We present a probabilistic framework for multilingual neural machine
translation that encompasses supervised and unsupervised setups, focusing on
unsupervised translation. In addition to studying the vanilla case where there
is only monolingual data available, we propose a novel setup where one language
in the (source, target) pair is not associated with any parallel data, but
there may exist auxiliary parallel data that contains the other. This auxiliary
data can naturally be utilized in our probabilistic framework via a novel
cross-translation loss term. Empirically, we show that our approach results in
higher BLEU scores over state-of-the-art unsupervised models on the WMT'14
English-French, WMT'16 English-German, and WMT'16 English-Romanian datasets in
most directions. In particular, we obtain a +1.65 BLEU advantage over the
best-performing unsupervised model in the Romanian-English direction.

提出了一个概率框架，用于多语言神经机器翻译，特别针对无监督翻译。通过使用一个新型的跨语言翻译损失项，自然地利用其他包含辅助平行数据的语言作为源或目标语之一。实验证明，在大多数方向上，我们的方法导致在 WMT'14 英语 - 法语、WMT'16 英语 - 德语和 WMT'16 英语 - 罗马尼亚语数据集上，BLEU 得分比最先进的无监督模型高，并且在罗马尼亚语 - 英语方向上，我们获得了比最佳无监督模型高 1.65 的 BLEU 优势。