{"id":"W2011012373","doi":"10.1109/icdar.2013.107","title":"Improving HMM-Based Keyword Spotting with Character Language Models","year":2013,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":38,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"","keywords":"Keyword spotting; Computer science; Spotting; Hidden Markov model; Artificial intelligence; Lexicon; Character (mathematics); Language model; Natural language processing; Speech recognition; Handwriting recognition; Context (archaeology); Optical character recognition; Pattern recognition (psychology); Feature extraction; 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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001733035,0.0001478648,0.000134943,0.0001292078,0.00007839507,0.000348728,0.0005025614,0.00005503458,0.0002867511],"category_scores_gemma":[0.00001307617,0.0001083619,0.000042114,0.0002263496,0.00002602678,0.00145005,0.0001114921,0.0001382296,0.000267717],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002826217,"about_ca_system_score_gemma":0.00005069177,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004091453,"about_ca_topic_score_gemma":0.00001014206,"domain_scores_codex":[0.9989073,0.00003429674,0.0001780055,0.0003467792,0.0002240647,0.000309591],"domain_scores_gemma":[0.9991568,0.00005765709,0.00008762253,0.0004622156,0.0001363238,0.00009943583],"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":[0.000005410119,0.0001021298,0.0004352008,0.00005019073,0.00001587424,0.00003950742,0.0008426125,0.00003004478,0.03727086,0.0089102,0.000941103,0.9513569],"study_design_scores_gemma":[0.0004006706,0.0001240788,0.0005746931,0.00006858241,0.000004883798,0.00002031749,0.00008501534,0.7964494,0.200107,0.001650901,0.000107814,0.0004067076],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08404182,0.0000103652,0.9037604,0.0005215269,0.00003011238,0.000300712,7.444028e-7,0.001139617,0.01019474],"genre_scores_gemma":[0.6510567,5.056323e-7,0.3464977,0.001415415,0.00003471288,0.0000836305,0.000002828587,0.00001254897,0.0008959089],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9509501,"threshold_uncertainty_score":0.4418871,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009690508726509334,"score_gpt":0.2108766470808638,"score_spread":0.2011861383543544,"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."}}