{"id":"W2914220664","doi":"","title":"Deep Models for Arabic Dialect Identification on Benchmarked Data","year":2018,"lang":"en","type":"article","venue":"International Conference on Computational Linguistics","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":61,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Benchmark (surveying); Computer science; Artificial intelligence; Task (project management); Deep learning; Arabic; Natural language processing; Binary classification; Deep neural networks; Identification (biology); Machine learning; Artificial neural network; Recurrent neural network; Test data; Binary number; Speech recognition; Support vector machine; Linguistics; Mathematics; Geography","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003822666,0.003153874,0.001154637,0.002856643,0.001163006,0.001773805,0.00283606,0.002279087,0.006617148],"category_scores_gemma":[0.01373547,0.000517507,0.001343481,0.0026688,0.001068354,0.003046163,0.00257073,0.003556804,0.005859227],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00225225,"about_ca_system_score_gemma":0.001401767,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.03114979,"about_ca_topic_score_gemma":0.04051483,"domain_scores_codex":[0.9975515,0.000904968,0.0002047483,0.0006413599,0.0004413933,0.0002559908],"domain_scores_gemma":[0.993727,0.002597362,0.0002861056,0.001557822,0.001538584,0.0002931368],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.002723394,0.002574268,0.01938711,0.00170758,0.0008150364,0.0008286241,0.0006264319,0.2374206,0.01110296,0.00365418,0.2302635,0.4888963],"study_design_scores_gemma":[0.0004096191,0.0005499137,0.01178978,0.0002336095,0.0001603937,0.0003246539,0.0008291264,0.9316401,0.01672951,0.008715757,0.02848861,0.0001288981],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7793805,0.01180767,0.0618514,0.003383128,0.002188389,0.0006476797,0.09620999,0.02442597,0.02010529],"genre_scores_gemma":[0.6701142,0.001339031,0.08052433,0.0009237159,0.000316679,0.0004937258,0.2342135,0.0006441923,0.01143065],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.03114979,"threshold_uncertainty_score":0.06193691,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1011538868834525,"score_gpt":0.3765717506027052,"score_spread":0.2754178637192528,"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."}}