{"id":"W2757376562","doi":"10.18653/v1/d17-1073","title":"Don't Throw Those Morphological Analyzers Away Just Yet: Neural Morphological Disambiguation for Arabic","year":2017,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":56,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"York University; New York University Abu Dhabi","keywords":"Computer science; Artificial intelligence; Ranking (information retrieval); Arabic; Feature (linguistics); Pattern recognition (psychology); Feature engineering; Approximation error; Artificial neural network; Embedding; Recurrent neural network; Vocabulary; Feature extraction; Speech recognition; Natural language processing; Deep learning; Algorithm","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005200859,0.0002442108,0.0002889486,0.00008633157,0.0006778016,0.0007430478,0.002436593,0.0002208646,0.00009074281],"category_scores_gemma":[0.0007161039,0.0001620683,0.0001677714,0.0001389073,0.0002604305,0.001132962,0.0005932591,0.0002669547,0.00002014277],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000577777,"about_ca_system_score_gemma":0.00003397877,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009642338,"about_ca_topic_score_gemma":0.00002280505,"domain_scores_codex":[0.9981663,0.00006452328,0.0002816621,0.0007210632,0.0003110875,0.0004553802],"domain_scores_gemma":[0.998127,0.0001480199,0.0002541436,0.001199204,0.000147735,0.0001239124],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0002137593,0.0007486875,0.01033256,0.0001195349,0.00009166845,0.001038952,0.0007513778,0.00009802005,0.1066908,0.3130364,0.0349615,0.5319167],"study_design_scores_gemma":[0.002960667,0.001764823,0.04516191,0.000145392,0.0001278661,0.0008421312,0.0001814054,0.3726771,0.1504765,0.420515,0.002541862,0.002605253],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1134677,0.000426538,0.8735876,0.009026752,0.0005388279,0.0005125476,0.00000831198,0.001194539,0.00123715],"genre_scores_gemma":[0.7010522,0.00001183416,0.2975484,0.0007987342,0.00008237872,0.00005902285,0.000009602225,0.000009283988,0.0004284621],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5875846,"threshold_uncertainty_score":0.7165227,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07278266145795757,"score_gpt":0.3595368032119135,"score_spread":0.2867541417539559,"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."}}