Abstract
Emotion cause detection (ECD) that aims to extract the trigger event of a certain emotion explicitly expressed in text has become a hot topic in natural language processing. However, the performance of existing models all suffers from inadequate sentiment information fusion and the limited size of corpora. In this paper, we propose a novel model to combine external sentiment knowledge for ECD task, namely ExSenti-ECD, to try to solve these problems. First, in order to fully fuse sentiment information, we utilize a sentiment-specific embedding method to encode external sentiment knowledge contained in emotional text into word vectors. Meanwhile a new sentiment polarity corpus is merged from multiple corpora. Then, a pre-training method is adopted to mitigate the impact of the limitation of annotated data for ECD task instead of simply expanding samples. Furthermore, we apply attention mechanism to take emotional context into consideration based on the observation that the context around emotion keywords can provide emotion cause clues. Experimental results show that our model greatly outperforms the state-of-the-art baseline models.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Lee, S.Y.M., Chen, Y., Li, S., Huang, C.-R.: Emotion cause events: corpus construction and analysis. In: LREC. ELRA, Valletta (2010)
Chen, Y., Lee, S.Y.M., Li, S., Zhou, G., Huang, C.-R.: Emotion cause detection with linguistic constructions. In: Proceedings of the 23rd International Conference on Computational Linguistics, pp. 179–187. Coling 2010 Organizing Committee, Beijing (2010)
Lee, S.Y.M., Chen, Y., Huang, C.-R.: A text-driven rule-based system for emotion cause detection. In: Proceedings of the NAACL HLT 2010 Workshop on Computational Approaches to Analysis and Generation of Emotion in Text, pp. 45–53. Association for Computational Linguistics, Los Angeles (2010)
Gui, L., Yuan, L., Xu, R., Liu, B., Lu, Q., Zhou, Y.: Emotion cause detection with linguistic construction in Chinese Weibo text. In: Zong, C., Nie, J.Y., Zhao, D., Feng, Y. (eds.) Natural Language Processing and Chinese Computing. Communications in Computer and Information Science, vol. 496, pp. 457–464. Springer, Heidelberg (2014). https://doi.org/10.1007/978-3-662-45924-9_42
Gui, L., Wu, D., Xu, R., Lu, Q., Zhou, Y.: Event-driven emotion cause extraction with corpus construction. In: EMNLP, pp. 1639–1649. ACL, Austin (2016)
Gui, L., et al.: A question answering approach for emotion cause extraction. In: EMNLP, pp. 1593–1602. ACL, Copenhagen (2017)
Li, X., Song, K., Feng, S., Wang, D., Zhang, Y.: A co-attention neural network model for emotion cause analysis with emotional context awareness. In: Conference on EMNLP, pp. 4752–4757. ACL, Brussels (2018)
Chen, Y., Hou, W., Cheng, X., Li, S.: Joint learning for emotion classification and emotion cause detection. In: EMNLP, pp. 646–651. ACl, Brussels (2018)
Neviarouskaya, A., Aono, M.: Extracting causes of emotions from text. In: IJCNLP, pp. 932–936. AFNLP, Nagoya (2013)
Russo, I., Caselli, T., Rubino, F., Boldrini, E.: EMOCause: an easy-adaptable approach to extract emotion cause contexts. In: Proceedings of the 2nd Workshop on Computational Approaches to Subjectivity and Sentiment Analysis, pp. 153–160. Association for Computational Linguistics, Portland (2011)
Ghazi, D., Inkpen, D., Szpakowicz, S.: Detecting emotion stimuli in emotion-bearing sentences. In: Gelbukh, A. (ed.) CICLing 2015. LNCS, vol. 9042, pp. 152–165. Springer, Cham (2015). https://doi.org/10.1007/978-3-319-18117-2_12
Cheng, X., Chen, Y., Cheng, B., Li, S., Zhou, G.: An emotion cause corpus for Chinese microblogs with multiple-user structures. ACM Trans. Asian Low-Resour. Lang. Inf. Process., 1–19 (2017)
Tang, D., Wei, F., Yang, N., Zhou, M., Liu, T., Qin, B.: Learning sentiment-specific word embedding for Twitter sentiment classification. In: Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics, pp. 1555–1565. ACL, Baltimore (2014)
Bespalov, D., Bing, B., Qi, Y., Shokoufandeh, A.: Sentiment classification based on supervised latent n-gram analysis. In: ACM International Conference on Information (2011)
Labutov, I., Lipson, H.: Re-embedding words. In: Proceedings of the 51st Annual Meeting of ACL, pp. 489–493. ACL, Sofia (2013)
Maas, A., Daly, R., Pham, P., Huang, D., Ng, A., Potts, C.: Learning word vectors for sentiment analysis. In: 49th Annual Meeting of ACL, pp. 142–150. ACL, Portland (2011)
Luo, K., Deng, Z.-H., Yu, H., Wei, L.: JEAM: a novel model for cross-domain sentiment classification based on emotion analysis. In: Proceedings of the 2015 Conference on EMNLP, pp. 2503–2508. ACL, Lisbon (2015)
Zhu, S., Li, S., Chen, Y., Zhou, G.: Corpus fusion for emotion classification. In: The 26th COLING, pp. 3287–3297. The COLING 2016 Organizing Committee, Osaka (2016)
Zhang, L., Wu, L., Li, S., Wang, Z., Zhou, G.: Cross-lingual emotion classification with auxiliary and attention neural networks. In: Zhang, M., Ng, V., Zhao, D., Li, S., Zan, H. (eds.) NLPCC 2018. LNCS (LNAI), vol. 11108, pp. 429–441. Springer, Cham (2018). https://doi.org/10.1007/978-3-319-99495-6_36
Mohtarami, M., Lan, M., Tan, C.: Probabilistic sense sentiment similarity through hidden emotions. In: The 51st ACL, pp. 983–992. ACL, Sofia (2013)
Gao, W., Li, S., Lee, S.Y.M., Zhou, G., Huang, C.R.: Joint learning on sentiment and emotion classification. In: Proceedings of the 22nd ACM International Conference on Information & Knowledge Management, pp. 1505–1508. ACM (2013)
Ou, G., et al.: Exploiting community emotion for microblog event detection. In: EMNLP, pp. 1159–1168. ACL, Doha (2014)
Devlin, J., Chang, M., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding (2018)
Ashish, V., et al.: Attention is all you need. In: Advances in Neural Information Processing, pp. 6000–6010 (2017)
Mikolov, T., Sutskever, I., Chen, K.: Distributed representations of words and phrases and their compositionality. In: Advances in Neural Information Processing Systems, pp. 3111–3119 (2013)
Mikolov, T., Corrado, G., Chen, K., Dean, J.: Efficient estimation of word representations in vector space, pp. 1–12 (2013)
Pennington, J., Socher, R., Manning, C.: Glove: global vectors for word representation. In: EMNLP, pp. 1532–1543 (2014)
Acknowledgement
This work was supported by the National Natural Science Foundation of China (Grant No. 61671064) and National Key Research & Development Program (Grant No. 2018YFC0831700).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
Hu, J., Shi, S., Huang, H. (2019). Combining External Sentiment Knowledge for Emotion Cause Detection. In: Tang, J., Kan, MY., Zhao, D., Li, S., Zan, H. (eds) Natural Language Processing and Chinese Computing. NLPCC 2019. Lecture Notes in Computer Science(), vol 11838. Springer, Cham. https://doi.org/10.1007/978-3-030-32233-5_55
Download citation
DOI: https://doi.org/10.1007/978-3-030-32233-5_55
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-32232-8
Online ISBN: 978-3-030-32233-5
eBook Packages: Computer ScienceComputer Science (R0)
