Zero-Shot Translation using Diffusion Models

Autor:	Nachmani, Eliya, Dovrat, Shaked
Rok vydání:	2021
Předmět:	Computer Science - Computation and Language Computer Science - Machine Learning
Druh dokumentu:	Working Paper
Popis:	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). Comment: preprint
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2111.01471 Zobrazit plný text záznamu View this record from Arxiv