{"id":"W4404782299","doi":"10.18653/v1/2024.emnlp-main.1211","title":"Casablanca: Data and Models for Multidialectal Arabic Speech Recognition","year":2024,"lang":"en","type":"article","venue":"","topic":"Language, Linguistics, Cultural Analysis","field":"Arts and Humanities","cited_by":6,"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","keywords":"Arabic; Computer science; Speech recognition; Natural language processing; Artificial intelligence; Linguistics","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":[0.00193627,0.002279518,0.001047617,0.001748193,0.001215026,0.002430405,0.003261419,0.002099778,0.01534681],"category_scores_gemma":[0.008545905,0.0008649308,0.001575409,0.001215144,0.0005384134,0.003503419,0.00285146,0.002569081,0.01992172],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001601527,"about_ca_system_score_gemma":0.001696232,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.04516879,"about_ca_topic_score_gemma":0.03708903,"domain_scores_codex":[0.9987876,0.000408343,0.0001104372,0.0003983722,0.0002068113,0.00008842911],"domain_scores_gemma":[0.9968877,0.00137933,0.0001074151,0.0007130153,0.0007316957,0.0001808394],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.005019678,0.0008632226,0.009988173,0.00118236,0.0007125944,0.0009219977,0.0008443984,0.09141702,0.02141298,0.00915328,0.2445937,0.6138905],"study_design_scores_gemma":[0.0002067458,0.0001589028,0.004143791,0.00009898234,0.0001336028,0.0002979494,0.0003401454,0.9161454,0.01582767,0.007190073,0.05533607,0.0001206205],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1182333,0.005897274,0.467096,0.004872285,0.002619761,0.001301502,0.1231174,0.2545773,0.0222851],"genre_scores_gemma":[0.4279037,0.001375065,0.3562792,0.0005781869,0.0003503398,0.002859612,0.186559,0.00525149,0.01884327],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.04516879,"threshold_uncertainty_score":0.08981174,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1317035454805794,"score_gpt":0.2873272728672311,"score_spread":0.1556237273866518,"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."}}