{"id":"W2119785746","doi":"10.1007/s10994-009-5110-1","title":"Training parsers by inverse reinforcement learning","year":2009,"lang":"en","type":"article","venue":"Machine Learning","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":70,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Treebank; Parsing; Computer science; Generalization; Artificial intelligence; Set (abstract data type); Reinforcement learning; Function (biology); Machine learning; Training set; Inverse; Algorithm; Mathematics","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008953355,0.0003839408,0.0003607798,0.0002349635,0.0006687189,0.0003959622,0.001049948,0.0001285741,0.0001496414],"category_scores_gemma":[0.0004570929,0.0003951638,0.0001461874,0.000618353,0.00005147299,0.0007917808,0.0002581384,0.001240626,0.0002110276],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001395637,"about_ca_system_score_gemma":0.00006895386,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004715834,"about_ca_topic_score_gemma":0.000002343312,"domain_scores_codex":[0.9969763,0.0002636314,0.0005470503,0.0006213092,0.0007161278,0.0008755513],"domain_scores_gemma":[0.9986634,0.0001464611,0.0003623147,0.0005023463,0.00006959905,0.0002559408],"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":[0.000008422765,0.00001273687,0.002007385,0.000007574753,0.00002359098,0.0000211593,0.002873796,0.9460119,0.001455483,0.002259953,0.00109552,0.0442225],"study_design_scores_gemma":[0.0005922793,0.0005454859,0.0002844098,0.00003854511,0.00001144084,0.00001791053,0.0002042134,0.873429,0.0002741941,0.00009226264,0.1240824,0.0004278263],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.005371991,0.00014026,0.9577644,0.00114814,0.0002612589,0.0002055405,2.007742e-7,0.001094244,0.03401393],"genre_scores_gemma":[0.9683691,0.00006538298,0.01549407,0.001529333,0.00008932386,0.000008185975,0.0000534885,0.00003292012,0.01435818],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9629971,"threshold_uncertainty_score":0.99985,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02311423201309188,"score_gpt":0.2528785846531024,"score_spread":0.2297643526400105,"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."}}