20 citations · 20 across the 1 of their papers we have counts for
2 papers
cs.LG2019
A Surprisingly Effective Fix for Deep Latent Variable Modeling of Text
Bohan Li, Junxian He, Graham Neubig +2
When trained effectively, the Variational Autoencoder (VAE) is both a powerful language model and an effective representation learning framework. In practice, however, VAEs are tra…
cs.CL2019★ 20 cited
An Adversarial Approach to High-Quality, Sentiment-Controlled Neural Dialogue Generation
Xiang Kong, Bohan Li, Graham Neubig +2
In this work, we propose a method for neural dialogue response generation that allows not only generating semantically reasonable responses according to the dialogue history, but a…