{"id":"W3203510119","doi":"","title":"AraT5: Text-to-Text Transformers for Arabic Language Understanding and Generation","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Topic Modeling","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Transformer; Computer science; Arabic; Benchmark (surveying); Language model; Natural language processing; Artificial intelligence; Variety (cybernetics); Set (abstract data type); Linguistics; Programming language; Engineering","routes":{"ca_aff":true,"ca_fund":false,"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":[0.002714478,0.001898783,0.000696157,0.001894168,0.0006515613,0.001925453,0.002977973,0.001636472,0.01378226],"category_scores_gemma":[0.008507187,0.000553218,0.002072618,0.001117361,0.0007631629,0.005247863,0.002690881,0.00343991,0.007484062],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001352912,"about_ca_system_score_gemma":0.001580409,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004597061,"about_ca_topic_score_gemma":0.005715901,"domain_scores_codex":[0.998834,0.0004775774,0.00008183182,0.0003299474,0.0001877508,0.00008892279],"domain_scores_gemma":[0.9974914,0.001393752,0.000108524,0.0004504364,0.0004149742,0.0001408713],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0006305039,0.0004035648,0.002483872,0.000550779,0.0002441191,0.0002269043,0.0004972062,0.1638201,0.009679346,0.02913659,0.05096697,0.74136],"study_design_scores_gemma":[0.00004812023,0.0001031268,0.0003287051,0.00002959824,0.00004165472,0.00008527729,0.00008023164,0.9566805,0.008880519,0.02241374,0.01128314,0.00002536031],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02448463,0.0009582798,0.9237894,0.0009006491,0.0003730955,0.0004678075,0.002826165,0.03674029,0.009459813],"genre_scores_gemma":[0.4600555,0.0008466528,0.4983245,0.000733323,0.0002431022,0.001086504,0.0161889,0.002976261,0.01954521],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01378226,"threshold_uncertainty_score":0.04610628,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1539031046193264,"score_gpt":0.2117494260121026,"score_spread":0.05784632139277618,"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."}}