Generalization and reliability of multilingual translation often highly depend on the amount of available parallel data for each language pair of interest. In this paper, we focus on zero-shot generalization---a challenging setup that tests models on translation directions they have not been optimized for at training time. To solve the problem, we (i) reformulate multilingual translation as probabilistic inference, (ii) define the notion of zero-shot consistency and show why standard training often results in models unsuitable for zero-shot tasks, and (iii) introduce a consistent agreement-based training method that encourages the model to produce equivalent translations of parallel sentences in auxiliary languages. We test our multilingual NMT models on multiple public zero-shot translation benchmarks (IWSLT17, UN corpus, Europarl) and show that agreement-based learning often results in 2-3 BLEU zero-shot improvement over strong baselines without any loss in performance on supervised translation directions.

通过将多语言翻译问题重新构造为概率推理，定义了零-shot一致性的概念；引入了一种基于一致性约束的训练方法，鼓励模型在辅助语言中生成等效的平行句子翻译，最终我们测试了多种公共的零-shot翻译基准数据集，并证明基于一致性约束训练的NMT模型通常会在无监督翻译任务上取得2-3 BLEU的提高，而在监督翻译任务上的性能不会降低。

零样本神经机器翻译中一致性的达成