{"id":"W3110986327","doi":"10.1609/aaai.v35i16.17713","title":"CARE: Commonsense-Aware Emotional Response Generation with Latent Concepts","year":2021,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Topic Modeling","field":"Computer Science","cited_by":35,"is_retracted":false,"has_abstract":true,"ca_institutions":"BC Research (Canada)","funders":"Nanyang Technological University; National Research Foundation Singapore; National Research Foundation","keywords":"Rationality; Construct (python library); Computer science; Field (mathematics); Cognitive psychology; Commonsense reasoning; Neglect; Focus (optics); Commonsense knowledge; Artificial intelligence; Cognitive science; Psychology; Epistemology; Knowledge base","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":[0.002839928,0.001096021,0.0007511929,0.0006647184,0.0004952141,0.001145141,0.001799464,0.001405028,0.002927131],"category_scores_gemma":[0.01059803,0.0004712902,0.001253777,0.0004220468,0.001138262,0.002407039,0.002278564,0.002462787,0.0008203326],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009261831,"about_ca_system_score_gemma":0.0006957736,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00217359,"about_ca_topic_score_gemma":0.003152627,"domain_scores_codex":[0.9980033,0.001089452,0.00006574924,0.0004883031,0.0002335577,0.0001196023],"domain_scores_gemma":[0.9960381,0.002730586,0.0002704719,0.0004731667,0.0002785107,0.0002091281],"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":[0.001197416,0.00109097,0.008624764,0.000551964,0.000385669,0.0004736735,0.003065144,0.3545786,0.03065441,0.05918868,0.01524315,0.5249456],"study_design_scores_gemma":[0.00004935995,0.00009346866,0.0005471979,0.00001628656,0.00003355819,0.00006380511,0.00007047705,0.9692603,0.002465238,0.02562515,0.001747726,0.00002737973],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03095336,0.0005074723,0.9628081,0.0007353191,0.0001004595,0.0002484446,0.0001772155,0.002185057,0.002284632],"genre_scores_gemma":[0.7478228,0.0002344047,0.2450525,0.0006837361,0.0001147021,0.0006226506,0.0005136988,0.0002013001,0.00475409],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002927131,"threshold_uncertainty_score":0.01501912,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1074049631242067,"score_gpt":0.3075754435097127,"score_spread":0.2001704803855061,"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."}}