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

Shuo Liang, Wei Wei, Xian-Ling Mao, Fei Wang, Zhiyong He


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.
Anthology ID:
2022.findings-acl.144
Volume:
Findings of the Association for Computational Linguistics: ACL 2022
Month:
May
Year:
2022
Address:
Dublin, Ireland
Editors:
Smaranda Muresan, Preslav Nakov, Aline Villavicencio
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1835–1848
Language:
URL:
https://aclanthology.org/2022.findings-acl.144
DOI:
10.18653/v1/2022.findings-acl.144
Bibkey:
Cite (ACL):
Shuo Liang, Wei Wei, Xian-Ling Mao, Fei Wang, and Zhiyong He. 2022. BiSyn-GAT+: Bi-Syntax Aware Graph Attention Network for Aspect-based Sentiment Analysis. In Findings of the Association for Computational Linguistics: ACL 2022, pages 1835–1848, Dublin, Ireland. Association for Computational Linguistics.
Cite (Informal):
BiSyn-GAT+: Bi-Syntax Aware Graph Attention Network for Aspect-based Sentiment Analysis (Liang et al., Findings 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.findings-acl.144.pdf
Code
 CCIIPLab/BiSyn_GAT_plus
Data
MAMS