BiSyn-GAT+: Bi-Syntax Aware Graph Attention Network for Aspect-based Sentiment Analysis

TL;DR

This paper introduces BiSyn-GAT+, a novel graph attention network that leverages constituent syntax to improve aspect-based sentiment analysis by better modeling aspect-sentiment relations.

Contribution

It proposes a syntax-aware graph attention model that utilizes phrase segmentation and hierarchical structures to enhance sentiment analysis accuracy.

Findings

Outperforms state-of-the-art methods on four benchmark datasets.

Effectively models intra- and inter-aspect sentiment relations.

Leverages constituent syntax to reduce noise from dependency trees.

Abstract

Aspect-based sentiment analysis (ABSA) is a fine-grained sentiment analysis task that aims to align aspects and corresponding sentiments for aspect-specific sentiment polarity inference. It is challenging because a sentence may contain multiple aspects or complicated (e.g., conditional, coordinating, or adversative) relations. Recently, exploiting dependency syntax information with graph neural networks has been the most popular trend. Despite its success, methods that heavily rely on the dependency tree pose challenges in accurately modeling the alignment of the aspects and their words indicative of sentiment, since the dependency tree may provide noisy signals of unrelated associations (e.g., the "conj" relation between "great" and "dreadful" in Figure 2). In this paper, to alleviate this problem, we propose a Bi-Syntax aware Graph Attention Network (BiSyn-GAT+). Specifically, BiSyn-GAT+ fully exploits the syntax information (e.g., phrase segmentation and hierarchical structure) of the constituent tree of a sentence to model the sentiment-aware context of every single aspect (called intra-context) and the sentiment relations across aspects (called inter-context) for learning. Experiments on four benchmark datasets demonstrate that BiSyn-GAT+ outperforms the state-of-the-art methods consistently.