{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001657269,0.0001996436,0.0002856191,0.0001475544,0.0008605528,0.0001118378,0.001389666,0.00008587138,0.000002637455],"category_scores_gemma":[0.007509404,0.0001631473,0.00030754,0.0007046387,0.00004647548,0.0001273394,0.0003795399,0.0002552829,7.187198e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003977081,"about_ca_system_score_gemma":0.0001659384,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002465685,"about_ca_topic_score_gemma":0.000005896741,"domain_scores_codex":[0.9976854,0.00003519062,0.0006008928,0.0003816143,0.0009626267,0.0003342332],"domain_scores_gemma":[0.9960284,0.0004608566,0.001154623,0.0001310571,0.002165941,0.00005909712],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0007281295,0.001184106,0.05484698,0.002425058,0.001085536,0.000001204189,0.043588,0.2122903,0.1045725,0.4721318,0.07943728,0.02770917],"study_design_scores_gemma":[0.004043218,0.001611318,0.01194173,0.0006871371,0.0006555655,0.00002120313,0.003322636,0.6957141,0.1304647,0.1070591,0.04237211,0.002107103],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5122004,0.002768901,0.3977854,0.03269184,0.01624399,0.01779634,0.004982023,0.00196662,0.01356447],"genre_scores_gemma":[0.8926207,8.195636e-7,0.1053782,0.0005184237,0.0003326552,0.000149761,0.0000248186,0.00002762519,0.000947012],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4834238,"threshold_uncertainty_score":0.8990001,"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."}}