{"id":"W2734029172","doi":"10.48550/arxiv.1703.05423","title":"End-to-end optimization of goal-driven and visually grounded dialogue systems Harm de Vries","year":2017,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Speech and dialogue systems","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Computer science; Task (project management); Utterance; Artificial intelligence; Context (archaeology); Reinforcement learning; Sequence (biology); Object (grammar); Human–computer interaction","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":[0.001648705,0.001342901,0.00103806,0.0004142405,0.0005548981,0.001156547,0.001153401,0.001658173,0.003672348],"category_scores_gemma":[0.00480139,0.000642737,0.000570341,0.0002174783,0.001111854,0.001043852,0.001884397,0.001756734,0.0007261708],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00145796,"about_ca_system_score_gemma":0.001817563,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006069632,"about_ca_topic_score_gemma":0.00646164,"domain_scores_codex":[0.9992139,0.0003142884,0.00003083454,0.0002384199,0.00009842084,0.0001040675],"domain_scores_gemma":[0.9984471,0.001078057,0.0000929445,0.00009472634,0.0001668651,0.0001202359],"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":[0.0001535527,0.0001144609,0.0004594567,0.00009359679,0.00003675797,0.00009333401,0.0001687024,0.9357467,0.003521151,0.005816572,0.001381809,0.05241401],"study_design_scores_gemma":[0.000008930911,0.00002467327,0.00004401813,0.000004646278,0.00000270399,0.000005427326,0.00001065706,0.9967073,0.0005020754,0.00246419,0.0002226128,0.00000273884],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04680854,0.0003501105,0.945509,0.0004304691,0.00007520388,0.0001620984,0.0001041252,0.001737579,0.004822918],"genre_scores_gemma":[0.8396844,0.0001352605,0.153376,0.0002120742,0.00003295936,0.0002953786,0.0002407185,0.0002710389,0.005752163],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006069632,"threshold_uncertainty_score":0.01228529,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05763941532819348,"score_gpt":0.2097574543190631,"score_spread":0.1521180389908696,"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."}}