Step-unrolled Denoising Autoencoders for Text Generation

Nikolay Savinov · Junyoung Chung · Mikolaj Binkowski · Erich Elsen · Aaron v den

Keywords: [ generative models ] [ text generation ]

[ Abstract ]
[ Visit Poster at Spot G1 in Virtual World ] [ OpenReview
Wed 27 Apr 10:30 a.m. PDT — 12:30 p.m. PDT


In this paper we propose a new generative model of text, Step-unrolled Denoising Autoencoder (SUNDAE), that does not rely on autoregressive models. Similarly to denoising diffusion techniques, SUNDAE is repeatedly applied on a sequence of tokens, starting from random inputs and improving them each time until convergence. We present a simple new improvement operator that converges in fewer iterations than diffusion methods, while qualitatively producing better samples on natural language datasets. SUNDAE achieves state-of-the-art results (among non-autoregressive methods) on the WMT'14 English-to-German translation task and good qualitative results on unconditional language modeling on the Colossal Cleaned Common Crawl dataset and a dataset of Python code from GitHub. The non-autoregressive nature of SUNDAE opens up possibilities beyond left-to-right prompted generation, by filling in arbitrary blank patterns in a template.

Chat is not available.