ESSDB-GCN: Enhanced Syntactic and Semantic Dual-Branch Graph Convolutional Network for Aspect Sentiment Triple Extraction

Aspect-based Sentiment Triplet Extraction (ASTE) is an emerging research area in sentiment analysis, which aims to identify aspect terms and their corresponding sentiment polarity and opinion terms in sentences. Previous studies have tried to use graph neural networks on dependency trees to handle ASTE tasks through pipelines or end-to-end approaches, but these methods have limitations and do not effectively combine semantic and syntactic information as well as various features in span markers.To address these issues, we propose a new solution called Enhanced Syntax and Semantics Dual-Branch Graph Convolutional Network (ESSDB-GCN), which can better integrate syntactic and semantic information. Specifically, we first designed a syntactic dependency enhancement channel to enhance syntactic features, and optimized syntactic information by treating the syntactic dependency probability matrix as a graph structure. Next, we designed a semantic channel with a self-attention mechanism to enhance semantic information and proposed orthogonal and differential regularizers to strengthen semantic relevance. Lastly, we explored span-level information and constraints to solve the problem of emotion word tagging, in order to generate more accurate aspect-based sentiment triplets. Our proposed ESSDB-GCN demonstrates strong performance on multiple benchmark datasets, proving the effectiveness of our method.