{"id":"W2579409202","doi":"10.21700/ijcis.2016.119","title":"Automatic Diacritics Restoration for Dialectal Arabic Text","year":2016,"lang":"en","type":"article","venue":"International Journal of Computing and Information Sciences","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":false,"ca_institutions":"","funders":"","keywords":"Arabic; Linguistics; Natural language processing; Artificial intelligence; Computer science; Philosophy","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"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":[0.0006064528,0.001374084,0.0008987859,0.003199238,0.001327405,0.001385788,0.0008042253,0.0008348408,0.008391187],"category_scores_gemma":[0.001524685,0.0003555338,0.0008665728,0.001396247,0.0005561991,0.001232036,0.001031419,0.001391285,0.009138676],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003443778,"about_ca_system_score_gemma":0.0009729341,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002303916,"about_ca_topic_score_gemma":0.004039113,"domain_scores_codex":[0.9994179,0.00007712914,0.00004972566,0.0002458576,0.0001360007,0.00007333538],"domain_scores_gemma":[0.9988809,0.0002153658,0.0001102201,0.0002179153,0.0005006855,0.00007483098],"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":[0.001261568,0.0001594537,0.001542046,0.0007628769,0.00005324411,0.0005488289,0.0003788872,0.001834147,0.1758851,0.002749786,0.01584445,0.7989795],"study_design_scores_gemma":[0.0002114877,0.0005910737,0.0157393,0.0002100882,0.0004326858,0.002347485,0.002427163,0.42007,0.4242622,0.01064104,0.1228926,0.0001749915],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2688718,0.004818162,0.6413746,0.001187224,0.002404217,0.0005984323,0.005780913,0.05639967,0.01856503],"genre_scores_gemma":[0.457444,0.001469302,0.510147,0.0001649308,0.0004179299,0.0001697486,0.008282709,0.002428644,0.01947564],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008391187,"threshold_uncertainty_score":0.02807128,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01376920173908248,"score_gpt":0.3163899634614012,"score_spread":0.3026207617223188,"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."}}