Dense Information Flow for Neural Machine Translation

NAACL 2018 Yanyao ShenXu TanDi HeTao QinTie-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... (read more)

PDF Abstract

Evaluation Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK COMPARE
Machine Translation WMT2014 English-German DenseNMT BLEU score 25.52 # 23