The ability of zero-shot translation emerges when we train a multilingual
model with certain translation directions; the model can then directly
translate in unseen directions. Alternatively, zero-shot translation can be
accomplished by pivoting through a third language (e.g., English). In our work,
we observe that both direct and pivot translations are noisy and achieve less
satisfactory performance. We propose EBBS, an ensemble method with a novel
bi-level beam search algorithm, where each ensemble component explores its own
prediction step by step at the lower level but they are synchronized by a "soft
voting" mechanism at the upper level. Results on two popular multilingual
translation datasets show that EBBS consistently outperforms direct and pivot
translations as well as existing ensemble techniques. Further, we can distill
the ensemble's knowledge back to the multilingual model to improve inference
efficiency; profoundly, our EBBS-based distillation does not sacrifice, or even
improves, the translation quality.

我们通过一个新颖的双层束搜索算法，提出了 EBBS，一种集成方法，在下层每个集成组件逐步探索自己的预测，而在上层通过一种 “软投票” 机制进行同步，结果在两个流行的多语言翻译数据集上显示，EBBS 始终优于直接和转换翻译以及现有的 ensemble 技术，此外，我们可以将 ensemble 的知识返还到多语言模型，提高推断效率，深入研究后发现，基于 EBBS 的蒸馏能在不牺牲甚至提高翻译质量的情况下实现。