{"id":"W4402671457","doi":"10.18653/v1/2024.arabicnlp-1.79","title":"NADI 2024: The Fifth Nuanced Arabic Dialect Identification Shared Task","year":2024,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"","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; UK Research and Innovation","keywords":"Arabic; Identification (biology); Task (project management); Computer science; Linguistics; Natural language processing; Artificial intelligence; Philosophy; Engineering","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02093897,0.002186807,0.002209176,0.002544465,0.003950083,0.004521771,0.003916443,0.002944418,0.0109679],"category_scores_gemma":[0.02869375,0.0007243279,0.001698981,0.001493066,0.001896997,0.003842515,0.01559965,0.004565208,0.01100999],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003563711,"about_ca_system_score_gemma":0.009310312,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01407814,"about_ca_topic_score_gemma":0.01894714,"domain_scores_codex":[0.9824637,0.008169289,0.0009172036,0.003059559,0.003509722,0.001880602],"domain_scores_gemma":[0.9707781,0.006127778,0.0009093534,0.006826161,0.008301509,0.007057116],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.006681101,0.004643108,0.02937346,0.002722153,0.0007489835,0.001480061,0.01631017,0.0137728,0.07436153,0.01364063,0.394577,0.441689],"study_design_scores_gemma":[0.00241981,0.005262549,0.05576066,0.000548571,0.0003879777,0.001840572,0.01502461,0.06003941,0.0729591,0.02872924,0.756252,0.0007756025],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"other","genre_scores_codex":[0.493008,0.003247445,0.2266241,0.008705873,0.00733707,0.01617486,0.09102345,0.02424653,0.1296325],"genre_scores_gemma":[0.4318613,0.0002979129,0.3557493,0.002429537,0.00074293,0.01316103,0.1428998,0.002809092,0.05004907],"genre_candidate":"other","genre_consensus":null,"teacher_disagreement_score":0.02093897,"threshold_uncertainty_score":0.1107371,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01126245484664217,"score_gpt":0.2741339424653891,"score_spread":0.2628714876187469,"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."}}