Understanding Back-Translation at Scale

EMNLP 2018  ·  Sergey Edunov, Myle Ott, Michael Auli, David 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... We find that in all but resource poor settings back-translations obtained via sampling or noised beam outputs are most effective. Our analysis shows that sampling or noisy synthetic data gives a much stronger training signal than data generated by beam or greedy search. We also compare how synthetic data compares to genuine bitext and study various domain effects. Finally, we scale to hundreds of millions of monolingual sentences and achieve a new state of the art of 35 BLEU on the WMT'14 English-German test set. read more

PDF Abstract EMNLP 2018 PDF EMNLP 2018 Abstract

Datasets


Results from the Paper


Ranked #2 on Machine Translation on WMT2014 English-German (using extra training data)

     Get a GitHub badge
Task Dataset Model Metric Name Metric Value Global Rank Uses Extra
Training Data
Result Benchmark
Machine Translation WMT2014 English-French Noisy back-translation BLEU score 45.6 # 2
SacreBLEU 43.8 # 2
Machine Translation WMT2014 English-German Noisy back-translation BLEU score 35.0 # 2
SacreBLEU 33.8 # 1

Methods


No methods listed for this paper. Add relevant methods here