Aspect-based Sentiment Classification via Memory Graph Convolutional Network
WANG Guang1, LI Hongyu1,2, QIU Yunfei1, YU Bowen2, LIU Tingwen2
1.School of Software, Liaoning Technical University, Huludao, Liaoning 125105, China; 2.Institute of Information Engineering, Chinese Academy of Sciences, Beijing 100089, China
Abstract：In aspect-based sentiment classification, the attention mechanism is often combined in recurrent neural network or convolutional neural network to obtain the importance of different words. However, such kind of methods fail to capture long-range syntactic relations that are obscure from the surface form, which would be beneficial to identify sentiment features directly related to the aspect target. In this paper, we propose a novel model named MemGCN to explicitly utilize the dependency relationship among words. Firstly, we employ the memory network to obtain the context-aware memory representation. After that, we apply graph convolutional network over the dependency tree to propagate sentiment features directly from the syntactic context of an aspect target. Finally, the attention mechanism is used to fuse memory and syntactic information. Experiment results on SemEval 2014 and Twitter datasets demonstrate our model outperforms baseline methods.
[1] Liu B. Sentiment analysis and opinion mining[M]. San Rafael: Morgan and Claypool Publishers, 2012: 1-167. [2] Zhou J, Huang J X, Chen Q, et al.Deep learning for aspect-level sentiment classification: survey, vision, and challenges[J].IEEE Access, 2019,7: 78454-78483. [3] Thomas N, Max W. Semi-supervised classification with graph convolutional networks[C]//Proceedings of the Conference on International Conference on Learning Representations,2017. [4] Liang Y, Mao C S, Luo Y. Graph convolutional networks for text classification[C]//Proceedings of the 33rd AAAI Conference on Artificial Intelligence.2019: 7370-7377. [5] Kiritchenko S, Zhu X, Cherry C, et al. NRC-Canada-2014: Detecting aspects and sentiment in customer reviews[C]//Proceedings of the 8th International Workshop on Semantic Evaluation,2014: 437-442. [6] Dong L, Wei F R, Tan C Q, et al. Adaptive recursive neural network for target-dependent twitter sentiment classification[C]//Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics. Stroudsburg, USA: ACL, 2014, II: 49-54. [7] Tang D Y, Qin B, Feng X C, et al. Effective LSTMs for target-dependent sentiment classification[C]//Proceedings of the 26th International Conference on Computational Linguistics. Berlin, Germany: Springer, 2016: 3298-3307. [8] Tom Y, Devamanyu H, Soujanya P, et al. Recent trends in deep learning based natural language processing[J]. IEEE Computational Intelligence Maga-zine 2018,13(3): 55-75. [9] Bahdanau D, Cho K, Bengio Y. Neural machine translation by jointly learning to align and translate[C]//Proceedings of the 3rd International Conference on Learning Representations,2015: 1-15. [10] Wang Y Q, Huang M L, Zhao L, et al. Attention-based LSTM for aspect-level sentiment classification[C]//Proceedings of the Conference on Empirical Methods in Natural Language Processing. Stroudsburg, USA: ACL, 2016: 606-615. [11] 曾锋,曾碧卿,韩旭丽,等.基于双层注意力循环神经网络的方面级情感分析[J]. 中文信息学报, 2019, 33(6): 108-115. [12] Xue W, Li T. Aspect based sentiment analysis with gated convolutional networks[C]//Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics. Melbourne, Australia: ACL, 2018: 2514-2523. [13] 梁斌,刘全,徐进,等.基于多注意力卷积神经网络的特定目标情感分析[J]. 计算机研究与发展, 2017, 54(8): 1724-1735. [14] 刘全,梁斌,徐进,等.一种用于基于方面情感分析的深度分层网络模型[J].计算机学报,2018,41(12): 2637-2652. [15] 杜慧,俞晓明,刘悦,等. 融合词性和注意力的卷积神经网络对象级情感分类方法[J]. 模式识别与人工智能, 2018, 31(12): 1120-1126. [16] Tang D Y, Qin B, Liu T. Aspect level sentiment classification with deep memory network[C]//Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing. Stroudsburg, USA: ACL, 2016: 214-224. [17] Ma D H, Li S J, Zhang X D, et al. Interactive attention networks for aspect-level sentiment classification[C]//Proceedings of the 26th International Joint Conference on Artificial Intelligence. Berlin, Germany: Springer, 2017: 4068-4074. [18] Chen P, Sun Z Q, Bing L D, et al. Recurrent attention network on memory for aspect sentiment analysis[C]//Proceedings of the Conference on Empirical Methods in Natural Language Processing. Stroudsburg, USA: ACL, 2017: 452-461. [19] Zhu P S, Qian T Y. Enhanced aspect level sentiment classification with auxiliary memory[C]//Proceedings of the 27th International Conference on Computational Lin-guistics. Stroudsburg,USA: ACL, 2018: 1077-1087. [20] Pennington J, Socher R, Manning C D. Glove: Global vectors for word representation[C]//Proceedings of the Conference on Empirical Methods in Natural Language Processing. Stroudsburg, USA: ACL, 2014: 1532-1543. [21] 贾川,方睿,浦东,等. 基于循环实体网络的细粒度情感分析[J]. 中文信息学报, 2019, 33(9): 123-128. [22] 廖祥文,林威,吴运兵,等.基于辅助记忆循环神经网络的视角级情感分析[J]. 模式识别与人工智能, 2019, 32(11): 987-996. [23] Diego M, Ivan T. Encoding sentences with graph convolu-tional networks for semantic role labeling[C]//Proceedings of the Conference on Empirical Methods in Natural Language Processing, 2017: 1506-1515. [24] Xu Y, Yang J. Look again at the syntax: Relational graph convolutional network for gendered ambiguous pronoun resolution[J]. arXiv preprint arXiv: 1905.08868, 2019. [25] 李鸿宇. 基于图卷积记忆网络的细粒度情感分析研究[D]. 葫芦岛: 辽宁工程技术大学硕士学位论文, 2020. [26] He R D, Lee W S, Ng H T, et al. Effective attention modeling for aspect-level sentiment classification[C]//Proceedings of the 27th International Conference on Com-putational Linguistics. Stroudsburg, USA: ACL, 2018: 1121-1131. [27] Devlin J, Chang M, Lee K, et al. BERT: Pre-training of deep bidirectional transformers for language understand-ing[C]//Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics: NAACL-HLT, 2019: 4171-4186. [28] Huang B X, Ou Y L, Kathleen M. Aspect level sentiment classification with attention-over-attention neural networks[C]//Proceedings of the International Conference on Social Computing, Behavioral-Cultural Modeling and Prediction and Behavior Representation in Modeling and Simulation,2018: 197-206. [29] He R D, Lee W S, Ng H T, et al. Exploiting document knowledge for aspect-level sentiment classification[C]//Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics. Stroudsburg, USA: ACL, 2018: 579-585. [30] Majumder N, Poria S, Gelbukh A F, et al. IARM: inter aspect relation modeling with memory networks in aspect-based sentiment analysis[C]//Proceedings of the Conference on Empirical Methods in Natural Language Processing. Stroudsburg, USA: ACL, 2018: 3402-3411. [31] Liu Q, Zhang H B, Zeng Y F, et al. Content attention model for aspect based sentiment analysis[C]//Proceedings of the World Wide Web Conference 2018. Washington, USA: IEEE, 2018: 1023-1032.
2021, Vol. 35 
