Though notable progress has been made, neural-based aspect-based sentiment analysis (ABSA) models are prone to learn spurious correlations from annotation biases, resulting in poor robustness on adversarial data transformations. Among the debiasing solutions, causal inference-based methods have attracted much research attention, which can be mainly categorized into causal intervention methods and counterfactual reasoning methods. However, most of the present debiasing methods focus on single-variable causal inference, which is not suitable for ABSA with two input variables (the target aspect and the review). In this paper, we propose a novel framework based on multi-variable causal inference for debiasing ABSA. In this framework, different types of biases are tackled based on different causal intervention methods. For the review branch, the bias is modeled as indirect confounding from context, where backdoor adjustment intervention is employed for debiasing. For the aspect branch, the bias is described as a direct correlation with labels, where counterfactual reasoning is adopted for debiasing. Extensive experiments demonstrate the effectiveness of the proposed method compared to various baselines on the two widely used real-world aspect robustness test set datasets.

翻译：尽管取得了显著进展，基于神经网络的方面级情感分析（ABSA）模型容易从标注偏差中学习虚假相关性，导致在对抗性数据转换中鲁棒性较差。在去偏解决方案中，基于因果推断的方法引起了广泛研究关注，主要可分为因果干预方法和反事实推理方法。然而，现有的大多数去偏方法侧重于单变量因果推断，不适用于具有两个输入变量（目标方面和评论文本）的ABSA任务。本文提出了一种基于多变量因果推断的去偏ABSA新框架。在该框架中，不同类型偏差通过不同因果干预方法进行处理：对于评论文本分支，偏差被建模为上下文中的间接混杂因素，采用后门调整干预进行去偏；对于方面分支，偏差被描述为与标签的直接相关性，采用反事实推理进行去偏。在两个广泛使用的真实世界方面鲁棒性测试集上的大量实验表明，与各种基线方法相比，所提方法具有有效性。