Dense Information Flow for Neural Machine Translation

NAACL 2018  ·  Yanyao Shen, Xu Tan, Di He, Tao Qin, Tie-Yan Liu ·

Recently, neural machine translation has achieved remarkable progress by introducing well-designed deep neural networks into its encoder-decoder framework. From the optimization perspective, residual connections are adopted to improve learning performance for both encoder and decoder in most of these deep architectures, and advanced attention connections are applied as well. Inspired by the success of the DenseNet model in computer vision problems, in this paper, we propose a densely connected NMT architecture (DenseNMT) that is able to train more efficiently for NMT. The proposed DenseNMT not only allows dense connection in creating new features for both encoder and decoder, but also uses the dense attention structure to improve attention quality. Our experiments on multiple datasets show that DenseNMT structure is more competitive and efficient.

PDF Abstract NAACL 2018 PDF NAACL 2018 Abstract

Datasets


Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Machine Translation WMT2014 English-German DenseNMT BLEU score 25.52 # 57
Hardware Burden None # 1
Operations per network pass None # 1

Methods