TL;DR本文提出了一种 TWR-VAE 模型，可以有效地避免 RNN-based VAE 模型在文本生成时出现的 KL loss vanishing 问题，从而提高了文本生成的多样性和效果。
Abstract
The variational autoencoder (VAE) is a popular and powerful model applied to text modelling to generate diverse sentences. However, an issue known as →