Counterfactual-Enhanced Information Bottleneck for Aspect-Based Sentiment Analysis

Authors

  • Mingshan Chang Shenzhen Key Laboratory for High Performance Data Mining, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences University of Chinese Academy of Sciences
  • Min Yang Shenzhen Key Laboratory for High Performance Data Mining, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences
  • Qingshan Jiang Shenzhen Key Laboratory for High Performance Data Mining, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences
  • Ruifeng Xu Harbin Institute of Technology (Shenzhen)

DOI:

https://doi.org/10.1609/aaai.v38i16.29726

Keywords:

NLP: Text Classification, NLP: Sentiment Analysis, Stylistic Analysis, and Argument Mining

Abstract

Despite having achieved notable success for aspect-based sentiment analysis (ABSA), deep neural networks are susceptible to spurious correlations between input features and output labels, leading to poor robustness. In this paper, we propose a novel Counterfactual-Enhanced Information Bottleneck framework (called CEIB) to reduce spurious correlations for ABSA. CEIB extends the information bottleneck (IB) principle to a factual-counterfactual balancing setting by integrating augmented counterfactual data, with the goal of learning a robust ABSA model. Concretely, we first devise a multi-pattern prompting method, which utilizes the large language model (LLM) to generate high-quality counterfactual samples from the original samples. Then, we employ the information bottleneck principle and separate the mutual information into factual and counterfactual parts. In this way, we can learn effective and robust representations for the ABSA task by balancing the predictive information of these two parts. Extensive experiments on five benchmark ABSA datasets show that our CEIB approach achieves superior prediction performance and robustness over the state-of-the-art baselines. Code and data to reproduce the results in this paper is available at: https://github.com/shesshan/CEIB.

Published

2024-03-24

How to Cite

Chang, M., Yang, M., Jiang, Q., & Xu, R. (2024). Counterfactual-Enhanced Information Bottleneck for Aspect-Based Sentiment Analysis. Proceedings of the AAAI Conference on Artificial Intelligence, 38(16), 17736-17744. https://doi.org/10.1609/aaai.v38i16.29726

Issue

Section

AAAI Technical Track on Natural Language Processing I