{"id":"W2963172394","doi":"10.1109/icassp.2019.8682634","title":"Why Do Neural Dialog Systems Generate Short and Meaningless Replies? a Comparison between Dialog and Translation","year":2019,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"National Natural Science Foundation of China","keywords":"Dialog box; Computer science; Utterance; Natural language processing; Machine translation; Randomness; Dialog system; Sequence (biology); Artificial intelligence; Translation (biology); Speech recognition; Conjecture; World Wide Web; Mathematics","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":[0.0003125678,0.0001329021,0.0002743622,0.00006577279,0.00007833762,0.0003806351,0.0002326712,0.00007301476,0.000003888661],"category_scores_gemma":[0.000005702588,0.0001148571,0.00002195801,0.00009894678,0.00002251761,0.0004181369,0.0001094025,0.0001069573,0.000003374176],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001329343,"about_ca_system_score_gemma":0.00001118512,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001814871,"about_ca_topic_score_gemma":0.00003355269,"domain_scores_codex":[0.9987443,0.00008079218,0.0002923211,0.0004850932,0.0001927235,0.0002047781],"domain_scores_gemma":[0.9993411,0.00009806113,0.00005083491,0.0003876871,0.00003439156,0.00008788834],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001597269,0.00003615754,0.7054428,0.0001963815,0.00007416547,0.0000083072,0.005257822,0.01075265,0.004930312,0.05057527,0.0005510445,0.2221591],"study_design_scores_gemma":[0.0002828087,0.00006170047,0.008736921,0.00002491744,0.00001237728,0.000008948681,0.00002611364,0.9893007,0.0002298728,0.0004838085,0.000628105,0.0002037356],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5791724,0.0007461275,0.4177231,0.0003362095,0.0003068144,0.0002370345,0.0000013493,0.0000989866,0.00137795],"genre_scores_gemma":[0.9923786,0.00001331093,0.007227067,0.0001793128,0.000133086,0.000006867719,0.000003807553,0.000008140256,0.00004983319],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.978548,"threshold_uncertainty_score":0.4683736,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05761809124299732,"score_gpt":0.2660111035770797,"score_spread":0.2083930123340824,"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."}}