Analysis of targeted sentiment by the attention gated convolutional network model

被引：0
作者：
Cao W. [1 ]
Li J. [1 ]
Wang H. [1 ]
机构：
[1] School of Computer Science and Technology, Civil Aviation University of China, Tianjin
来源：
Xi'an Dianzi Keji Daxue Xuebao/Journal of Xidian University | 2019年 / 46卷 / 06期
关键词：
Gated convolution mechanism; Multiple attention mechanism; Recurrent neural networks; Sentiment analysis;
D O I：
10.19665/j.issn1001-2400.2019.06.005
中图分类号：
学科分类号：
摘要：
The recurrent neural networks are used for traditional targeted sentiment analysis and usually lead to a long training time. And other alternative models are unable to make a good interaction between context and target words. An attention gated convolutional network model for targeted sentiment analysis is proposed. First, context and target words are processed by the multiple attention mechanism to enhance their interactions. Second, the gated convolution mechanism is used to selectively generate emotional features. Finally, the emotional features are classified by the Softmax classifier to output the emotional polarity. Experimental results show that compared with the Recurrent Attention Network model, which has the highest accuracy rate in the recurrent neural network models, the proposed model improves the accuracy rate by 1.29% and 0.12% respectively on the Restaurant and Laptop datasets of SemEval 2014 Task4. Compared with the Attention-based Long Short-Term Memory Network model, which has a faster convergence rate in the recurrent neural network model, the convergence time is reduced by 29.17 s. © 2019, The Editorial Board of Journal of Xidian University. All right reserved.
引用
收藏
页码：30 / 36
页数：6
相关论文
共 14 条
  • [1] Wang S., Mazumder S., Liu B., Et al., Target-sensitive Memory Networks for Aspect Sentiment Classification, Proceedings of the 2018 56th Annual Meeting of the Association for Computational Linguistics, pp. 957-967, (2018)
  • [2] Ma D.H., Li S.J., Wang H.F., Joint Learning for Targeted Sentiment Analysis, Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pp. 4737-4742, (2018)
  • [3] Liu F., Cohn T., Baldwin T., Recurrent Entity Networks with Delayed Memory Update for Targeted Aspect-based Sentiment Analysis, Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pp. 278-283, (2018)
  • [4] Chen P., Sun Z., Bing L., Et al., Recurrent Attention Network on Memory for Aspect Sentiment Analysis, Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pp. 452-461, (2017)
  • [5] Tang D., Qin B., Liu T., Aspect Level Sentiment Classification with Deep Memory Network, Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, pp. 214-224, (2016)
  • [6] Wang Y., Huang M., Zhu X., Et al., Attention-based LSTM for Aspect-level Sentiment Classification, Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, pp. 606-615, (2016)
  • [7] Ma D.H., Li S.J., Zhang X.D., Et al., Interactive Attention Networks for Aspect-level Sentiment Classification
  • [8] Mishra A., Dey K., Bhattacharyya P., Learning Cognitive Features from Gaze Data for Sentiment and Sarcasm Classification Using Convolutional Neural Network, Proceedings of the 201755th Annual Meeting of the Association for Computational Linguistics, pp. 377-387, (2017)
  • [9] Xue W., Li T., Aspect Based Sentiment Analysis with Gated Convolutional Networks, Proceedings of the 201856th Annual Meeting of the Association for Computational Linguistics, pp. 2514-2523, (2018)
  • [10] Li X., Bing L., Lam W., Et al., Transformation Networks for Target-oriented Sentiment Classification, Proceedings of the 201856th Annual Meeting of the Association for Computational Linguistics, pp. 946-956, (2018)
12