{"id":"W2875408189","doi":"","title":"The APVA-TURBO Approach To Question Answering in Knowledge Base","year":2018,"lang":"en","type":"article","venue":"International Conference on Computational Linguistics","topic":"Topic Modeling","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"","keywords":"Question answering; Computer science; Correctness; Bottleneck; Knowledge base; Object (grammar); Artificial intelligence; Base (topology); Subject (documents); Information retrieval; Theoretical computer science; Machine learning; Programming language; World Wide Web","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":[0.0005605672,0.0001455857,0.0001062916,0.0001962695,0.0001861426,0.0003452326,0.001101008,0.00004968825,0.000008368925],"category_scores_gemma":[0.001425322,0.000127324,0.00003378272,0.0002472796,0.00007021613,0.00006853541,0.0002413263,0.0001966434,0.0001463758],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001762882,"about_ca_system_score_gemma":0.000229289,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003141662,"about_ca_topic_score_gemma":0.00004688915,"domain_scores_codex":[0.998434,0.00007744173,0.0003521611,0.0004275321,0.0004666879,0.0002421682],"domain_scores_gemma":[0.9978457,0.0003276865,0.0000856039,0.0002792889,0.001362666,0.00009904717],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001389989,0.00007478104,0.000158607,0.00000278943,0.000007755812,0.000002812237,0.0004808957,0.03289331,0.00001055297,0.9554626,0.0002289159,0.01066302],"study_design_scores_gemma":[0.0001774381,0.00005555214,0.001324667,0.00005450029,0.000001177134,0.000003950337,0.00003094285,0.906776,0.00005108608,0.08408241,0.007303573,0.000138763],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002513832,0.0000131933,0.8715593,0.001266109,0.002835723,0.0001533294,0.000006369505,0.00008397581,0.1215681],"genre_scores_gemma":[0.862905,0.000002895132,0.1354008,0.0003854254,0.0009915937,0.00002105151,0.00001376158,0.000007966835,0.0002714179],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8738827,"threshold_uncertainty_score":0.5192123,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06531592434647242,"score_gpt":0.3406081913215932,"score_spread":0.2752922669751208,"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."}}