{"id":"W2804967932","doi":"10.18653/v1/n18-1087","title":"Noise-Robust Morphological Disambiguation for Dialectal Arabic","year":2018,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":23,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"York University; New York University Abu Dhabi","keywords":"Arabic; Computer science; Natural language processing; Computational linguistics; Artificial intelligence; Linguistics; Speech recognition; Philosophy","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":[0.0001862755,0.0000873266,0.00008643667,0.00005289171,0.0001209005,0.0001293831,0.000581396,0.00007120492,0.00004117803],"category_scores_gemma":[0.0001812932,0.00006237846,0.00004315943,0.0002168011,0.00008006486,0.0003753793,0.0001351737,0.00006288522,0.00003988669],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002869581,"about_ca_system_score_gemma":0.00002410947,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001299871,"about_ca_topic_score_gemma":0.000009247421,"domain_scores_codex":[0.9992369,0.00001911391,0.0001189597,0.0002959756,0.0001305274,0.000198505],"domain_scores_gemma":[0.9994479,0.0000679288,0.00004389312,0.0002614624,0.0001359561,0.00004281708],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00005803493,0.0002044356,0.0005085609,0.00003668667,0.00001708508,0.0000221673,0.000700509,0.00000556894,0.130629,0.5302154,0.02956311,0.3080395],"study_design_scores_gemma":[0.0006564968,0.001122477,0.001363287,0.00003364303,0.00001269273,0.0001078518,0.00001407168,0.1555455,0.4502739,0.3876186,0.002586276,0.000665185],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01048237,0.00009115139,0.9857115,0.001022115,0.0001910567,0.0001921079,0.000001082803,0.0008494172,0.001459266],"genre_scores_gemma":[0.4830579,6.248181e-7,0.5160931,0.0004099548,0.0001339692,0.00002452403,0.000002368149,0.000003439642,0.0002741468],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4725755,"threshold_uncertainty_score":0.254372,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03194904325261866,"score_gpt":0.2923111573815551,"score_spread":0.2603621141289364,"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."}}