Understanding Back-Translation at Scale

EMNLP 2018 Sergey EdunovMyle OttMichael AuliDavid Grangier

An effective method to improve neural machine translation with monolingual data is to augment the parallel training corpus with back-translations of target language sentences. This work broadens the understanding of back-translation and investigates a number of methods to generate synthetic source sentences... (read more)

PDF Abstract

Evaluation results from the paper


Task Dataset Model Metric name Metric value Global rank Compare
Machine Translation WMT2014 English-French Transformer Big + BT BLEU score 45.6 # 1
Machine Translation WMT2014 English-French Transformer Big + BT SacreBLEU 43.8 # 1
Machine Translation WMT2014 English-German Transformer Big + BT BLEU score 35.0 # 1
Machine Translation WMT2014 English-German Transformer Big + BT SacreBLEU 33.8 # 1