{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004608458,0.00009956527,0.00008574151,0.0001148054,0.0002076904,0.0004279034,0.001450177,0.00004879661,0.00002885365],"category_scores_gemma":[0.0001935153,0.00006371678,0.00004896922,0.001366741,0.00003590937,0.0005579713,0.0002560713,0.0001429631,0.0004480156],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003552007,"about_ca_system_score_gemma":0.00004588545,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006507277,"about_ca_topic_score_gemma":0.00004526186,"domain_scores_codex":[0.9989216,0.00005773152,0.0001743308,0.0003338858,0.0002678791,0.0002445459],"domain_scores_gemma":[0.9989952,0.0001194711,0.00008098943,0.0006744821,0.00009057948,0.00003920748],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00001104096,0.0000498206,0.0003040794,0.00006458015,0.0000432934,0.00005811758,0.002984714,0.00005856248,0.1857755,0.2173424,0.2734517,0.3198563],"study_design_scores_gemma":[0.0004655841,0.0001050346,0.01419254,0.0001187483,0.00002226733,0.0000459838,0.0001179325,0.254977,0.2234215,0.4878191,0.0177382,0.0009761284],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.006932676,0.0007890178,0.9747398,0.01068634,0.0006058304,0.0004226148,0.000005984001,0.003998918,0.001818793],"genre_scores_gemma":[0.9118582,0.0000336118,0.07866699,0.0007331375,0.0001075662,0.0001036446,0.00001897937,0.00001331685,0.008464578],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9049255,"threshold_uncertainty_score":0.5758484,"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."}}