{"id":"W3199808029","doi":"10.36227/techrxiv.16569420.v1","title":"Soft Computing Approaches for tagging Arabic text","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Association of Canadian Archivists","funders":"","keywords":"Computer science; Artificial intelligence; Arabic; Support vector machine; Hindi; Natural language processing; Artificial neural network; Process (computing); Multilayer perceptron; Perceptron; Part of speech; Machine learning; Speech recognition; Linguistics","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001183696,0.0009715053,0.0007026989,0.0036136,0.0008062903,0.00248185,0.001168224,0.001025081,0.003828337],"category_scores_gemma":[0.003704216,0.0003704984,0.000920503,0.003087767,0.001068179,0.002643264,0.001284832,0.001288924,0.00242949],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001133016,"about_ca_system_score_gemma":0.001051603,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002977019,"about_ca_topic_score_gemma":0.004171445,"domain_scores_codex":[0.9988598,0.0003041094,0.0001130766,0.0002657642,0.0003875733,0.00006962412],"domain_scores_gemma":[0.9983745,0.0007763177,0.0001651366,0.0002243711,0.0004097349,0.00004987406],"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":[0.0001218157,0.0001478982,0.00141861,0.0005431817,0.0001029279,0.0002023682,0.0004367357,0.0832164,0.01449251,0.08207294,0.00565959,0.8115851],"study_design_scores_gemma":[0.00001298337,0.00008161235,0.0009432245,0.000116163,0.00003451258,0.0001288243,0.0003534536,0.8446038,0.01139299,0.1236683,0.01861356,0.00005066595],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.006534402,0.0009764825,0.9855365,0.0004498387,0.000166596,0.0001277384,0.0001376257,0.0006033257,0.005467555],"genre_scores_gemma":[0.1928166,0.001726982,0.7910914,0.0004716633,0.0003137403,0.0003781273,0.0006227915,0.0001628716,0.0124158],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003828337,"threshold_uncertainty_score":0.01280707,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06861444804767225,"score_gpt":0.28092561340744,"score_spread":0.2123111653597677,"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."}}