{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00258214,0.001040894,0.001587586,0.0009520202,0.0006153601,0.001103672,0.002187792,0.002403843,0.006075742],"category_scores_gemma":[0.01418403,0.001476835,0.001023245,0.000593291,0.001777502,0.002852054,0.001926974,0.004279763,0.001422255],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001221447,"about_ca_system_score_gemma":0.002269748,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004106336,"about_ca_topic_score_gemma":0.005273471,"domain_scores_codex":[0.9987493,0.0004997433,0.00007063885,0.000356047,0.0001927969,0.0001316199],"domain_scores_gemma":[0.989732,0.008226462,0.000307519,0.0007401834,0.000804337,0.000189618],"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":[0.0003070734,0.0002960386,0.002256173,0.0002476384,0.000134499,0.0002407319,0.0002373623,0.6017127,0.005326719,0.02986714,0.008228417,0.3511455],"study_design_scores_gemma":[0.00002518966,0.00002296099,0.00006721588,0.00001252228,0.00001445568,0.00001952539,0.000009188798,0.9829047,0.001200299,0.01525938,0.0004571209,0.000007382752],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02562534,0.0002768507,0.9664972,0.0006145808,0.0001293086,0.00008617173,0.00009793924,0.004485401,0.002187142],"genre_scores_gemma":[0.6120088,0.0002331224,0.380967,0.0005398936,0.00008370665,0.0003628181,0.0004070113,0.0006009729,0.004796643],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.006075742,"threshold_uncertainty_score":0.02032536,"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."}}