Year: 2021
Type: preprint
Abstract: 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).
Source: arXiv (Cornell University)
Authors: Nachmani, Eliya, Dovrat, Shaked
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W3208972171