Non-autoregressive approaches aim to improve the inference speed of
translation models by only requiring a single forward pass to generate the
output sequence instead of iteratively producing each predicted token.
Consequently, their translation quality still tends to be inferior to their
autoregressive counterparts due to several issues involving output token
interdependence. In this work, we take a step back and revisit several
techniques that have been proposed for improving non-autoregressive translation
models and compare their combined translation quality and speed implications
under third-party testing environments. We provide novel insights for
establishing strong baselines using length prediction or CTC-based architecture
variants and contribute standardized BLEU, chrF++, and TER scores using
sacreBLEU on four translation tasks, which crucially have been missing as
inconsistencies in the use of tokenized BLEU lead to deviations of up to 1.7
BLEU points. Our open-sourced code is integrated into fairseq for
reproducibility.

本文旨在改进非自回归方法在机器翻译方面的表现，探讨了多种技术提升其翻译质量和效率，并将其在四个翻译任务上进行了评估，考虑到 tokenized BLEU 的使用不一致，我们贡献了标准化的 BLEU、chrF++ 及 TER 得分，并将代码开源集成于 fairseq 中以便重现研究结果。