{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006899564,0.0009106203,0.0005237557,0.000950351,0.0007583159,0.001351415,0.00108743,0.0008959732,0.004036325],"category_scores_gemma":[0.002092303,0.0003667418,0.0006689876,0.0007090995,0.0006020906,0.00306448,0.0009840979,0.001124623,0.00485068],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000424571,"about_ca_system_score_gemma":0.0006594276,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003380641,"about_ca_topic_score_gemma":0.006214241,"domain_scores_codex":[0.9995827,0.00008009925,0.00003985191,0.0001628224,0.0001043947,0.00003023146],"domain_scores_gemma":[0.9994156,0.0001702784,0.00008553085,0.0001181157,0.0001808867,0.00002962937],"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":[0.0004591304,0.0000524915,0.002212575,0.0002891229,0.00009988477,0.0004271617,0.0003922556,0.01712807,0.05950582,0.006529733,0.0101911,0.9027126],"study_design_scores_gemma":[0.0000386842,0.0001772267,0.003117891,0.0001540067,0.0002032437,0.001355473,0.0007640516,0.7750937,0.134489,0.0340655,0.05041795,0.0001232579],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.08325893,0.002251685,0.8810535,0.001455503,0.0006086949,0.00007931973,0.0006127702,0.02153258,0.009147074],"genre_scores_gemma":[0.4935045,0.001122171,0.4919145,0.0006594633,0.0001108075,0.00004273654,0.001094887,0.0008480914,0.01070283],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.004036325,"threshold_uncertainty_score":0.0135029,"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."}}