Robust Neural Machine Translation with Doubly Adversarial Inputs

Yong Cheng
Yong Cheng
Wolfgang Macherey
Wolfgang Macherey

ACL (1), pp. 4324-4333, 2019.

Cited by: 25|Bibtex|Views41|DOI:https://doi.org/10.18653/v1/p19-1425
EI
Other Links: dblp.uni-trier.de|arxiv.org

Abstract:

Neural machine translation (NMT) often suffers from the vulnerability to noisy perturbations in the input. We propose an approach to improving the robustness of NMT models, which consists of two parts: (1) attack the translation model with adversarial source examples; (2) defend the translation model with adversarial target inputs to im...More

Code:

Data:

Full Text
Your rating :
0

 

Tags
Comments