{"id":"W4285289306","doi":"10.18653/v1/2022.acl-long.47","title":"AraT5: Text-to-Text Transformers for Arabic Language Generation","year":2022,"lang":"en","type":"article","venue":"Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":97,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Transformer; Arabic; Natural language processing; Artificial intelligence; Benchmark (surveying); Language model; Variety (cybernetics); Set (abstract data type); Test set; Programming language; Linguistics; 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":[0.002028436,0.001797197,0.0005942451,0.001566867,0.0006273751,0.001642759,0.002866011,0.001335071,0.01769011],"category_scores_gemma":[0.005529988,0.0005016063,0.001642474,0.0009194547,0.0006696404,0.004039873,0.002660137,0.002647564,0.01008147],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001016749,"about_ca_system_score_gemma":0.001528938,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003065768,"about_ca_topic_score_gemma":0.003972568,"domain_scores_codex":[0.9990827,0.0003238343,0.00007534253,0.0002734275,0.0001636044,0.00008095378],"domain_scores_gemma":[0.9985073,0.0006050279,0.00007610802,0.0003622744,0.0003426735,0.0001065965],"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":[0.0006256097,0.0004458917,0.002485153,0.0004957362,0.0001821253,0.0002641901,0.0003353467,0.1042606,0.01358085,0.01888315,0.0576234,0.800818],"study_design_scores_gemma":[0.00008706168,0.0002391591,0.0004315469,0.00003690324,0.00004749753,0.0001659149,0.00009638246,0.9402425,0.02080127,0.01759589,0.02021735,0.00003857819],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03335118,0.0008087619,0.8778697,0.0006819098,0.0005744269,0.0006549584,0.003832441,0.06872578,0.01350088],"genre_scores_gemma":[0.4404667,0.0006196779,0.5167119,0.0006703559,0.0001989583,0.00106412,0.0178213,0.003165958,0.01928098],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01769011,"threshold_uncertainty_score":0.05917937,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.008532702958726601,"score_gpt":0.249648385788478,"score_spread":0.2411156828297514,"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."}}