CLLGNov 2, 2020

Improving Variational Autoencoder for Text Modelling with Timestep-Wise Regularisation

arXiv:2011.01136v2992 citations
AI Analysis

This addresses a critical bottleneck in text generation for researchers and practitioners using RNN-based VAEs, though it is incremental as it builds on existing VAE frameworks.

The paper tackles the posterior collapse problem in Variational Autoencoders (VAEs) for text modelling, where latent variables are ignored, by proposing a Timestep-Wise Regularisation VAE (TWR-VAE) that effectively avoids this issue and demonstrates effectiveness in tasks like language modelling and dialogue response generation.

The Variational Autoencoder (VAE) is a popular and powerful model applied to text modelling to generate diverse sentences. However, an issue known as posterior collapse (or KL loss vanishing) happens when the VAE is used in text modelling, where the approximate posterior collapses to the prior, and the model will totally ignore the latent variables and be degraded to a plain language model during text generation. Such an issue is particularly prevalent when RNN-based VAE models are employed for text modelling. In this paper, we propose a simple, generic architecture called Timestep-Wise Regularisation VAE (TWR-VAE), which can effectively avoid posterior collapse and can be applied to any RNN-based VAE models. The effectiveness and versatility of our model are demonstrated in different tasks, including language modelling and dialogue response generation.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes