{"id":"W2128826758","doi":"10.1109/icdar.2009.78","title":"Handling Out-of-Vocabulary Words and Recognition Errors Based on Word Linguistic Context for Handwritten Sentence Recognition","year":2009,"lang":"en","type":"preprint","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"École de Technologie Supérieure","funders":"","keywords":"Computer science; Speech recognition; Word error rate; Artificial intelligence; Natural language processing; Vocabulary; Focus (optics); Word (group theory); Sentence; Classifier (UML); Language model; 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":[0.0008567448,0.001301958,0.0013518,0.001009366,0.0003525967,0.001057755,0.001100674,0.0008425853,0.001648712],"category_scores_gemma":[0.006866212,0.0003951148,0.0005337877,0.0007155403,0.0005130661,0.002110753,0.0007903297,0.0009101372,0.001143996],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002452341,"about_ca_system_score_gemma":0.0006595533,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009296205,"about_ca_topic_score_gemma":0.001770952,"domain_scores_codex":[0.9986601,0.000353733,0.0001261716,0.0003299391,0.0004441988,0.00008591631],"domain_scores_gemma":[0.9935325,0.003162734,0.001239461,0.001092242,0.0008332353,0.0001397427],"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":[0.0006932523,0.0002303674,0.004384035,0.0006307724,0.000112819,0.0008096991,0.0004104612,0.02296045,0.2093812,0.001074755,0.001357679,0.7579545],"study_design_scores_gemma":[0.00005344686,0.0007733065,0.009549556,0.000123315,0.0002538595,0.002157539,0.000342333,0.7041557,0.2721555,0.005577827,0.004737078,0.0001206306],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.192506,0.001828621,0.7997931,0.0002341319,0.0001595662,0.0001354737,0.0002164484,0.004270974,0.0008556546],"genre_scores_gemma":[0.6112373,0.0007753894,0.3844265,0.0001404799,0.0001424165,0.00009708653,0.0005986204,0.0004309438,0.002151243],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.001648712,"threshold_uncertainty_score":0.005515516,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04528160092575161,"score_gpt":0.2989305269474514,"score_spread":0.2536489260216997,"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."}}