{"id":"W2905695339","doi":"10.1109/icfhr-2018.2018.00048","title":"Improving Word Spotting System Performance using Ensemble Classifier Combination Methods","year":2018,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"","keywords":"Spotting; Computer science; Artificial intelligence; Classifier (UML); Support vector machine; Word (group theory); Keyword spotting; Pattern recognition (psychology); Random subspace method; Lexicon; Linear discriminant analysis; Arabic; Speech recognition; Natural language processing; 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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001451502,0.0001449506,0.0001704555,0.0002128775,0.0003433783,0.0002703486,0.000502363,0.00009547261,0.00002298469],"category_scores_gemma":[0.00006144027,0.0001340629,0.00004956075,0.000520783,0.00005575978,0.001108358,0.0002616629,0.0001309109,0.00007528853],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001722567,"about_ca_system_score_gemma":0.00006538619,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005382266,"about_ca_topic_score_gemma":0.000002524706,"domain_scores_codex":[0.9985558,0.0001840838,0.0003270785,0.0003863274,0.0002242117,0.0003224853],"domain_scores_gemma":[0.9988737,0.00009821748,0.0001805427,0.0004337264,0.0003400041,0.000073824],"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":[0.000002112468,0.00001709317,0.0001898011,0.00006060061,0.000005745349,0.000001737269,0.00016454,9.870763e-7,0.08669259,0.01005515,0.00006235558,0.9027473],"study_design_scores_gemma":[0.000108325,0.00005944512,0.0001983855,0.0000788625,0.000004378687,0.00003996777,0.00005151546,0.5613586,0.4374583,0.0003197518,0.0001818048,0.0001406405],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08641938,0.00001126962,0.8913524,0.00004265659,0.0004005878,0.0001821806,1.676948e-7,0.001070942,0.02052041],"genre_scores_gemma":[0.5021897,8.400166e-7,0.4974511,0.00007562136,0.00007093309,0.000008488289,3.928295e-7,0.000008053496,0.0001948467],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9026067,"threshold_uncertainty_score":0.5466926,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04119228170569745,"score_gpt":0.3182822732577243,"score_spread":0.2770899915520268,"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."}}