Emotional Dialogue Generation Based on Conditional Variational Autoencoder and Dual Emotion Framework

Table 3

Diversity scores for the CVAE-DE and the baselines. Distinct-1 and Distinct-2 are the ratios of distinct unigrams and bigrams in the generated responses.

Model	Distinct-1	Distinct-2
Seq2Seq [21]	0.0045	0.0353
ECM [14]	0.0062	0.0396
CVAE [16]	0.0256	0.2635
CVAE-MTDA [25]	0.0287	0.2712
EDGAN [27]	0.0273	0.2658
CVAE-DE	0.0308	0.2836
Target responses	0.0952	0.5897