{"id":"W2077054502","doi":"10.1145/2396761.2398676","title":"Improving the performance of the reinforcement learning model for answering complex questions","year":2012,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Lethbridge","funders":"","keywords":"Reinforcement learning; Automatic summarization; Computer science; Question answering; Artificial intelligence; Task (project management); Set (abstract data type); Sentence; Natural language processing; Process (computing); Reinforcement; Feature (linguistics); Machine learning","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004270934,0.0009127955,0.0013601,0.0004407932,0.000380542,0.0008793787,0.001515688,0.001442257,0.001347251],"category_scores_gemma":[0.01641495,0.0003214889,0.0004569804,0.0003590105,0.0004068412,0.00225204,0.0009810845,0.00190807,0.0007170714],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008477076,"about_ca_system_score_gemma":0.001040551,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006126635,"about_ca_topic_score_gemma":0.004142758,"domain_scores_codex":[0.9986541,0.0006888465,0.00006279467,0.0002946906,0.0002070469,0.00009257467],"domain_scores_gemma":[0.9922335,0.005844942,0.0003171817,0.0005270423,0.0008584505,0.000218757],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0007910152,0.0006748268,0.004140394,0.0001527205,0.0001034424,0.000131571,0.0003019303,0.6868618,0.01177188,0.003910266,0.003615915,0.2875443],"study_design_scores_gemma":[0.00001257794,0.00004773894,0.0001194042,0.000001355353,0.00000383421,0.000006093207,0.000005018808,0.9981375,0.0007433538,0.0008029216,0.0001168674,0.000003449475],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1666465,0.0008361678,0.8254575,0.0006952152,0.00009489799,0.000115726,0.00009756299,0.003749511,0.002307042],"genre_scores_gemma":[0.868794,0.0001835065,0.1283477,0.0001921382,0.00008373614,0.00009640784,0.0003013448,0.0001285814,0.001872609],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006126635,"threshold_uncertainty_score":0.02258718,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04739034023367434,"score_gpt":0.2605318500398405,"score_spread":0.2131415098061661,"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."}}