Adaptive Data Augmentation for Aspect Sentiment Quad Prediction
This work addresses data imbalance for researchers in aspect-based sentiment analysis, but it is incremental as it builds on existing generative frameworks.
The paper tackles the data imbalance problem in aspect sentiment quad prediction by proposing an Adaptive Data Augmentation framework to enhance tail quad patterns and aspect categories, showing that it improves performance and outperforms naive oversampling.
Aspect sentiment quad prediction (ASQP) aims to predict the quad sentiment elements for a given sentence, which is a critical task in the field of aspect-based sentiment analysis. However, the data imbalance issue has not received sufficient attention in ASQP task. In this paper, we divide the issue into two-folds, quad-pattern imbalance and aspect-category imbalance, and propose an Adaptive Data Augmentation (ADA) framework to tackle the imbalance issue. Specifically, a data augmentation process with a condition function adaptively enhances the tail quad patterns and aspect categories, alleviating the data imbalance in ASQP. Following previous studies, we also further explore the generative framework for extracting complete quads by introducing the category prior knowledge and syntax-guided decoding target. Experimental results demonstrate that data augmentation for imbalance in ASQP task can improve the performance, and the proposed ADA method is superior to naive data oversampling.