RDGCN: Reinforced Dependency Graph Convolutional Network for Aspect-based Sentiment Analysis

TL;DR

This paper introduces RDGCN, a novel graph neural network that enhances aspect-based sentiment analysis by more effectively modeling syntactic dependencies using reinforcement learning and attention mechanisms.

Contribution

The paper proposes a reinforced dependency graph convolutional network that improves dependency importance calculation for better sentiment analysis performance.

Findings

RDGCN outperforms existing GNN-based models on multiple datasets.

The importance calculation criterion improves syntactic dependency utilization.

Reinforcement learning effectively optimizes dependency weight distribution.

Abstract

Aspect-based sentiment analysis (ABSA) is dedicated to forecasting the sentiment polarity of aspect terms within sentences. Employing graph neural networks to capture structural patterns from syntactic dependency parsing has been confirmed as an effective approach for boosting ABSA. In most works, the topology of dependency trees or dependency-based attention coefficients is often loosely regarded as edges between aspects and opinions, which can result in insufficient and ambiguous syntactic utilization. To address these problems, we propose a new reinforced dependency graph convolutional network (RDGCN) that improves the importance calculation of dependencies in both distance and type views. Initially, we propose an importance calculation criterion for the minimum distances over dependency trees. Under the criterion, we design a distance-importance function that leverages reinforcement learning for weight distribution search and dissimilarity control. Since dependency types often do not have explicit syntax like tree distances, we use global attention and mask mechanisms to design type-importance functions. Finally, we merge these weights and implement feature aggregation and classification. Comprehensive experiments on three popular datasets demonstrate the effectiveness of the criterion and importance functions. RDGCN outperforms state-of-the-art GNN-based baselines in all validations.