Multi-layer Representation Fusion for Neural Machine Translation

TL;DR

This paper introduces a multi-layer representation fusion method for neural machine translation, improving the use of stacked layer information and achieving state-of-the-art results in German-English translation.

Contribution

It proposes a novel multi-layer fusion approach with three fusion functions to enhance sentence representations in NMT models.

Findings

Achieved 0.92 BLEU improvement on IWSLT German-English

Achieved 0.56 BLEU improvement on NIST Chinese-English

Set new state-of-the-art in German-English translation

Abstract

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.