{"id":"W2019010736","doi":"10.1109/icip.2014.7025519","title":"Context-dependent BLSTM models. Application to offline handwriting recognition","year":2014,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"École de Technologie Supérieure","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Context (archaeology); Context model; Speech recognition; Feature (linguistics); Handwriting; Artificial intelligence; Cluster analysis; Hidden Markov model; Natural language processing; Pattern recognition (psychology); Linguistics; Object (grammar)","routes":{"ca_aff":true,"ca_fund":true,"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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.000778261,0.0001657298,0.0002019138,0.0002034347,0.0001318742,0.0002064235,0.0005936331,0.00009135254,0.00005184186],"category_scores_gemma":[0.00008861678,0.0001634562,0.00007755694,0.0003324876,0.0000187084,0.0007353373,0.0002169922,0.0001280537,0.0007836451],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005582504,"about_ca_system_score_gemma":0.00002184765,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001356528,"about_ca_topic_score_gemma":0.00007834625,"domain_scores_codex":[0.9983338,0.0000880272,0.0003662449,0.0005703709,0.0003480646,0.0002934879],"domain_scores_gemma":[0.9987161,0.0001045883,0.00008924737,0.0005887094,0.0003196437,0.0001817535],"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":[0.000003584836,0.00004729654,0.000007169679,0.000008610828,0.00000646535,5.378318e-7,0.0001012888,0.00003974714,0.002912624,0.02845962,0.0007842554,0.9676288],"study_design_scores_gemma":[0.0006430399,0.0002722647,0.00005016264,0.00008430176,0.00001423973,0.00003380439,0.00006900642,0.5481914,0.2253368,0.2121679,0.01252702,0.0006100866],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002233222,0.00002192657,0.9670584,0.001380353,0.00007123291,0.0005036051,0.000004475949,0.001232661,0.02749408],"genre_scores_gemma":[0.807772,0.00001034135,0.1883022,0.003205095,0.0001124939,0.0002413884,0.00001824779,0.00001513162,0.000323092],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9670187,"threshold_uncertainty_score":0.9999943,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02251295593834747,"score_gpt":0.2490320440562123,"score_spread":0.2265190881178649,"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."}}