Non-Autoregressive Neural Machine Translation

ICLR 2018 Jiatao GuJames BradburyCaiming XiongVictor O. K. LiRichard Socher

Existing approaches to neural machine translation condition each output word on previously generated outputs. We introduce a model that avoids this autoregressive property and produces its outputs in parallel, allowing an order of magnitude lower latency during inference... (read more)

PDF Abstract

Evaluation Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK COMPARE
Machine Translation IWSLT2015 English-German NAT +FT + NPD BLEU score 28.16 # 2
Machine Translation WMT2014 English-German NAT +FT + NPD BLEU score 19.17 # 33
Machine Translation WMT2014 German-English NAT +FT + NPD BLEU score 23.20 # 7
Machine Translation WMT2016 English-Romanian NAT +FT + NPD BLEU score 29.79 # 7
Machine Translation WMT2016 Romanian-English NAT +FT + NPD BLEU score 31.44 # 7