Xiaodong Gu, Kyunghyun Cho, Jungwoo Ha, Sunghun Kim
TL;DR提出了 DialogWAE,这是一种特殊设计的条件 WAE,用于对话建模,能够通过在潜变量空间内训练 GAN 来模拟数据的分布,并进一步发展了高斯混合先验网络,能够产生具有更连贯、更丰富和更多样化响应的结果。
Abstract
variational autoencoders (VAEs) have shown a promise in data-driven conversation modeling. However, most VAE conversation models match the approximate posterior distribution over the latent variables to a simple prior such as standard normal distribution, thereby restricting the genera