Zero-shot translation, translating between language pairs on which a Neural
Machine Translation (NMT) system has never been trained, is an emergent
property when training the system in multilingual settings. However, naive
training for zero-shot NMT easily fails, and is sensitive to hyper-parameter
setting. The performance typically lags far behind the more conventional
pivot-based approach which translates twice using a third language as a pivot.
In this work, we address the degeneracy problem due to capturing spurious
correlations by quantitatively analyzing the mutual information between
language IDs of the source and decoded sentences. Inspired by this analysis, we
propose to use two simple but effective approaches: (1) decoder pre-training;
(2) back-translation. These methods show significant improvement (4~22 BLEU
points) over the vanilla zero-shot translation on three challenging
multilingual datasets, and achieve similar or better results than the
pivot-based approach.

本研究提出了两种简单但有效的方法，解决零样本神经机器翻译的退化问题，即解决了源语言和解码语言之间的虚假相关性问题。实验结果表明，在三个具有挑战性的多语言数据集上，在零样本翻译上取得了显著的提高，并且在某些情况下可以实现优于传统基于 pivot 翻译的效果。