Nothing Special   »   [go: up one dir, main page]

CAT-Gen: Improving Robustness in NLP Models via Controlled Adversarial Text Generation

Tianlu Wang, Xuezhi Wang, Yao Qin, Ben Packer, Kang Li, Jilin Chen, Alex Beutel, Ed Chi


Abstract
NLP models are shown to suffer from robustness issues, i.e., a model’s prediction can be easily changed under small perturbations to the input. In this work, we present a Controlled Adversarial Text Generation (CAT-Gen) model that, given an input text, generates adversarial texts through controllable attributes that are known to be invariant to task labels. For example, in order to attack a model for sentiment classification over product reviews, we can use the product categories as the controllable attribute which would not change the sentiment of the reviews. Experiments on real-world NLP datasets demonstrate that our method can generate more diverse and fluent adversarial texts, compared to many existing adversarial text generation approaches. We further use our generated adversarial examples to improve models through adversarial training, and we demonstrate that our generated attacks are more robust against model re-training and different model architectures.
Anthology ID:
2020.emnlp-main.417
Volume:
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)
Month:
November
Year:
2020
Address:
Online
Editors:
Bonnie Webber, Trevor Cohn, Yulan He, Yang Liu
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
5141–5146
Language:
URL:
https://aclanthology.org/2020.emnlp-main.417
DOI:
10.18653/v1/2020.emnlp-main.417
Bibkey:
Cite (ACL):
Tianlu Wang, Xuezhi Wang, Yao Qin, Ben Packer, Kang Li, Jilin Chen, Alex Beutel, and Ed Chi. 2020. CAT-Gen: Improving Robustness in NLP Models via Controlled Adversarial Text Generation. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 5141–5146, Online. Association for Computational Linguistics.
Cite (Informal):
CAT-Gen: Improving Robustness in NLP Models via Controlled Adversarial Text Generation (Wang et al., EMNLP 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.emnlp-main.417.pdf
Video:
 https://slideslive.com/38939090