{"id":"W4389518365","doi":"10.18653/v1/2023.arabicnlp-1.67","title":"Frank at NADI 2023 Shared Task: Trio-Based Ensemble Approach for Arabic Dialect Identification","year":2023,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Computer science; Task (project management); Arabic; Hyperparameter; Identification (biology); Ensemble learning; Artificial intelligence; Ensemble forecasting; Natural language processing; Machine learning; Speech recognition; 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":[0.002424691,0.001753468,0.001374877,0.001687956,0.001744382,0.001698283,0.001954104,0.00179006,0.007910914],"category_scores_gemma":[0.003380999,0.0004451904,0.001133918,0.001024454,0.0002969225,0.002517344,0.003382814,0.001999789,0.01018657],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006039068,"about_ca_system_score_gemma":0.001280105,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01296944,"about_ca_topic_score_gemma":0.02094176,"domain_scores_codex":[0.9983523,0.0004033832,0.00008681165,0.0006327007,0.0003039216,0.0002209708],"domain_scores_gemma":[0.9985448,0.0002186591,0.00005479014,0.0004690462,0.0005179598,0.0001947706],"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":[0.001066879,0.0005597236,0.006480498,0.0002589413,0.0004054141,0.0005335229,0.0009922592,0.01522986,0.05914584,0.001614408,0.1028475,0.8108651],"study_design_scores_gemma":[0.0001703871,0.0007756474,0.01228273,0.00008535739,0.0004000811,0.001233393,0.001267382,0.7679175,0.1094111,0.008974298,0.09714835,0.0003338672],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2211728,0.002357358,0.612848,0.001203538,0.001525264,0.00106291,0.01618178,0.1131742,0.03047414],"genre_scores_gemma":[0.5367527,0.0003747168,0.394136,0.0006045157,0.0002929649,0.0006146465,0.03238707,0.002747391,0.03209],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01296944,"threshold_uncertainty_score":0.02646464,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02703376176587034,"score_gpt":0.2806555018163519,"score_spread":0.2536217400504815,"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."}}