CAN: Constrained Attention Networks for Multi-Aspect Sentiment Analysis
Mengting Hu, Shiwan Zhao, Li Zhang, Keke Cai, Zhong Su, Renhong Cheng, Xiaowei Shen
Abstract
Aspect level sentiment classification is a fine-grained sentiment analysis task. To detect the sentiment towards a particular aspect in a sentence, previous studies have developed various attention-based methods for generating aspect-specific sentence representations. However, the attention may inherently introduce noise and downgrade the performance. In this paper, we propose constrained attention networks (CAN), a simple yet effective solution, to regularize the attention for multi-aspect sentiment analysis, which alleviates the drawback of the attention mechanism. Specifically, we introduce orthogonal regularization on multiple aspects and sparse regularization on each single aspect. Experimental results on two public datasets demonstrate the effectiveness of our approach. We further extend our approach to multi-task settings and outperform the state-of-the-art methods.- Anthology ID:
- D19-1467
- 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:
- 4601–4610
- Language:
- URL:
- https://aclanthology.org/D19-1467
- DOI:
- 10.18653/v1/D19-1467
- Cite (ACL):
- Mengting Hu, Shiwan Zhao, Li Zhang, Keke Cai, Zhong Su, Renhong Cheng, and Xiaowei Shen. 2019. CAN: Constrained Attention Networks for Multi-Aspect Sentiment Analysis. 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 4601–4610, Hong Kong, China. Association for Computational Linguistics.
- Cite (Informal):
- CAN: Constrained Attention Networks for Multi-Aspect Sentiment Analysis (Hu et al., EMNLP-IJCNLP 2019)
- PDF:
- https://preview.aclanthology.org/teach-a-man-to-fish/D19-1467.pdf