{"id":"W4244522263","doi":"10.1002/asi.20463","title":"The reusability of induced knowledge for the automatic semantic markup of taxonomic descriptions","year":2006,"lang":"en","type":"article","venue":"Journal of the American Society for Information Science and Technology","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University","funders":"","keywords":"Markup language; Computer science; Natural language processing; Knowledge base; XML; Artificial intelligence; Information retrieval; Reusability; Text corpus; World Wide Web; Programming language; Software","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"simulation_or_modeling","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"medium","status":"direct model label, unvalidated"},{"model":"gpt","categories":[],"domain":null,"study_design":"design_other","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"low","status":"direct model label, unvalidated"}],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007645577,0.0003888795,0.0004183366,0.003645443,0.000777719,0.001756452,0.001539736,0.0007446471,0.001566371],"category_scores_gemma":[0.04151201,0.0005857194,0.0005359632,0.002100739,0.001227902,0.005339296,0.002204625,0.001282708,0.0005676982],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000768791,"about_ca_system_score_gemma":0.001051258,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001092489,"about_ca_topic_score_gemma":0.00191861,"domain_scores_codex":[0.9943753,0.003033476,0.0005580852,0.0008012558,0.001131906,0.00009998209],"domain_scores_gemma":[0.9507815,0.03122158,0.00274666,0.01156186,0.00343634,0.0002521241],"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":[0.0004419247,0.0005084779,0.008655181,0.00106052,0.0001465126,0.0008218074,0.002462421,0.02190311,0.07597803,0.04392258,0.006709063,0.8373904],"study_design_scores_gemma":[0.0001100658,0.000457287,0.01356649,0.0005427751,0.0002317398,0.001543271,0.001277742,0.49575,0.3621409,0.05647417,0.06770004,0.0002055211],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1228889,0.0003395053,0.8614857,0.0005161362,0.00006828222,0.0002947043,0.001390762,0.008289433,0.004726493],"genre_scores_gemma":[0.357155,0.0002182849,0.6371978,0.0001236255,0.0000316369,0.0002155008,0.003441875,0.0005749631,0.001041237],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007645577,"threshold_uncertainty_score":0.04043418,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01596344210632304,"score_gpt":0.2855851794837944,"score_spread":0.2696217373774714,"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."}}