{"id":"W2599940792","doi":"10.24963/ijcai.2017/385","title":"End-to-end optimization of goal-driven and visually grounded dialogue systems","year":2017,"lang":"en","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":89,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"Agence Nationale de la Recherche; Compute Canada; Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs; Canadian Institute for Advanced Research","keywords":"Computer science; Task (project management); Utterance; Artificial intelligence; Reinforcement learning; Sequence (biology); Object (grammar); Human–computer interaction; Engineering","routes":{"ca_aff":true,"ca_fund":true,"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":[],"consensus_categories":[],"category_scores_codex":[0.0002020448,0.00009108106,0.0001468885,0.00007495482,0.000269062,0.0003567939,0.0008044482,0.00004553928,0.0000108863],"category_scores_gemma":[0.0001179839,0.00008211179,0.00002155164,0.00008188362,0.00005619489,0.0003428973,0.0003717657,0.00006908405,0.00002261182],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001904335,"about_ca_system_score_gemma":0.00002873353,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003860651,"about_ca_topic_score_gemma":0.00006977852,"domain_scores_codex":[0.9991533,0.000050226,0.0001903351,0.0002983418,0.0001749669,0.0001328983],"domain_scores_gemma":[0.9987137,0.00008758599,0.0001836369,0.0008189118,0.0001003512,0.00009584566],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00000927416,0.0001292749,0.02643525,0.00006736848,0.00004275984,0.000002649314,0.001273597,0.3702055,0.00476227,0.5719841,0.0002447258,0.02484323],"study_design_scores_gemma":[0.0002034197,0.00004880041,0.109107,0.00001472585,0.000004263599,0.000004049466,0.000009353226,0.8900375,0.0001188863,0.0001547099,0.0001995491,0.00009776052],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03874923,0.000009674429,0.95287,0.001055582,0.000119068,0.0002933745,0.000003554414,0.0001037722,0.006795742],"genre_scores_gemma":[0.8526888,0.000004306224,0.1469848,0.00004516368,0.00003351991,0.00003084437,0.000004645758,0.000006606255,0.0002013047],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8139395,"threshold_uncertainty_score":0.5836174,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01768662620118641,"score_gpt":0.293410836131722,"score_spread":0.2757242099305356,"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."}}