Step-unrolled Denoising Autoencoders for Text GenerationDownload PDF

Published: 28 Jan 2022, Last Modified: 22 Oct 2023ICLR 2022 PosterReaders: Everyone
Keywords: generative models, text generation, denoising autoencoders
Abstract: 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.
One-sentence Summary: We propose a new generative model of text that unrolls the denoising process during training.
Community Implementations: [![CatalyzeX](/images/catalyzex_icon.svg) 2 code implementations](https://www.catalyzex.com/paper/arxiv:2112.06749/code)
13 Replies

Loading