Syntactic-Enhanced Multi-Task Learning Model for Aspect Sentiment Triplet Extraction

Abstract Aspect sentiment triplet extraction (ASTE), which aims to extract aspect terms, opinion terms, and sentiment polarity from textual comments, is a crucial task in aspect-based sentiment analysis. Most existing approaches focus on leveraging contextual information while neglecting the effective utilization of syntactic structures within the text. To improve extraction performance, this paper proposes a syntax-enhanced multi-task learning model, SE-ASTE, which jointly extracts aspect sentiment triplets by incorporating syntax connections and dependency edge type information. Specifically, the ASTE task is decomposed into three sub-tasks: opinion entity extraction, relation detection, and sentiment extraction. To capture syntactic dependencies, we employ a graph convolutional network with an attention mechanism, which computes the importance of dependency edges and aggregates node information in a targeted manner to generate a syntax-enhanced contextual representation. Subsequently, a self-attention module is utilized to generate task-specific features, while a sentiment extraction module, based on a affine scorer, captures sentiment relationships between words. Experimental results on the ASTE-Data-V2 dataset demonstrate that SE-ASTE achieves an average improvement of 1.45% in the F1-score compared to baseline models, highlighting its effectiveness in aspect sentiment triplet extraction.