Paper Info
Title
Discrete Opinion Tree Induction for Aspect-based Sentiment Analysis
Abstract
Dependency trees have been intensively used with graph neural networks for aspect-based sentiment classification. Though being effective, such methods rely on external dependency parsers, which can be unavailable for low-resource languages or perform worse in low-resource domains. In addition, dependency trees are also not optimized for aspect-based sentiment classification. In this paper, we propose an aspect-specific and language-agnostic discrete latent opinion tree model as an alternative structure to explicit dependency trees. To ease the learning of complicated structured latent variables, we build a connection between aspect-to-context attention scores and syntactic distances, inducing trees from the attention scores. Results on six English benchmarks, one Chinese dataset and one Korean dataset show that our model can achieve competitive performance and interpretability.
Year
DOI
Venue
2022
10.18653/v1/2022.acl-long.145
PROCEEDINGS OF THE 60TH ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS (ACL 2022), VOL 1: (LONG PAPERS)
DocType
Volume
Citations 
Conference
Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
0
PageRank 
References 
Authors
0.34
0
4
Name
Order
Citations
PageRank
Chenhua Chen100.34
Zhiyang Teng2447.03
Zhong-qing Wang314020.28
Yue Zhang41364114.17