Abstract
Emotion classification has become a hot research topic in natural language processing due to its wide application. Existing studies suffer from the error propagation problem when using the syntax information in emotion classification since the parser can not produce perfect syntax trees. To address this problem, we propose a new approach by comparing and combining different levels of syntactic information to make full use of syntactic information and alleviate the error propagation. First, we propose to use graph convolutional networks (GCN) to encode dependency trees, in which the probability matrix of all dependency arcs (edge-weighted graph) is treated as the GCN adjacent matrix. Next, we extract the dependency parser encoder hidden representations as the implicit syntactic representations, which can directly avoid the error propagation problem. Finally, we fuse the two different syntax-aware information and inject them into our baseline model as extra inputs. Further experimental results show that the explicit and implicit syntactic information can improve the performance of a BERT-based system which is much stronger than the baseline. In addition, we find that the syntactic knowledge that BERT can express is limited, and the syntactic information of our model brings more contributions, which makes our model consistently outperform the BERT on different sentence lengths.
This work was supported by National Natural Science Foundation of China (Grant No.61936010).
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Baziotis, C., et al.: NTUA-SLP at semeval-2018 task 1: predicting affective content in tweets with deep attentive rnns and transfer learning. In: Proceedings of SemEval@NAACL-HLT, pp. 245–255 (2018)
Chandra, M.A., Bedi, S.S.: Benchmarking tree-based least squares twin support vector machine classifiers. Int. J. Bus. Intell. Data Min. 16(3), 381–395 (2020)
Devlin, J., Chang, M., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: Proceedings of NAACL-HLT (1), pp. 4171–4186 (2019)
Dozat, T., Manning, C.D.: Deep biaffine attention for neural dependency parsing. In: Proceedings of SIGIR (2016)
Duan, S., Zhao, H., Zhang, D., Wang, R.: Syntax-aware data augmentation for neural machine translation. CoRR (2020)
Fei, H., Zhang, Y., Ren, Y., Ji, D.: Latent emotion memory for multi-label emotion classification. In: Proceedings of AAAI, pp. 7692–7699 (2020)
Joulin, A., Grave, E., Bojanowski, P., Mikolov, T.: Bag of tricks for efficient text classification. In: Proceedings of EACL, pp. 427–431 (2017)
Kipf, T.N., Welling, M.: Semi-supervised classification with graph convolutional networks. In: Proceedings of ICLR (2017)
Lai, Y., Zhang, L., Han, D., Zhou, R., Wang, G.: Fine-grained emotion classification of chinese microblogs based on graph convolution networks. In: Proceedings of WWW, pp. 2771–2787 (2020)
Liu, R.: The number of twitter users has accelerated. Website (2021). https://finance.sina.com.cn/tech/2021-02-10/doc-ikftpnny6189670.shtml
Mohammad, S., Bravo-Marquez, F., Salameh, M., Kiritchenko, S.: Semeval-2018 task 1: affect in tweets. In: Proceedings of SemEval@NAACL-HLT, pp. 1–17 (2018)
Peters, M.E., et al.: Deep contextualized word representations. In: Proceedings of NAACL-HLT, pp. 2227–2237 (2018)
Schuster, M., Paliwal, K.K.: Bidirectional recurrent neural networks. IEEE Trans. Sig. Process. 11, 2673–2681 (1997)
Shuangyong, S., Chao, W., Chenglong, C., Wei, Z., Haiqing, C.: Sentiment analysis for intelligent customer service chatbots. J. Chin. Inf. Process. 2, 80–95 (2020)
Vaswani, A., et al.: Attention is all you need. In: Proceedings of NIPS, pp. 5998–6008 (2017)
Wang, C., Wang, B.: Encoding sentences with a syntax-aware self-attention neural network for emotion distribution prediction. In: Proceedings of NLPCC (2), vol. 12431, pp. 256–266 (2020)
Wang, C., Wang, B., Xiang, W., Xu, M.: Encoding syntactic dependency and topical information for social emotion classification. In: Proceedings of SIGIR, pp. 881–884 (2019)
Xia, Q., Li, Z., Zhang, M.: A syntax-aware multi-task learning framework for chinese semantic role labeling. In: EMNLP/IJCNLP (1), pp. 5381–5391 (2019)
Xu, P., Liu, Z., Winata, G.I., Lin, Z., Fung, P.: Emograph: capturing emotion correlations using graph networks. CoRR (2020)
Yang, Q., et al.: Senwave: monitoring the global sentiments under the COVID-19 pandemic. CoRR (2020)
Ying, W., Xiang, R., Lu, Q.: Improving multi-label emotion classification by integrating both general and domain-specific knowledge. In: Proceedings of W-NUT@EMNLP, pp. 316–321 (2019)
Yu, N., Zhang, M., Fu, G.: Transition-based neural rst parsing with implicit syntax features. In: Proceedings of COLING, pp. 559–570 (2018)
Zhang, B., Zhang, Y., Wang, R., Li, Z., Zhang, M.: Syntax-aware opinion role labeling with dependency graph convolutional networks. In: Proceedings of ACL, pp. 3249–3258 (2020)
Zhang, Y., Li, Z., Zhang, M.: Efficient second-order treecrf for neural dependency parsing. In: Proceedings of ACL, pp. 3295–3305 (2020)
Zhao, J., Liu, K., Xu, L.: Sentiment analysis: mining opinions, sentiments, and emotions. Comput. Linguist. 3, 595–598 (2016)
Zheng, R., Zhang, S., Liu, L., Luo, Y., Sun, M.: Uncertainty in bayesian deep label distribution learning. Appl. Soft Comput. 101, 107046 (2021)
Zhou, D., Yang, Y., He, Y.: Relevant emotion ranking from text constrained with emotion relationships. In: Proceedings of NAACL-HLT, pp. 561–571 (2018)
Zhou, X., Wang, Z., Li, S., Zhou, G., Zhang, M.: Emotion detection with neural personal discrimination. In: Proceedings of EMNLP/IJCNLP, pp. 5498–5506 (2019)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Chen, N., Xia, Q., Zhou, X., Chen, W., Zhang, M. (2021). Emotion Classification with Explicit and Implicit Syntactic Information. In: Wang, L., Feng, Y., Hong, Y., He, R. (eds) Natural Language Processing and Chinese Computing. NLPCC 2021. Lecture Notes in Computer Science(), vol 13028. Springer, Cham. https://doi.org/10.1007/978-3-030-88480-2_48
Download citation
DOI: https://doi.org/10.1007/978-3-030-88480-2_48
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-88479-6
Online ISBN: 978-3-030-88480-2
eBook Packages: Computer ScienceComputer Science (R0)