In this paper, we propose a new adversarial augmentation method for Neural Machine Translation (NMT). The main idea is to minimize the vicinal risk over virtual sentences sampled from two vicinity distributions, of which the crucial one is a novel vicinity distribution for adversarial sentences that describes a smooth interpolated embedding space centered around observed training sentence pairs. We then discuss our approach, AdvAug, to train NMT models using the embeddings of virtual sentences in sequence-to-sequence learning. Experiments on Chinese-English, English-French, and English-German translation benchmarks show that AdvAug achieves significant improvements over the Transformer (up to 4.9 BLEU points), and substantially outperforms other data augmentation techniques (e.g. back-translation) without using extra corpora.
@article{arxiv.2006.11834,
title = {AdvAug: Robust Adversarial Augmentation for Neural Machine Translation},
author = {Yong Cheng and Lu Jiang and Wolfgang Macherey and Jacob Eisenstein},
journal= {arXiv preprint arXiv:2006.11834},
year = {2020}
}