{"id":"W4389520667","doi":"10.18653/v1/2023.emnlp-main.396","title":"Advancements in Arabic Grammatical Error Detection and Correction: An Empirical Investigation","year":2023,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"York University; New York University Abu Dhabi","keywords":"Computer science; Preprocessor; Natural language processing; Artificial intelligence; Arabic; Benchmark (surveying); Transformer; Task (project management); Language model; Class (philosophy); Linguistics","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":[0.01142348,0.001969528,0.0009352468,0.003164077,0.001429838,0.002274783,0.002476346,0.002091445,0.003352811],"category_scores_gemma":[0.06072438,0.0005443959,0.001048721,0.003324581,0.001570426,0.005936594,0.002981224,0.003605949,0.0040106],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00146365,"about_ca_system_score_gemma":0.001230772,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01022838,"about_ca_topic_score_gemma":0.01178761,"domain_scores_codex":[0.991227,0.004116808,0.0006542671,0.002288445,0.001421207,0.0002923916],"domain_scores_gemma":[0.9356735,0.04297595,0.002853632,0.01101111,0.006389653,0.001096143],"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":[0.001620378,0.001619358,0.296747,0.001751165,0.000622777,0.001377385,0.004012929,0.04136036,0.00713147,0.004899175,0.0889272,0.5499308],"study_design_scores_gemma":[0.000306863,0.001532826,0.2580193,0.0009591535,0.0007283566,0.005606521,0.008428855,0.5766665,0.02706228,0.01991328,0.1003743,0.0004017985],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9437296,0.004834814,0.01963764,0.002273299,0.000431856,0.0002326389,0.01092157,0.005073813,0.0128648],"genre_scores_gemma":[0.9383354,0.001155679,0.02301728,0.0006655202,0.0001583455,0.0001679147,0.0322878,0.0008295604,0.003382414],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01142348,"threshold_uncertainty_score":0.0604139,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03459840212741797,"score_gpt":0.3380574985760335,"score_spread":0.3034590964486155,"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."}}