{"id":"W2970680405","doi":"10.18653/v1/d19-1201","title":"Modeling Personalization in Continuous Space for Response Generation via Augmented Wasserstein Autoencoders","year":2019,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":48,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"National Key Research and Development Program of China; National Natural Science Foundation of China; National Science Foundation","keywords":"Personalization; Computer science; Chen; Joint (building); Space (punctuation); Artificial intelligence; Natural language processing; World Wide Web; Engineering; Operating system","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":[],"consensus_categories":[],"category_scores_codex":[0.000590227,0.00008836074,0.0001184784,0.0001765924,0.00004721149,0.0001007119,0.0001692817,0.00005757608,0.0001023376],"category_scores_gemma":[0.00008797883,0.00008550222,0.00005069908,0.0002185232,0.000005255045,0.0003856443,0.00002436588,0.00003723809,0.0000623426],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000085991,"about_ca_system_score_gemma":0.00005239002,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005505278,"about_ca_topic_score_gemma":0.0001160545,"domain_scores_codex":[0.9990822,0.0001129658,0.00018264,0.0002915993,0.0001604273,0.0001701836],"domain_scores_gemma":[0.9995335,0.0000996608,0.000037668,0.0001882518,0.0001011979,0.00003968034],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001031692,0.0004236147,0.001771777,0.00009808221,0.00007754628,0.00001568445,0.006211359,0.152879,0.7100931,0.03459223,0.002451268,0.0903547],"study_design_scores_gemma":[0.0005947705,0.0000582881,0.00005761364,0.00001390882,0.000002331272,0.000002915999,0.0002256471,0.9867557,0.01173848,0.0002604844,0.0001704362,0.0001194493],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2648813,0.000009934505,0.7331399,0.0009959592,0.0001445273,0.0003095195,7.843842e-7,0.00008258527,0.0004354923],"genre_scores_gemma":[0.8298736,0.000002627984,0.1675995,0.0003793249,0.00002073913,0.00003486593,0.000009584902,0.000008316524,0.002071412],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8338767,"threshold_uncertainty_score":0.3486679,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0294755678688546,"score_gpt":0.2524900829017831,"score_spread":0.2230145150329285,"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."}}