Log In Sign Up

Robust Unsupervised Neural Machine Translation with Adversarial Training

by   Haipeng Sun, et al.

Unsupervised neural machine translation (UNMT) has recently attracted great interest in the machine translation community, achieving only slightly worse results than supervised neural machine translation. However, in real-world scenarios, there usually exists minor noise in the input sentence and the neural translation system is sensitive to the small perturbations in the input, leading to poor performance. In this paper, we first define two types of noises and empirically show the effect of these noisy data on UNMT performance. Moreover, we propose adversarial training methods to improve the robustness of UNMT in the noisy scenario. To the best of our knowledge, this paper is the first work to explore the robustness of UNMT. Experimental results on several language pairs show that our proposed methods substantially outperform conventional UNMT systems in the noisy scenario.


page 1

page 2

page 3

page 4


Self-Training for Unsupervised Neural Machine Translation in Unbalanced Training Data Scenarios

Unsupervised neural machine translation (UNMT) that relies solely on mas...

On the Impact of Various Types of Noise on Neural Machine Translation

We examine how various types of noise in the parallel training data impa...

Learning to Discriminate Noises for Incorporating External Information in Neural Machine Translation

Previous studies show that incorporating external information could impr...

Neural Machine Translation with Noisy Lexical Constraints

Lexically constrained decoding for machine translation has shown to be b...

Robust Neural Machine Translation: Modeling Orthographic and Interpunctual Variation

Neural machine translation systems typically are trained on curated corp...

Word Shape Matters: Robust Machine Translation with Visual Embedding

Neural machine translation has achieved remarkable empirical performance...

Translation Between Waves, wave2wave

The understanding of sensor data has been greatly improved by advanced d...