A Surprisingly Effective Fix for Deep Latent Variable Modeling of Text
EMNLP/IJCNLP (1), pp. 3601-3612, 2019.
When trained effectively, the Variational Autoencoder (VAE) is both a powerful language model and an effective representation learning framework. In practice, however, VAEs are trained with the evidence lower bound (ELBO) as a surrogate objective to the intractable marginal data likelihood. This approach to training yields unstable resu...More
PPT (Upload PPT)