TASK	DATASET	MODEL	METRIC NAME	METRIC VALUE	GLOBAL RANK
Machine Translation	WMT2014 English-German	DenseNMT	BLEU score	25.52	# 68
Machine Translation	WMT2014 English-German	DenseNMT	Hardware Burden	None	# 1
Machine Translation	WMT2014 English-German	DenseNMT	Operations per network pass	None	# 1

Badge	Markdown
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/dense-information-flow-for-neural-machine/machine-translation-on-wmt2014-english-german)](https://paperswithcode.com/sota/machine-translation-on-wmt2014-english-german?p=dense-information-flow-for-neural-machine)`

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.