{"id":"W2186676076","doi":"","title":"UBC Entity Linking at TAC-KBP 2013: random forests for high accuracy","year":2013,"lang":"en","type":"article","venue":"Theory and applications of categories","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Computer science; Cluster analysis; Random forest; Task (project management); Artificial intelligence; Natural language processing; Generative grammar; F1 score; Reuse; Machine learning; Data mining; Biology","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01419355,0.003326484,0.002051242,0.003455352,0.003165946,0.002987997,0.003410683,0.003829863,0.008985301],"category_scores_gemma":[0.03239938,0.001293577,0.002022798,0.004167782,0.0009596715,0.004815739,0.002867749,0.004281954,0.01340749],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001605938,"about_ca_system_score_gemma":0.002312879,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01886444,"about_ca_topic_score_gemma":0.02416482,"domain_scores_codex":[0.9885854,0.004481259,0.0006546302,0.002460254,0.002658359,0.001160123],"domain_scores_gemma":[0.9805053,0.008574196,0.0004045643,0.005032044,0.004702898,0.0007810647],"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":[0.002557623,0.001234231,0.008428264,0.0007835568,0.0008303439,0.0008237434,0.0006318429,0.1217796,0.0154825,0.00365045,0.3588516,0.4849464],"study_design_scores_gemma":[0.0005279536,0.0003001944,0.006081909,0.0001019707,0.0001930346,0.0004982976,0.0002666486,0.9099913,0.03248469,0.01245867,0.0369045,0.0001908086],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1929047,0.004119829,0.4354928,0.002649304,0.003057291,0.001406747,0.03325948,0.3066565,0.02045338],"genre_scores_gemma":[0.3880635,0.0004313256,0.5039542,0.0008088416,0.0005164975,0.0008701558,0.08214323,0.01406678,0.009145452],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01886444,"threshold_uncertainty_score":0.07506359,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.007377326336720849,"score_gpt":0.2619472615456965,"score_spread":0.2545699352089757,"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."}}