Aspect-based Sentiment Classification with Reinforced Dependency Graph

Abstract

We proposed Reinforced Dependency Graph for Aspect-based Sentiment Classification (RDGSC), a reinforced dependency graph model for aspect-based sentiment classification. In this framework, we train a policy network using deep reinforcement learning and construct a reinforced dependency graph for aspect-based sentiment classification. The graph attention network is used to fuse the aspect-related information in the text over the reinforced dependency graph. Each contextual representation is given an aspect-related attention weight through a retrieve-based attention mechanism. A refined final representation is obtained for classification and calculating delayed reward to guide the policy network to updates. Extensive experiments were conducted on five publicly available datasets, the results show that our method is superior to all the baseline methods in two evaluation indicators Accuracy and F1.

Keywords

• natural language processing
• aspect-based sentiment classification
• deep reinforcement learning
• graph attention network
• dependency tree