{"id":"W2577349305","doi":"","title":"Training & Quality Assessment of an Optical Character Recognition Model for Northern Haida.","year":2016,"lang":"en","type":"article","venue":"Language Resources and Evaluation","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Optical character recognition; Computer science; Character (mathematics); Language model; Unicode; Porting; Artificial intelligence; Natural language processing; Hidden Markov model; Speech recognition; Set (abstract data type); 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":[0.00138039,0.000733847,0.0004636255,0.0004987013,0.0006773091,0.0008175591,0.0009798482,0.0006614859,0.002599166],"category_scores_gemma":[0.003678292,0.0003221594,0.0004079424,0.0004174708,0.0003164695,0.0008630855,0.0005934858,0.0005287091,0.001437094],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001306263,"about_ca_system_score_gemma":0.001948607,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.1402283,"about_ca_topic_score_gemma":0.1447897,"domain_scores_codex":[0.9994224,0.0001029505,0.00004370331,0.0001958385,0.0001718022,0.00006333779],"domain_scores_gemma":[0.9979572,0.0004228585,0.00008995333,0.0002519728,0.001179299,0.00009867576],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001737791,0.0006942674,0.04380491,0.0002916771,0.0002456561,0.0003560559,0.0004470484,0.1879176,0.07649422,0.0004741852,0.01272178,0.6748149],"study_design_scores_gemma":[0.0000626551,0.0003828449,0.03711302,0.00002407442,0.0001001638,0.00008860001,0.0003164276,0.9130394,0.04581007,0.0001794591,0.002852395,0.00003086968],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.9339243,0.0005377874,0.05351438,0.0002412699,0.0001824486,0.0002800371,0.00129118,0.004764598,0.00526398],"genre_scores_gemma":[0.961786,0.0001196065,0.02717968,0.00005817198,0.00001417364,0.00008391437,0.003011402,0.0002189084,0.007528018],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.1402283,"threshold_uncertainty_score":0.2788241,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1226647332271734,"score_gpt":0.3879749591543143,"score_spread":0.265310225927141,"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."}}