128 citations · 186 across the 5 of their papers we have counts for
4 papers · 1 filter
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…
Revisiting Self-Training for Neural Sequence Generation
Junxian He, Jiatao Gu, Jiajun Shen +1
Self-training is one of the earliest and simplest semi-supervised methods. The key idea is to augment the original labeled dataset with unlabeled data paired with the model's predi…
Lagging Inference Networks and Posterior Collapse in Variational Autoencoders
Junxian He, Daniel Spokoyny, Graham Neubig +1
The variational autoencoder (VAE) is a popular combination of deep latent variable model and accompanying variational learning technique. By using a neural inference network to app…
Efficient Correlated Topic Modeling with Topic Embedding
Junxian He, Zhiting Hu, Taylor Berg-Kirkpatrick +2
Correlated topic modeling has been limited to small model and problem sizes due to their high computational cost and poor scaling. In this paper, we propose a new model which learn…