{"id":"W2970485137","doi":"10.18653/v1/w19-4637","title":"No Army, No Navy: BERT Semi-Supervised Learning of Arabic Dialects","year":2019,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":36,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"Social Sciences and Humanities Research Council of Canada; Natural Sciences and Engineering Research Council of Canada; Compute Canada","keywords":"Porting; Computer science; Arabic; Artificial intelligence; Natural language processing; Identification (biology); Navy; Macro; Supervised learning; Task (project management); F1 score; Set (abstract data type); Machine learning; Engineering; Linguistics; History; Artificial neural network; Programming language","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006407364,0.0009696134,0.0004631414,0.0007906028,0.0006201179,0.0009625981,0.0009271389,0.0006616104,0.00772749],"category_scores_gemma":[0.001917074,0.0002706662,0.0004514501,0.0004016899,0.0002337798,0.001445641,0.001395877,0.001225651,0.01007366],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000397682,"about_ca_system_score_gemma":0.000794359,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004181487,"about_ca_topic_score_gemma":0.01200931,"domain_scores_codex":[0.9995555,0.00009123632,0.00002613645,0.0001882151,0.0000913536,0.00004752474],"domain_scores_gemma":[0.9991902,0.0001628331,0.0000657581,0.0002371772,0.0002556665,0.0000884699],"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":[0.0007024259,0.0002413183,0.008959425,0.0002978045,0.0001187974,0.0002168502,0.0003545138,0.01305942,0.05571292,0.002777932,0.07455615,0.8430025],"study_design_scores_gemma":[0.00006431581,0.0002957503,0.007122024,0.00007469015,0.00006531032,0.0004530456,0.000351977,0.8239231,0.09482054,0.009824036,0.06290986,0.00009538714],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.2056736,0.001182403,0.6220889,0.001329374,0.000948502,0.0003240704,0.01527142,0.1293955,0.02378624],"genre_scores_gemma":[0.6379222,0.0002784626,0.2999749,0.0006200073,0.000196201,0.0002413996,0.02170959,0.001576402,0.03748085],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.00772749,"threshold_uncertainty_score":0.02585107,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.007084348724772917,"score_gpt":0.2356253151227733,"score_spread":0.2285409663980004,"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."}}