Multi-View Attention Syntactic Enhanced Graph Convolutional Network for Aspect-based Sentiment Analysis

2025-01-27

AI Summary

Existing GNN-based aspect-based sentiment analysis (ABSA) methods rely solely on a single dependency tree view, limiting their capacity to capture multifaceted syntactic information. To address this, we propose Multi-View Attention-enhanced Graph Convolutional Networks (MV-GCN), a novel framework that introduces: (i) a distance-masked multi-subgraph construction strategy to explicitly encode diverse syntactic distances; (ii) a learnable, dependency-type-aware adjacency matrix to better model heterogeneous edge semantics; and (iii) a structural entropy regularization loss to enhance graph structural robustness. Furthermore, we pioneer the integration of multi-view attention to dynamically weight and fuse representations from complementary syntactic perspectives. Extensive experiments on four benchmark ABSA datasets demonstrate consistent and significant improvements over state-of-the-art methods. Our code and data are publicly available.

Technology Category

• Natural Language Processing: Syntax — Tagging, Chunking & Parsing
• Machine Learning: Multi-instance/Multi-view Learning
• Computer Vision: Multi-modal Vision

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Web Mining and Content Analysis: Large pretrained models with web data

Abstract

Aspect-based Sentiment Analysis (ABSA) is the task aimed at predicting the sentiment polarity of aspect words within sentences. Recently, incorporating graph neural networks (GNNs) to capture additional syntactic structure information in the dependency tree derived from syntactic dependency parsing has been proven to be an effective paradigm for boosting ABSA. Despite GNNs enhancing model capability by fusing more types of information, most works only utilize a single topology view of the dependency tree or simply conflate different perspectives of information without distinction, which limits the model performance. To address these challenges, in this paper, we propose a new multi-view attention syntactic enhanced graph convolutional network (MASGCN) that weighs different syntactic information of views using attention mechanisms. Specifically, we first construct distance mask matrices from the dependency tree to obtain multiple subgraph views for GNNs. To aggregate features from different views, we propose a multi-view attention mechanism to calculate the attention weights of views. Furthermore, to incorporate more syntactic information, we fuse the dependency type information matrix into the adjacency matrices and present a structural entropy loss to learn the dependency type adjacency matrix. Comprehensive experiments on four benchmark datasets demonstrate that our model outperforms state-of-the-art methods. The codes and datasets are available at https://github.com/SELGroup/MASGCN.

Problem

• Graph Neural Networks
• Aspect-based Sentiment Analysis
• Multi-perspective Information Processing

Innovation

• MASGCN
• Multi-angle Attention Mechanism
• Grammar-enhanced Graph Network