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

Citations Over TimeTop 10% of 2022 papers

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 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 intracontext) and the sentiment relations across aspects (called inter-context) for learning. Experiments on four benchmark datasets demonstrate that BiSyn-GAT+ outperforms the stateof-the-art methods consistently.

Related Papers

• → Some arguments for higher nodes in syntax: a reply to Hudson’s ‘Constituency and dependency’(1980)71 cited
• → Effective Approach to Joint Training of POS Tagging and Dependency Parsing Models(2020)1 cited
• → Factors influencing dependency parsing of coordinating structure(2009)1 cited
• → A Simulated Shallow Dependency Parser Based on Weighted Hierarchical Structure Learning(2008)1 cited
• → A simulated shallow dependency parser based on weighted hierarchical structure learning(2008)