loading page

Topic-Aware Causal Intervention for Counterfactual Detection
  • +2
  • Thong Nguyen ,
  • Xiaobao Wu ,
  • Cong-Duy Nguyen ,
  • See-Kiong Ng ,
  • Anh Tuan Luu
Thong Nguyen
National University of Singapore

Corresponding Author:[email protected]

Author Profile
Xiaobao Wu
Author Profile
Cong-Duy Nguyen
Author Profile
See-Kiong Ng
Author Profile
Anh Tuan Luu
Author Profile

Abstract

Counterfactual statements, which describe events that did not or cannot take place, are beneficial to numerous NLP applications. Hence, we consider the problem of counterfactual detection (CFD) and seek to enhance the CFD models. Previous models are reliant on clue phrases to predict counterfactuality, so they suffer from significant performance drop when clue phrase hints do not exist during testing. Moreover, these models’ prediction also biases towards non-counterfactual over the counterfactual class. To address these issues, we propose to integrate neural topic model into the CFD model to capture the global semantics of the input statement. We continue to causally intervene the hidden representations of the CFD model to balance the effect of the class labels. Extensive experiments show that our approach outperforms previous state-of-the-art CFD and bias-resolving methods in both the CFD and other bias-sensitive tasks.