{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004256117,0.0001896716,0.0001442421,0.0002429872,0.0002066137,0.0004788821,0.002604413,0.00008198056,0.00003179356],"category_scores_gemma":[0.002616868,0.0001865826,0.0000456692,0.000180748,0.0001056528,0.0002641137,0.0003118125,0.0001720561,0.00005930857],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001082905,"about_ca_system_score_gemma":0.0002102914,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009185227,"about_ca_topic_score_gemma":0.00000984462,"domain_scores_codex":[0.9979771,0.00004572573,0.0003982279,0.0006981606,0.0006784282,0.0002023036],"domain_scores_gemma":[0.9956573,0.0005260945,0.0002619635,0.0006476,0.002836721,0.00007028241],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00004994828,0.00008310348,0.000007019195,0.000007449884,0.00002603434,0.000002895901,0.00009448813,0.00352941,0.00005483354,0.9814138,0.001942372,0.01278868],"study_design_scores_gemma":[0.0001331567,0.00009371698,0.00003693794,0.00003803159,0.000004027241,0.000001919946,0.000002484114,0.5473148,0.0002862934,0.4509433,0.001027302,0.0001180229],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00009287752,0.00003137437,0.9858099,0.001150341,0.002174177,0.0002537172,0.0001387221,0.0002670311,0.01008191],"genre_scores_gemma":[0.629195,0.000003921534,0.3686186,0.0005881207,0.000850204,0.00002228598,0.0005925079,0.00001070842,0.000118542],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6291022,"threshold_uncertainty_score":0.7608616,"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."}}