{"id":"W2805089673","doi":"10.63317/3wos9hprfv6b","title":"You Tweet What You Speak: A City-Level Dataset of Arabic Dialects","year":2018,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":62,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Arabic; Computer science; Natural language processing; Artificial intelligence; Linguistics","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003866051,0.0001576663,0.0001994242,0.0001489339,0.0000794154,0.0003074239,0.001664048,0.0000816812,0.0001033089],"category_scores_gemma":[0.0001390075,0.0001221395,0.00004065646,0.0005383926,0.0001630685,0.002000178,0.0006776882,0.0001367061,0.00006424653],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002780457,"about_ca_system_score_gemma":0.00007673516,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001580961,"about_ca_topic_score_gemma":0.00007822604,"domain_scores_codex":[0.99863,0.00004663753,0.0002674434,0.0004355776,0.0003262223,0.0002941254],"domain_scores_gemma":[0.9985435,0.00005775809,0.0001401399,0.001002001,0.0001709484,0.00008566376],"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":[0.00005641855,0.0004132601,0.001219071,0.0001899897,0.00008176493,0.0001012824,0.003618806,5.036014e-7,0.05020507,0.09637068,0.2297384,0.6180047],"study_design_scores_gemma":[0.0005276346,0.0005243262,0.0006564136,0.0002923406,0.00002197843,0.00008160206,0.00007894065,0.004209152,0.8830292,0.0789593,0.03086753,0.0007516244],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01170895,0.001774932,0.9816107,0.001403226,0.0005964627,0.0002669143,0.0001675241,0.0007952124,0.001676075],"genre_scores_gemma":[0.3306338,0.00003301314,0.6675209,0.001084011,0.0001561751,0.000005657218,0.00009027853,0.00001026597,0.0004657945],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8328241,"threshold_uncertainty_score":0.4980705,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03993097122083863,"score_gpt":0.3037672573981623,"score_spread":0.2638362861773237,"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."}}