Multilingual machine translation, which translates multiple languages with a
single model, has attracted much attention due to its efficiency of offline
training and online serving. However, traditional multilingual translation
usually yields inferior accuracy compared with the counterpart using individual
models for each language pair, due to language diversity and model capacity
limitations. In this paper, we propose a distillation-based approach to boost
the accuracy of multilingual machine translation. Specifically, individual
models are first trained and regarded as teachers, and then the multilingual
model is trained to fit the training data and match the outputs of individual
models simultaneously through knowledge distillation. Experiments on IWSLT, WMT
and Ted talk translation datasets demonstrate the effectiveness of our method.
Particularly, we show that one model is enough to handle multiple languages (up
to 44 languages in our experiment), with comparable or even better accuracy
than individual models.

本文提出一种基于蒸馏的方法来提高多语言机器翻译的准确性，并在数据集上进行了实验，结果表明该方法可以通过训练单独的模型（即老师）来训练多语言模型，这使得一个模型即可具备处理多达 44 种不同语言的能力（且其准确性与单独模型相当甚至更优）。