Topic-aware Causal Intervention for Counterfactual Detection

TL;DR

This paper introduces a topic-aware causal intervention approach to improve counterfactual detection in NLP, addressing the reliance on clue phrases and class imbalance issues in previous models.

Contribution

It integrates neural topic modeling with causal intervention techniques to enhance counterfactual detection accuracy and robustness against bias.

Findings

Outperforms previous state-of-the-art CFD models

Effective in bias-sensitive NLP tasks

Improves detection when clue phrases are absent

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 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.