Phrase-level Adversarial Example Generation for Neural Machine Translation

01/06/2022
by   Juncheng Wan, et al.
0

While end-to-end neural machine translation (NMT) has achieved impressive progress, noisy input usually leads models to become fragile and unstable. Generating adversarial examples as the augmented data is proved to be useful to alleviate this problem. Existing methods for adversarial example generation (AEG) are word-level or character-level. In this paper, we propose a phrase-level adversarial example generation (PAEG) method to enhance the robustness of the model. Our method leverages a gradient-based strategy to substitute phrases of vulnerable positions in the source input. We verify our method on three benchmarks, including LDC Chinese-English, IWSLT14 German-English, and WMT14 English-German tasks. Experimental results demonstrate that our approach significantly improves performance compared to previous methods.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
06/06/2019

Robust Neural Machine Translation with Doubly Adversarial Inputs

Neural machine translation (NMT) often suffers from the vulnerability to...
research
06/17/2017

Towards Neural Phrase-based Machine Translation

In this paper, we present Neural Phrase-based Machine Translation (NPMT)...
research
11/08/2019

Domain Robustness in Neural Machine Translation

Translating text that diverges from the training domain is a key challen...
research
06/29/2018

Neural Machine Translation with Key-Value Memory-Augmented Attention

Although attention-based Neural Machine Translation (NMT) has achieved r...
research
11/27/2017

Modeling Past and Future for Neural Machine Translation

Existing neural machine translation systems do not explicitly model what...
research
06/10/2021

Progressive Multi-Granularity Training for Non-Autoregressive Translation

Non-autoregressive translation (NAT) significantly accelerates the infer...
research
06/15/2016

Agreement-based Learning of Parallel Lexicons and Phrases from Non-Parallel Corpora

We introduce an agreement-based approach to learning parallel lexicons a...

Please sign up or login with your details

Forgot password? Click here to reset