Counterfactual Augmented Causal Reasoning for Aspect-Based Sentiment Analysis

摘要

Aspect-based sentiment analysis (ABSA) aims to identify the sentiment polarity of the specified aspect in a sentence. Despite achieving the remarkable success, deep models are susceptible to capturing spurious correlations between surface patterns and predicted labels instead of capturing aspect-related causal features, leading to poor robustness. To this end, we propose a new counterfactual-enhanced causal reasoning (CECR) framework to reduce spurious correlations. Specifically, at the data level, the counterfactual data augmentation (CDA) module is exploited to employ a three-stage reasoning paradigm guided by cognitive chain-of-thought (COT) principles to generate high-quality counterfactual data from the training data. At the model level, the multi-level causal attention (MCA) is designed to iteratively extract causal features and remove confounding features. Experimental results on the utilized datasets demonstrate that the CECR achieves outstanding performance on state-of-the-art baselines.