• DOI:10.18653/v1/P19-1425
Corpus ID: 174802397

Robust Neural Machine Translation with Doubly Adversarial Inputs

@inproceedings{Cheng2019RobustNM,
  title={Robust Neural Machine Translation with Doubly Adversarial Inputs},
  author={Yong Cheng and Lu Jiang and Wolfgang Macherey},
  booktitle={ACL},
  year={2019}
}

Yong Cheng, Lu Jiang, Wolfgang Macherey

Published in ACL 2019

Computer Science

Neural machine translation (NMT) often suffers from the vulnerability to noisy perturbations in the input. [...] Key MethodFor the generation of adversarial inputs, we propose a gradient-based method to craft adversarial examples informed by the translation loss over the clean inputs.Experimental results on Chinese-English and English-German translation tasks demonstrate that our approach achieves significant improvements ($2.8$ and $1.6$ BLEU points) over Transformer on standard clean benchmarks as well as…Expand Abstract

View on ACL

arxiv.org

Save to Library

Create Alert

Cite

Launch Research Feed