Shuhan Yuan


pdf bib
Robust Hate Speech Detection via Mitigating Spurious Correlations
Kshitiz Tiwari | Shuhan Yuan | Lu Zhang
Proceedings of the 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 12th International Joint Conference on Natural Language Processing (Volume 2: Short Papers)

We develop a novel robust hate speech detection model that can defend against both word- and character-level adversarial attacks. We identify the essential factor that vanilla detection models are vulnerable to adversarial attacks is the spurious correlation between certain target words in the text and the prediction label. To mitigate such spurious correlation, we describe the process of hate speech detection by a causal graph. Then, we employ the causal strength to quantify the spurious correlation and formulate a regularized entropy loss function. We show that our method generalizes the backdoor adjustment technique in causal inference. Finally, the empirical evaluation shows the efficacy of our method.