Human-Like Decision Making: Document-level Aspect Sentiment Classification via Hierarchical Reinforcement Learning

Jingjing Wang, Changlong Sun, Shoushan Li, Jiancheng Wang, Luo Si, Min Zhang, Xiaozhong Liu, Guodong Zhou


Abstract
Recently, neural networks have shown promising results on Document-level Aspect Sentiment Classification (DASC). However, these approaches often offer little transparency w.r.t. their inner working mechanisms and lack interpretability. In this paper, to simulating the steps of analyzing aspect sentiment in a document by human beings, we propose a new Hierarchical Reinforcement Learning (HRL) approach to DASC. This approach incorporates clause selection and word selection strategies to tackle the data noise problem in the task of DASC. First, a high-level policy is proposed to select aspect-relevant clauses and discard noisy clauses. Then, a low-level policy is proposed to select sentiment-relevant words and discard noisy words inside the selected clauses. Finally, a sentiment rating predictor is designed to provide reward signals to guide both clause and word selection. Experimental results demonstrate the impressive effectiveness of the proposed approach to DASC over the state-of-the-art baselines.
Anthology ID:
D19-1560
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:
5581–5590
Language:
URL:
https://aclanthology.org/D19-1560
DOI:
10.18653/v1/D19-1560
Bibkey:
Cite (ACL):
Jingjing Wang, Changlong Sun, Shoushan Li, Jiancheng Wang, Luo Si, Min Zhang, Xiaozhong Liu, and Guodong Zhou. 2019. Human-Like Decision Making: Document-level Aspect Sentiment Classification via Hierarchical Reinforcement Learning. 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 5581–5590, Hong Kong, China. Association for Computational Linguistics.
Cite (Informal):
Human-Like Decision Making: Document-level Aspect Sentiment Classification via Hierarchical Reinforcement Learning (Wang et al., EMNLP-IJCNLP 2019)
Copy Citation:
PDF:
https://aclanthology.org/D19-1560.pdf