3 accepted papers
Despite of the superb performance on a wide range of tasks, pre-trained language models (e.g., BERT) have been proved vulnerable to adversarial texts. In this paper, we present RoChBERT, a framework to build more Robust BERT-based models by utilizing a more comprehensive adversarial graph to fuse Ch…
Adversarial texts help explore vulnerabilities in language models, improve model robustness, and explain their working mechanisms. However, existing word-level attack methods trap in a one-to-one attack pattern, i.e., only a single word can be modified in one transformation round, and they ignore th…
Natural language processing (NLP) models are known vulnerable to adversarial examples, similar to image processing models. Studying adversarial texts is an essential step to improve the robustness of NLP models. However, existing studies mainly focus on analyzing English texts and generating adversa…