{"id":"W2902138027","doi":"10.1007/978-3-030-17705-8_9","title":"Generating Responses Expressing Emotion in an Open-Domain Dialogue System","year":2019,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Topic Modeling","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Sentence; Encoder; Artificial intelligence; Natural language processing; Artificial neural network; Open domain; Domain (mathematical analysis); Speech recognition; Machine learning; Question answering","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","scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.002556723,0.0005038669,0.0006529543,0.0009639917,0.0003037085,0.002092802,0.005756617,0.0003598509,0.000004337447],"category_scores_gemma":[0.00009482691,0.0004891107,0.00006308165,0.000483298,0.0002098555,0.001973229,0.002997593,0.0007933869,0.00002198012],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007030597,"about_ca_system_score_gemma":0.000940419,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001095348,"about_ca_topic_score_gemma":0.0002713437,"domain_scores_codex":[0.9952599,0.0002397288,0.0007806377,0.002145363,0.0008656165,0.0007087553],"domain_scores_gemma":[0.9967525,0.0004457285,0.0003799061,0.002110146,0.000161175,0.0001505194],"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":[0.00001938004,0.0000403528,0.0003496348,0.0001317184,0.000005316218,0.0002565228,0.004150106,0.4654202,0.005615671,0.05045782,0.000003962308,0.4735493],"study_design_scores_gemma":[0.0003431526,0.0001308446,0.0001165756,0.001367858,0.000002233795,0.00007192282,0.00000188404,0.9803696,0.0005851484,0.01634605,0.00008052823,0.0005842376],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01152211,0.0001965544,0.9836969,0.0002112535,0.002301071,0.0006960329,0.000003783575,0.0001578889,0.001214421],"genre_scores_gemma":[0.4097901,0.000003176395,0.5891461,0.0004707681,0.0004165486,0.000009208033,0.0000048388,0.00003215986,0.0001271286],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.5149494,"threshold_uncertainty_score":0.999756,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04062409163093213,"score_gpt":0.2750319400816078,"score_spread":0.2344078484506756,"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."}}