{"id":"W1515737728","doi":"10.1007/978-3-642-02017-9_40","title":"An Online Algorithm for Applying Reinforcement Learning to Handle Ambiguity in Spoken Dialogues","year":2009,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Speech and dialogue systems","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Guelph","funders":"","keywords":"Computer science; Reinforcement learning; Ambiguity; Artificial intelligence; Natural language; Online learning; Reinforcement; Human–computer interaction; Natural language processing; Multimedia; Programming language","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":[0.001495866,0.0005485989,0.000714367,0.001160396,0.0002787258,0.0004884753,0.00292466,0.0003166692,0.000003773574],"category_scores_gemma":[0.0001402217,0.0005289515,0.0001338127,0.0007036895,0.0001645774,0.0006413648,0.0006345853,0.0006634407,0.00002083047],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004585398,"about_ca_system_score_gemma":0.0004520632,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002247448,"about_ca_topic_score_gemma":0.0007648304,"domain_scores_codex":[0.9956996,0.00005257588,0.0007306752,0.001675058,0.0008822817,0.0009597912],"domain_scores_gemma":[0.9977363,0.0002980627,0.0002689597,0.001132674,0.0002298714,0.000334128],"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":[0.000008964738,0.0000377398,0.00004151171,0.00001782466,0.000003629084,0.00003285638,0.000952892,0.1265106,0.000122846,0.0005625853,0.00001003479,0.8716985],"study_design_scores_gemma":[0.0006238985,0.001064257,0.0003378287,0.0004644852,0.000004901952,0.00002315069,0.000001230307,0.96572,0.0009953453,0.02566901,0.004269005,0.0008268827],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0002016063,0.000193981,0.9957408,0.0002232836,0.00139676,0.001469377,0.00001025903,0.0001878921,0.0005759874],"genre_scores_gemma":[0.08832205,0.00002921978,0.9077063,0.001935088,0.001385381,0.00008873981,0.00009460546,0.00004361699,0.0003949928],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8708716,"threshold_uncertainty_score":0.9997162,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03491495359236249,"score_gpt":0.2726276674597225,"score_spread":0.23771271386736,"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."}}