{"id":"W3119989665","doi":"","title":"ARBERT & MARBERT: Deep Bidirectional Transformers for Arabic.","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":138,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Arabic; Transformer; Natural language processing; Inference; Language model; Task (project management); Artificial intelligence; Benchmark (surveying); Machine learning; Linguistics","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0001822841,0.000366599,0.0003639758,0.0002507688,0.0001849145,0.0001580151,0.001745235,0.0003814571,0.0000235981],"category_scores_gemma":[0.00006424297,0.0004047356,0.0003609225,0.0005937141,0.00009262266,0.0004741749,0.000694708,0.0006846527,0.00002499836],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002450424,"about_ca_system_score_gemma":0.0002544246,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008039019,"about_ca_topic_score_gemma":0.00004491779,"domain_scores_codex":[0.9979541,0.00006095936,0.0002121645,0.001262748,0.0001222011,0.0003877793],"domain_scores_gemma":[0.9987758,0.0001330524,0.0001920627,0.0004913239,0.0002048004,0.0002029648],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0003557471,0.0002656461,0.000538139,0.001065361,0.0005434039,0.0005364295,0.0009555564,0.007173705,0.00152307,0.9356091,0.005736581,0.04569725],"study_design_scores_gemma":[0.0004599402,0.00009597186,0.00004634746,0.0001083875,0.00009339076,0.00001235545,0.00002215368,0.4765406,0.003411822,0.5143833,0.00408528,0.0007405425],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001481824,0.0004873351,0.9934303,0.0009600714,0.0005788872,0.000535771,0.0000267219,0.001151061,0.00134799],"genre_scores_gemma":[0.8172452,0.0001147837,0.1809124,0.0004935543,0.0001569867,0.000008675118,0.00004364777,0.00003420264,0.0009905664],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8157634,"threshold_uncertainty_score":0.9998404,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05721774270401291,"score_gpt":0.2069810579594347,"score_spread":0.1497633152554217,"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."}}