Aspect-based-sentiment-analysis (ABSA) is a fine-grained sentiment evaluation task, which analyze the emotional polarity of the evaluation aspects. Generally, the emotional polarity of an aspect exists in the corresponding opinion expression, whose diversity has great impacts on model's performance. To mitigate this problem, we propose a novel and simple counterfactual data augmentation method that reverses the opinion expression of the aspects. Specially, the integrated gradients are calculated to identify and mask the opinion expression. Then, a prompt with the reverse expression polarity is combined to the original text, and a pre-trained language model (PLM), T5, is finally was employed to predict the masks. The experimental results show the proposed counterfactual data augmentation method perform better than current methods on three open-source datasets, i.e. Laptop, Restaurant and MAMS.

翻译：方面级情感分析是一项细粒度的情感评估任务，旨在分析评价方面的情感极性。通常，某方面的情感极性存在于对应的观点表达中，其多样性对模型性能有显著影响。为缓解这一问题，我们提出一种新颖且简洁的反事实数据增强方法，通过逆转方面的观点表达来实现。具体而言，首先计算积分梯度以识别并遮掩观点表达，随后将具有相反表达极性的提示与原始文本结合，并最终采用预训练语言模型T5预测被遮掩的部分。实验结果表明，所提出的反事实数据增强方法在三个开源数据集（即Laptop、Restaurant和MAMS）上的表现优于现有方法。