Massively multilingual models for neural machine translation (NMT) are theoretically attractive, but often underperform bilingual models and deliver poor zero-shot translations. In this paper, we explore ways to improve them. We argue that multilingual NMT requires stronger modeling capacity to support language pairs with varying typological characteristics, and overcome this bottleneck via language-specific components and deepening NMT architectures. We identify the off-target translation issue (i.e. translating into a wrong target language) as the major source of the inferior zero-shot performance, and propose random online backtranslation to enforce the translation of unseen training language pairs. Experiments on OPUS-100 (a novel multilingual dataset with 100 languages) show that our approach substantially narrows the performance gap with bilingual models in both one-to-many and many-to-many settings, and improves zero-shot performance by ~10 BLEU, approaching conventional pivot-based methods.

本文探讨了如何改善大规模多语言神经机器翻译模型的性能，并提出了加强模型能力、引入语言特定组件和加深神经机器翻译结构以支持具有不同类型学特征的语言对，同时通过随机在线回译来解决离线训练中未出现的语言对翻译问题。实验结果表明，本方法在一对多和多对多设置中缩小了双语模型的性能差距，并将零-shot表现提高约10 BLEU，接近传统的基于中间语言的方法。

改进大规模多语言神经机器翻译和零样例翻译