Context-aware Adversarial Attack on Named Entity Recognition

Shuguang Chen, Leonardo Neves, Thamar Solorio


Abstract
In recent years, large pre-trained language models (PLMs) have achieved remarkable performance on many natural language processing benchmarks. Despite their success, prior studies have shown that PLMs are vulnerable to attacks from adversarial examples. In this work, we focus on the named entity recognition task and study context-aware adversarial attack methods to examine the model’s robustness. Specifically, we propose perturbing the most informative words for recognizing entities to create adversarial examples and investigate different candidate replacement methods to generate natural and plausible adversarial examples. Experiments and analyses show that our methods are more effective in deceiving the model into making wrong predictions than strong baselines.
Anthology ID:
2024.wnut-1.2
Volume:
Proceedings of the Ninth Workshop on Noisy and User-generated Text (W-NUT 2024)
Month:
March
Year:
2024
Address:
San Ġiljan, Malta
Editors:
Rob van der Goot, JinYeong Bak, Max Müller-Eberstein, Wei Xu, Alan Ritter, Tim Baldwin
Venues:
WNUT | WS
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
11–16
Language:
URL:
https://aclanthology.org/2024.wnut-1.2
DOI:
Bibkey:
Cite (ACL):
Shuguang Chen, Leonardo Neves, and Thamar Solorio. 2024. Context-aware Adversarial Attack on Named Entity Recognition. In Proceedings of the Ninth Workshop on Noisy and User-generated Text (W-NUT 2024), pages 11–16, San Ġiljan, Malta. Association for Computational Linguistics.
Cite (Informal):
Context-aware Adversarial Attack on Named Entity Recognition (Chen et al., WNUT-WS 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.wnut-1.2.pdf