{"id":"W2017882693","doi":"10.1016/j.artmed.2014.03.005","title":"A token centric part-of-speech tagger for biomedical text","year":2014,"lang":"en","type":"article","venue":"Artificial Intelligence in Medicine","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":8,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Victoria","funders":"","keywords":"Computer science; Artificial intelligence; Security token; Natural language processing; Classifier (UML); Part-of-speech tagging; Lemmatisation; Domain (mathematical analysis); Training set; Speech recognition; Part of speech","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":[0.0009475589,0.0001423875,0.0002982937,0.0001314494,0.00004006695,0.000005025693,0.0002833787,0.0002266078,0.0001165237],"category_scores_gemma":[0.002928765,0.0001086578,0.00006579921,0.0003055583,0.0006769742,0.000002107818,0.0000613407,0.0001154914,0.00001529246],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001052176,"about_ca_system_score_gemma":0.00004620285,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007789692,"about_ca_topic_score_gemma":0.00005920489,"domain_scores_codex":[0.9984511,0.00007298068,0.0005746779,0.0003406656,0.0002216794,0.0003389598],"domain_scores_gemma":[0.9991756,0.0002210227,0.0001119278,0.0002779984,0.0000949603,0.0001184774],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001623988,0.0001241365,0.0006354573,0.00004439754,0.00001964175,0.000003384637,0.0002489582,0.00001128448,0.04359546,0.002643983,0.006003367,0.9465075],"study_design_scores_gemma":[0.0004562913,0.003297707,0.0004120703,0.0002659702,0.00004439155,0.00001865702,0.00174501,0.00608388,0.2351168,0.01759393,0.7345716,0.0003937425],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.4927817,0.002259739,0.4870322,0.01205684,0.002489649,0.0007920855,0.00002871521,0.00006146744,0.002497639],"genre_scores_gemma":[0.9922843,0.0001549233,0.005451049,0.0004760255,0.001331657,0.00003979992,0.00007622325,0.00001519104,0.0001708154],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9461138,"threshold_uncertainty_score":0.4430938,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05250969537362214,"score_gpt":0.3476245910035085,"score_spread":0.2951148956298863,"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."}}