Topic-aware Causal Intervention for Counterfactual Detection
This work addresses counterfactual detection for NLP applications, offering improvements over incremental methods by resolving bias and enhancing robustness.
The paper tackled the problem of counterfactual detection in NLP, where existing models rely on clue phrases and suffer from performance drops without them, by integrating a neural topic model and causal intervention to capture global semantics and balance class effects, resulting in outperforming previous state-of-the-art methods in CFD and bias-sensitive tasks.
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 tend to predict non-counterfactuals over counterfactuals. 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.