{"id":"W2037378121","doi":"10.1109/isccsp.2012.6217760","title":"A novel segmentation technique for splitting a typed Persian text to sub-words","year":2012,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Windsor","funders":"","keywords":"Persian; Computer science; Natural language processing; Segmentation; Component (thermodynamics); Artificial intelligence; Character (mathematics); Word (group theory); Text segmentation; Text recognition; Speech recognition; Linguistics; Mathematics; Image (mathematics)","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":[0.0002409544,0.0009544884,0.0005418765,0.001082203,0.0005155123,0.0005375635,0.0007615587,0.0006984543,0.003660573],"category_scores_gemma":[0.0008023542,0.0003258298,0.0005445103,0.001030305,0.0005469804,0.001238715,0.0004149331,0.0008853214,0.002989216],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002135328,"about_ca_system_score_gemma":0.0005456491,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007002035,"about_ca_topic_score_gemma":0.001339178,"domain_scores_codex":[0.9995967,0.00003241673,0.00004156591,0.0001579834,0.0001343671,0.0000370014],"domain_scores_gemma":[0.9993906,0.000143282,0.00008988061,0.0001300549,0.0002139714,0.00003225523],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002054028,0.00006860594,0.0004581887,0.0002824265,0.00002870964,0.0003474086,0.000352991,0.001308648,0.5384399,0.001579223,0.003792359,0.4531361],"study_design_scores_gemma":[0.00004718055,0.0005435891,0.003917699,0.00004984066,0.0001259482,0.003331789,0.0002888218,0.07746531,0.8587847,0.002257143,0.05310994,0.00007807847],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.04810602,0.001054065,0.9402925,0.0001845454,0.0004150557,0.000219556,0.0002583786,0.005586109,0.00388379],"genre_scores_gemma":[0.09971923,0.000565229,0.8888373,0.0001645533,0.0001233612,0.000143069,0.0006358612,0.0004291428,0.009382231],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.003660573,"threshold_uncertainty_score":0.01224577,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02718313247388557,"score_gpt":0.2942379434968472,"score_spread":0.2670548110229616,"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."}}