Existing approaches to neural machine translation condition each output word
on previously generated outputs. We introduce a model that avoids this
autoregressive property and produces its outputs in parallel, allowing an order
of magnitude lower latency during inference. Through knowledge distillation,
the use of input token fertilities as a latent variable, and policy gradient
fine-tuning, we achieve this at a cost of as little as 2.0 BLEU points relative
to the autoregressive Transformer network used as a teacher. We demonstrate
substantial cumulative improvements associated with each of the three aspects
of our training strategy, and validate our approach on IWSLT 2016
English-German and two WMT language pairs. By sampling fertilities in parallel
at inference time, our non-autoregressive model achieves near-state-of-the-art
performance of 29.8 BLEU on WMT 2016 English-Romanian.

本文提出一种新的神经机器翻译模型，通过避免自回归的特性，以并行方式生成输出，进而做到了比先前方法更低的延迟时间。通过知识蒸馏，潜在变量，以及多样本策略梯度微调等技术手段，几乎没有损失性能，达到了先进的翻译效果。