%0 Conference Proceedings %T CAN: Constrained Attention Networks for Multi-Aspect Sentiment Analysis %A Hu, Mengting %A Zhao, Shiwan %A Zhang, Li %A Cai, Keke %A Su, Zhong %A Cheng, Renhong %A Shen, Xiaowei %Y Inui, Kentaro %Y Jiang, Jing %Y Ng, Vincent %Y Wan, Xiaojun %S Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP) %D 2019 %8 November %I Association for Computational Linguistics %C Hong Kong, China %F hu-etal-2019-constrained %X 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. %R 10.18653/v1/D19-1467 %U https://aclanthology.org/D19-1467 %U https://doi.org/10.18653/v1/D19-1467 %P 4601-4610