Aspect-based Sentiment Classification with Dependency Relation and Structured Attention
Yuxiang Jia, Yadong Wang, Hongying Zan, Qi Xie, Yingjie Yan, Yalei Liu · 2021
Aspect-based sentiment classification (ASC) is a task to determine the sentiment polarities of specific aspects in a review. Syntactic information like dependency relation has been proven effective when extracting sentiment features. On the other hand, multiple semantic segments in a review may influence the sentiment polarity. Thus, we propose a neural network based on dependency relation and structured attention (DRSAN) to fuse both dependency relation features and multiple semantic segments with different attention mechanisms. To our knowledge, we are the first to explicitly integrate dependency relation and structured attention for the ASC task. The experimental results on SemEval 2014 Task4 and Twitter datasets show that the proposed model outperforms all other benchmark models.