{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001873053,0.000933233,0.001472415,0.0006099534,0.0006992352,0.0009047971,0.002679733,0.001952538,0.005665958],"category_scores_gemma":[0.004330754,0.0006183423,0.0005592803,0.0005178926,0.0009333432,0.001383113,0.00214238,0.001944741,0.001071587],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001003851,"about_ca_system_score_gemma":0.001691236,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006914177,"about_ca_topic_score_gemma":0.005332519,"domain_scores_codex":[0.9992251,0.0002179689,0.00005302715,0.000221298,0.0001798348,0.0001027105],"domain_scores_gemma":[0.9981694,0.001157701,0.00008458331,0.0001297646,0.0003521385,0.000106343],"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":[0.0004274358,0.0003613792,0.0006486168,0.0001030327,0.00006641234,0.0001125916,0.000151731,0.352154,0.006539157,0.01138812,0.003800547,0.624247],"study_design_scores_gemma":[0.0000372047,0.00003135894,0.00004240587,0.000003949197,0.000005681998,0.00001469949,0.000006360804,0.9962736,0.0007803707,0.002507503,0.0002917857,0.000005025049],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.006393829,0.00007020298,0.9912528,0.00006537942,0.00006494559,0.00007747483,0.00001830563,0.001245562,0.0008113788],"genre_scores_gemma":[0.268529,0.00007846695,0.7268263,0.0001662034,0.0000630683,0.000394474,0.0001036527,0.000195982,0.003642807],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.006914177,"threshold_uncertainty_score":0.01895452,"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."}}