This paper describes Facebook AI's submission to the WAT 2019 Myanmar-English
translation task. Our baseline systems are BPE-based transformer models. We
explore methods to leverage monolingual data to improve generalization,
including self-training, back-translation and their combination. We further
improve results by using noisy channel re-ranking and ensembling. We
demonstrate that these techniques can significantly improve not only a system
trained with additional monolingual data, but even the baseline system trained
exclusively on the provided small parallel dataset. Our system ranks first in
both directions according to human evaluation and BLEU, with a gain of over 8
BLEU points above the second best system.

本文描述了 Facebook AI 在 WAT 2019 缅甸语 - 英语翻译任务中的提交。我们运用基于 BPE 的 transformer 模型，探索了利用单语数据提高泛化能力的方法，包括自训练、回译和它们的组合。我们进一步通过使用噪声通道重排和集成来提高结果。我们证明了这些技术不仅可以显著提高使用额外单语数据训练的系统，而且还可以提高仅使用提供的小型平行数据集训练的基线系统。我们的系统在人类评估和 BLEU 方面均排名第一，在第二名系统上取得了超过 8 BLEU 分的优势。