{"id":"W4389518436","doi":"10.18653/v1/2023.arabicnlp-1.62","title":"NADI 2023: The Fourth Nuanced Arabic Dialect Identification Shared Task","year":2023,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":28,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"Alliance de recherche numérique du Canada; Social Sciences and Humanities Research Council of Canada; Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Arabic; Task (project management); Identification (biology); Machine translation; Computer science; Natural language processing; Focus (optics); Artificial intelligence; Linguistics; Engineering","routes":{"ca_aff":true,"ca_fund":true,"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":[0.01306412,0.002498763,0.002705345,0.002712259,0.003928785,0.004072708,0.003434728,0.003273546,0.0102416],"category_scores_gemma":[0.02148002,0.0006540839,0.001861947,0.001868452,0.001573296,0.003924225,0.01499159,0.004681718,0.01228874],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00253465,"about_ca_system_score_gemma":0.007441364,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0101918,"about_ca_topic_score_gemma":0.01710836,"domain_scores_codex":[0.9861778,0.00567506,0.00085646,0.002926858,0.002736981,0.001626835],"domain_scores_gemma":[0.9795853,0.004562498,0.0006752462,0.005099503,0.005259377,0.004818226],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00581684,0.003593605,0.02177942,0.00311965,0.0006959907,0.001816463,0.0129604,0.009238255,0.08639425,0.007864744,0.4280068,0.4187137],"study_design_scores_gemma":[0.00228918,0.00428318,0.05448446,0.0005603867,0.0003850868,0.003131991,0.01447558,0.06142464,0.0772004,0.02528591,0.7556548,0.0008244445],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"empirical","genre_gemma":"other","genre_scores_codex":[0.5139022,0.00474339,0.1932565,0.007467527,0.008900676,0.01353175,0.1141143,0.0317179,0.1123657],"genre_scores_gemma":[0.4119796,0.0004088025,0.3320568,0.002441335,0.001045217,0.01194266,0.1883303,0.003249485,0.04854592],"genre_candidate":"other","genre_consensus":null,"teacher_disagreement_score":0.01306412,"threshold_uncertainty_score":0.06909055,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01787887490943504,"score_gpt":0.276753934861565,"score_spread":0.25887505995213,"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."}}