Synchronous Bidirectional Neural Machine Translation

TACL 2019 Long ZhouJiajun ZhangChengqing Zong

Existing approaches to neural machine translation (NMT) generate the target language sequence token by token from left to right. However, this kind of unidirectional decoding framework cannot make full use of the target-side future contexts which can be produced in a right-to-left decoding direction, and thus suffers from the issue of unbalanced outputs... (read more)

PDF Abstract

Evaluation Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK COMPARE
Machine Translation WMT2014 English-German SB-NMT BLEU score 29.21 # 10