{"id":"W2044833006","doi":"10.1186/1471-2105-12-s3-s1","title":"Building a biomedical tokenizer using the token lattice design pattern and the adapted Viterbi algorithm","year":2011,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":18,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Victoria","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Lexical analysis; Computer science; Security token; Viterbi algorithm; Artificial intelligence; Domain (mathematical analysis); Classifier (UML); Natural language processing; Hidden Markov model","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003681378,0.0008568852,0.001024551,0.00165702,0.0009850726,0.001686656,0.002550131,0.001530368,0.00698993],"category_scores_gemma":[0.008888351,0.0007438266,0.0008925386,0.001750783,0.001522988,0.002720439,0.00179246,0.001971955,0.006255101],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001314822,"about_ca_system_score_gemma":0.004042481,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002987431,"about_ca_topic_score_gemma":0.004175759,"domain_scores_codex":[0.9972269,0.0007947775,0.0003970889,0.0007527433,0.0006459167,0.0001826235],"domain_scores_gemma":[0.995963,0.001775967,0.0003604054,0.0006378702,0.001107142,0.0001555773],"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":[0.001259873,0.0002560883,0.004131099,0.0007308389,0.0001285256,0.0005084223,0.0006422807,0.06571659,0.05401304,0.04926799,0.018463,0.8048822],"study_design_scores_gemma":[0.000212442,0.0002862001,0.0004676236,0.00006739573,0.00008615672,0.0005892296,0.0001510604,0.8075851,0.1221585,0.03745641,0.03085531,0.00008475347],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00686898,0.00007498647,0.9856205,0.0001785225,0.00007670069,0.0001534221,0.00018474,0.005908059,0.0009341781],"genre_scores_gemma":[0.0477733,0.00005790616,0.9484025,0.0001489063,0.00002805959,0.0002295472,0.0006339634,0.000627663,0.002098216],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.00698993,"threshold_uncertainty_score":0.02338362,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06077148618579305,"score_gpt":0.2754870983270212,"score_spread":0.2147156121412281,"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."}}