Capsule Network with Interactive Attention for Aspect-Level Sentiment Classification

Chunning Du, Haifeng Sun, Jingyu Wang, Qi Qi, Jianxin Liao, Tong Xu, Ming Liu


Abstract
Aspect-level sentiment classification is a crucial task for sentiment analysis, which aims to identify the sentiment polarities of specific targets in their context. The main challenge comes from multi-aspect sentences, which express multiple sentiment polarities towards different targets, resulting in overlapped feature representation. However, most existing neural models tend to utilize static pooling operation or attention mechanism to identify sentimental words, which therefore insufficient for dealing with overlapped features. To solve this problem, we propose to utilize capsule network to construct vector-based feature representation and cluster features by an EM routing algorithm. Furthermore, interactive attention mechanism is introduced in the capsule routing procedure to model the semantic relationship between aspect terms and context. The iterative routing also enables encoding sentence from a global perspective. Experimental results on three datasets show that our proposed model achieves state-of-the-art performance.
Anthology ID:
D19-1551
Volume:
Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)
Month:
November
Year:
2019
Address:
Hong Kong, China
Editors:
Kentaro Inui, Jing Jiang, Vincent Ng, Xiaojun Wan
Venues:
EMNLP | IJCNLP
SIG:
SIGDAT
Publisher:
Association for Computational Linguistics
Note:
Pages:
5489–5498
Language:
URL:
https://aclanthology.org/D19-1551
DOI:
10.18653/v1/D19-1551
Bibkey:
Cite (ACL):
Chunning Du, Haifeng Sun, Jingyu Wang, Qi Qi, Jianxin Liao, Tong Xu, and Ming Liu. 2019. Capsule Network with Interactive Attention for Aspect-Level Sentiment Classification. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pages 5489–5498, Hong Kong, China. Association for Computational Linguistics.
Cite (Informal):
Capsule Network with Interactive Attention for Aspect-Level Sentiment Classification (Du et al., EMNLP-IJCNLP 2019)
Copy Citation:
PDF:
https://aclanthology.org/D19-1551.pdf