Neural machine translation systems require a number of stacked layers for deep models. But the prediction depends on the sentence representation of the top-most layer with no access to low-level representations. This makes it more difficult to train the model and poses a risk of information loss to prediction. In this paper, we propose a multi-layer representation fusion (MLRF) approach to fusing stacked layers. In particular, we design three fusion functions to learn a better representation from the stack. Experimental results show that our approach yields improvements of 0.92 and 0.56 BLEU points over the strong Transformer baseline on IWSLT German-English and NIST Chinese-English MT tasks respectively. The result is new state-of-the-art in German-English translation.
@article{arxiv.2002.06714,
title = {Multi-layer Representation Fusion for Neural Machine Translation},
author = {Qiang Wang and Fuxue Li and Tong Xiao and Yanyang Li and Yinqiao Li and Jingbo Zhu},
journal= {arXiv preprint arXiv:2002.06714},
year = {2020}
}