Improved Variational Autoencoders for Text Modeling using Dilated Convolutions

Zichao Yang, Zhiting Hu, Ruslan Salakhutdinov, Taylor Berg-Kirkpatrick

Abstract: Recent work on generative text modeling has found that variational autoencoders (VAE) with LSTM decoders perform worse than simpler LSTM language models (Bowman et al., 2015). This negative result ...