papers AI Learner
The Github is limit! Click to go to the new site.

Multilingual Neural Machine Translation with Knowledge Distillation

2019-02-27
Xu Tan, Yi Ren, Di He, Tao Qin, Zhou Zhao, Tieyan Liu

Abstract

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.

Abstract (translated by Google)
URL

http://arxiv.org/abs/1902.10461

PDF

http://arxiv.org/pdf/1902.10461


Similar Posts

Comments