Graph Convolutional Network with Syntactic Dependency for Aspect-Based Sentiment Analysis
Fan Zhang, Wenbin Zheng, Yujie Yang
Abstract
Abstract Aspect-based sentiment analysis (ABSA) aims to mine the sentiment tendencies expressed by specific aspect terms. The studies of ABSA mainly focus on the attention-based approaches and the graph neural network approaches based on dependency trees. However, the attention-based methods usually face difficulties in capturing long-distance syntactic dependencies. Additionally, existing approaches using graph neural networks have not made sufficient exploit the syntactic dependencies among aspects and opinions. In this paper, we propose a novel Syntactic Dependency Graph Convolutional Network (SD-GCN) model for ABSA. We employ the Biaffine Attention to model the sentence syntactic dependencies and build syntactic dependency graphs from aspects and emotional words. This allows our SD-GCN to learn both the semantic relationships of aspects and the overall semantic meaning. According to these graphs, the long-distance syntactic dependency relationships are captured by GCNs, which facilitates SD-GCN to capture the syntactic dependencies between aspects and viewpoints more comprehensively, and consequently yields enhanced aspect features. We conduct extensive experiments on four aspect-level sentiment datasets. The experimental results show that our SD-GCN outperforms other methodologies. Moreover, ablation experiments and visualization of attention further substantiate the effectiveness of SD-GCN.