Recent work on non-autoregressive neural machine translation (NAT) aims at improving the efficiency by parallel decoding without sacrificing the quality. However, existing NAT methods are either inferior to Transformer or require multiple decoding passes, leading to reduced speedup. We propose the Glancing Language Model (GLM), a method to learn word interdependency for single-pass parallel generation models. With GLM, we develop Glancing Transformer (GLAT) for machine translation. With only single-pass parallel decoding, GLAT is able to generate high-quality translation with 8-15 times speedup. Experiments on multiple WMT language directions show that GLAT outperforms all previous single pass non-autoregressive methods, and is nearly comparable to Transformer, reducing the gap to 0.25-0.9 BLEU points.
@article{arxiv.2008.07905,
title = {Glancing Transformer for Non-Autoregressive Neural Machine Translation},
author = {Lihua Qian and Hao Zhou and Yu Bao and Mingxuan Wang and Lin Qiu and Weinan Zhang and Yong Yu and Lei Li},
journal= {arXiv preprint arXiv:2008.07905},
year = {2021}
}