A Novel Counterfactual Data Augmentation Method for Aspect-Based Sentiment Analysis
This work addresses a domain-specific problem in natural language processing for sentiment analysis, offering an incremental improvement in data augmentation techniques.
The authors tackled the problem of limited opinion expression diversity in aspect-based sentiment analysis by proposing a counterfactual data augmentation method that generates reversed-sentiment opinion expressions, achieving better performance than current methods on three datasets (Laptop, Restaurant, and MAMS).
Aspect-based-sentiment-analysis (ABSA) is a fine-grained sentiment evaluation task, which analyzes the emotional polarity of the evaluation aspects. Generally, the emotional polarity of an aspect exists in the corresponding opinion expression, whose diversity has great impact on model's performance. To mitigate this problem, we propose a novel and simple counterfactual data augmentation method to generate opinion expressions with reversed sentiment polarity. In particular, the integrated gradients are calculated to locate and mask the opinion expression. Then, a prompt combined with the reverse expression polarity is added to the original text, and a Pre-trained language model (PLM), T5, is finally was employed to predict the masks. The experimental results shows the proposed counterfactual data augmentation method performs better than current augmentation methods on three ABSA datasets, i.e. Laptop, Restaurant, and MAMS.