Jiahao Zhao


2023

pdf bib
Generative Adversarial Training with Perturbed Token Detection for Model Robustness
Jiahao Zhao | Wenji Mao
Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing

Adversarial training is the dominant strategy towards model robustness. Current adversarial training methods typically apply perturbations to embedding representations, whereas actual text-based attacks introduce perturbations as discrete tokens. Thus there exists a gap between the continuous embedding representations and discrete text tokens that hampers the effectiveness of adversarial training. Moreover, the continuous representations of perturbations cannot be further utilized, resulting in the suboptimal performance. To bridge this gap for adversarial robustness, in this paper, we devise a novel generative adversarial training framework that integrates gradient-based learning, adversarial example generation and perturbed token detection. Our proposed framework consists of generative adversarial attack and adversarial training process. Specifically, in generative adversarial attack, the embeddings are shared between the classifier and the generative model, which enables the generative model to leverage the gradients from the classifier for generating perturbed tokens. Then, adversarial training process combines adversarial regularization with perturbed token detection to provide token-level supervision and improve the efficiency of sample utilization. Extensive experiments on five datasets from the AdvGLUE benchmark demonstrate that our framework significantly enhances the model robustness, surpassing the state-of-the-art results of ChatGPT by 10% in average accuracy.

2020

pdf bib
Effective Inter-Clause Modeling for End-to-End Emotion-Cause Pair Extraction
Penghui Wei | Jiahao Zhao | Wenji Mao
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics

Emotion-cause pair extraction aims to extract all emotion clauses coupled with their cause clauses from a given document. Previous work employs two-step approaches, in which the first step extracts emotion clauses and cause clauses separately, and the second step trains a classifier to filter out negative pairs. However, such pipeline-style system for emotion-cause pair extraction is suboptimal because it suffers from error propagation and the two steps may not adapt to each other well. In this paper, we tackle emotion-cause pair extraction from a ranking perspective, i.e., ranking clause pair candidates in a document, and propose a one-step neural approach which emphasizes inter-clause modeling to perform end-to-end extraction. It models the interrelations between the clauses in a document to learn clause representations with graph attention, and enhances clause pair representations with kernel-based relative position embedding for effective ranking. Experimental results show that our approach significantly outperforms the current two-step systems, especially in the condition of extracting multiple pairs in one document.