Residual Tree Aggregation of Layers for Neural Machine Translation

TL;DR

This paper introduces RTAL, a residual tree aggregation method for Transformer models in neural machine translation, which fuses multi-layer information to improve translation quality.

Contribution

It proposes a novel residual tree aggregation approach that effectively combines information across layers in Transformer models for NMT.

Findings

RTAL outperforms baseline models on WMT14 English-German translation.

RTAL achieves significant improvements on WMT17 English-French translation.

The method effectively utilizes multi-layer information to enhance translation accuracy.

Abstract

Although attention-based Neural Machine Translation has achieved remarkable progress in recent layers, it still suffers from issue of making insufficient use of the output of each layer. In transformer, it only uses the top layer of encoder and decoder in the subsequent process, which makes it impossible to take advantage of the useful information in other layers. To address this issue, we propose a residual tree aggregation of layers for Transformer(RTAL), which helps to fuse information across layers. Specifically, we try to fuse the information across layers by constructing a post-order binary tree. In additional to the last node, we add the residual connection to the process of generating child nodes. Our model is based on the Neural Machine Translation model Transformer and we conduct our experiments on WMT14 English-to-German and WMT17 English-to-France translation tasks. Experimental results across language pairs show that the proposed approach outperforms the strong baseline model significantly