{"id":"W2009946426","doi":"10.1007/s10032-003-0113-0","title":"Lexicon-driven HMM decoding for large vocabulary handwriting recognition with multiple character models","year":2003,"lang":"en","type":"article","venue":"International Journal on Document Analysis and Recognition (IJDAR)","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":35,"is_retracted":false,"has_abstract":false,"ca_institutions":"Concordia University; École de Technologie Supérieure","funders":"Conselho Nacional de Desenvolvimento Científico e Tecnológico","keywords":"Computer science; Bigram; Lexicon; Hidden Markov model; Speech recognition; Vocabulary; Artificial intelligence; Word recognition; Handwriting recognition; Natural language processing; Word (group theory); Segmentation; Optical character recognition; Tree (set theory); Decoding methods; Handwriting; Pattern recognition (psychology); Feature extraction; Linguistics; Mathematics; Algorithm","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":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.001176099,0.0003189747,0.0004156873,0.001267094,0.0004532217,0.001288791,0.0004408445,0.0001324331,0.0003047548],"category_scores_gemma":[0.0001584213,0.0002680748,0.0003949512,0.0004923626,0.00003761649,0.002087288,0.00007275981,0.0003554187,0.00003611584],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001673799,"about_ca_system_score_gemma":0.00008444432,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001059983,"about_ca_topic_score_gemma":0.00004519608,"domain_scores_codex":[0.9972438,0.0002132972,0.0007478267,0.0006025215,0.0007715062,0.0004210166],"domain_scores_gemma":[0.9974425,0.0003266168,0.0006145889,0.0002029297,0.001177291,0.0002360045],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0007757914,0.001574928,0.01318333,0.00007363849,0.009349973,0.0003504897,0.001708252,0.0004594961,0.002696313,0.01988896,0.00117479,0.948764],"study_design_scores_gemma":[0.02172159,0.002779191,0.003724408,0.002570496,0.003120809,0.002256643,0.001295576,0.3908651,0.1344539,0.4205827,0.01246253,0.004167031],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1342117,0.00007282832,0.8628758,0.000909699,0.0003424365,0.0003572784,0.00009182437,0.0001275857,0.001010915],"genre_scores_gemma":[0.8853437,0.0006228443,0.1118416,0.001265231,0.0002960353,0.0001267096,0.0003113504,0.00002851395,0.0001639616],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.944597,"threshold_uncertainty_score":0.9999772,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02501651241459563,"score_gpt":0.2759748070783409,"score_spread":0.2509582946637453,"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."}}