Preventing Posterior Collapse in Sequence VAEs with Pooling

Variational Autoencoders (VAEs) hold great potential for modelling text, as they could in theory separate high-level semantic and syntactic properties from local regularities of natural language. Practically, however, VAEs with autoregressive decoders often suffer from posterior collapse, a phenomenon where the model learns to ignore the latent variables, causing the sequence VAE to degenerate into a language model. Previous works attempt to solve this problem with complex architectural changes or costly optimization schemes. In this paper, we argue that posterior collapse is caused in part by the encoder network failing to capture the input variabilities. We verify this hypothesis empirically and propose a straightforward fix using pooling. This simple technique effectively prevents posterior collapse, allowing the model to achieve significantly better data log-likelihood than standard sequence VAEs. Compared to the previous SOTA on preventing posterior collapse, we are able to achieve comparable performances while being significantly faster.