This paper presents two strong methods, CTC and Imputer, for
non-autoregressive machine translation that model latent alignments with
dynamic programming. We revisit CTC for machine translation and demonstrate
that a simple CTC model can achieve state-of-the-art for single-step
non-autoregressive machine translation, contrary to what prior work indicates.
In addition, we adapt the Imputer model for non-autoregressive machine
translation and demonstrate that Imputer with just 4 generation steps can match
the performance of an autoregressive Transformer baseline. Our latent alignment
models are simpler than many existing non-autoregressive translation baselines;
for example, we do not require target length prediction or re-scoring with an
autoregressive model. On the competitive WMT'14 En$\rightarrow$De task, our CTC
model achieves 25.7 BLEU with a single generation step, while Imputer achieves
27.5 BLEU with 2 generation steps, and 28.0 BLEU with 4 generation steps. This
compares favourably to the autoregressive Transformer baseline at 27.8 BLEU.

本文提出了两种强有力的方法，CTC 和 Imputer，用于非自回归机器翻译，模拟了动态规划中的潜在对齐。我们重新审视了 CTC 和 Imputer 模型，并证明了一个简单的 CTC 模型可以实现单步非自回归机器翻译的最新成果，与之前的工作相反。另外，我们还将 Imputer 模型适应于非自回归机器翻译，并证明只需 4 个生成步骤，Imputer 即可匹配自回归 Transformer 基准的性能。