0009107254,0.0001891413,0.002429122,0.03620555,0.01256757,0.02111726],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01541914,"threshold_uncertainty_score":0.05158222,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1394722614919398,"score_gpt":0.215801483058999,"score_spread":0.07632922156705926,"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."}}