Dual Graph Convolutional Networks for Aspect-based Sentiment Analysis

Ruifan Li, Hao Chen, Fangxiang Feng, Zhanyu Ma, Xiaojie Wang, Eduard Hovy


Abstract
Aspect-based sentiment analysis is a fine-grained sentiment classification task. Recently, graph neural networks over dependency trees have been explored to explicitly model connections between aspects and opinion words. However, the improvement is limited due to the inaccuracy of the dependency parsing results and the informal expressions and complexity of online reviews. To overcome these challenges, in this paper, we propose a dual graph convolutional networks (DualGCN) model that considers the complementarity of syntax structures and semantic correlations simultaneously. Particularly, to alleviate dependency parsing errors, we design a SynGCN module with rich syntactic knowledge. To capture semantic correlations, we design a SemGCN module with self-attention mechanism. Furthermore, we propose orthogonal and differential regularizers to capture semantic correlations between words precisely by constraining attention scores in the SemGCN module. The orthogonal regularizer encourages the SemGCN to learn semantically correlated words with less overlap for each word. The differential regularizer encourages the SemGCN to learn semantic features that the SynGCN fails to capture. Experimental results on three public datasets show that our DualGCN model outperforms state-of-the-art methods and verify the effectiveness of our model.
Anthology ID:
2021.acl-long.494
Volume:
Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)
Month:
August
Year:
2021
Address:
Online
Editors:
Chengqing Zong, Fei Xia, Wenjie Li, Roberto Navigli
Venues:
ACL | IJCNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
6319–6329
Language:
URL:
https://aclanthology.org/2021.acl-long.494
DOI:
10.18653/v1/2021.acl-long.494
Bibkey:
Cite (ACL):
Ruifan Li, Hao Chen, Fangxiang Feng, Zhanyu Ma, Xiaojie Wang, and Eduard Hovy. 2021. Dual Graph Convolutional Networks for Aspect-based Sentiment Analysis. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pages 6319–6329, Online. Association for Computational Linguistics.
Cite (Informal):
Dual Graph Convolutional Networks for Aspect-based Sentiment Analysis (Li et al., ACL-IJCNLP 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.acl-long.494.pdf
Video:
 https://aclanthology.org/2021.acl-long.494.mp4
Code
 ccchenhao997/dualgcn-absa