DeepAI AI Chat
Log In Sign Up

Robust Neural Machine Translation with Doubly Adversarial Inputs

by   Yong Cheng, et al.

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 improve its robustness against the adversarial source inputs.For 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 exhibiting higher robustness on noisy data.


page 1

page 2

page 3

page 4


Towards Robust Neural Machine Translation

Small perturbations in the input can severely distort intermediate repre...

Phrase-level Adversarial Example Generation for Neural Machine Translation

While end-to-end neural machine translation (NMT) has achieved impressiv...

Doubly-Trained Adversarial Data Augmentation for Neural Machine Translation

Neural Machine Translation (NMT) models are known to suffer from noisy i...

Generating Authentic Adversarial Examples beyond Meaning-preserving with Doubly Round-trip Translation

Generating adversarial examples for Neural Machine Translation (NMT) wit...

Robust Neural Machine Translation: Modeling Orthographic and Interpunctual Variation

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

Addressing the Vulnerability of NMT in Input Perturbations

Neural Machine Translation (NMT) has achieved significant breakthrough i...

Can NMT Understand Me? Towards Perturbation-based Evaluation of NMT Models for Code Generation

Neural Machine Translation (NMT) has reached a level of maturity to be r...