{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008089528,0.0001746036,0.0001769459,0.0000357262,0.0002104566,0.00005395409,0.0003604395,0.0002037336,0.00001524004],"category_scores_gemma":[0.000222324,0.0000885388,0.00007525865,0.0001189936,0.0007763137,0.000008549889,0.0002845423,0.0001621176,0.000006107407],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000008133011,"about_ca_system_score_gemma":0.00006669334,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004908171,"about_ca_topic_score_gemma":0.000004096161,"domain_scores_codex":[0.9988673,0.0001399776,0.0003472612,0.0001466253,0.0001991554,0.000299736],"domain_scores_gemma":[0.9992264,0.000139518,0.0001407332,0.0003524943,0.00004842438,0.00009241896],"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":[0.0006235659,0.0001836298,0.001137957,0.0002456064,0.0005046788,0.00001411096,0.01023935,0.00005593395,0.004957666,0.0005402935,0.005721956,0.9757752],"study_design_scores_gemma":[0.003555789,0.0004330628,0.0009230303,0.00009399501,0.000212522,0.0003586216,0.003148347,0.9531222,0.007332956,0.0005419638,0.02975692,0.0005206013],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02010473,0.0006106107,0.9784506,0.0001786075,0.0001752586,0.0002596395,0.00001253655,0.00002877646,0.000179245],"genre_scores_gemma":[0.05871345,0.0001228134,0.9396815,0.001164378,0.0002071747,0.00002204312,0.00001455783,0.00001906994,0.00005499913],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9752547,"threshold_uncertainty_score":0.3610508,"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."}}