Zero-Shot Translation using Diffusion Models

11/02/2021

∙

by   Eliya Nachmani, et al.

∙

0

∙

share

In this work, we show a novel method for neural machine translation (NMT), using a denoising diffusion probabilistic model (DDPM), adjusted for textual data, following recent advances in the field. We show that it's possible to translate sentences non-autoregressively using a diffusion model conditioned on the source sentence. We also show that our model is able to translate between pairs of languages unseen during training (zero-shot learning).