Abstract
The purpose of empathetic dialogue generation is to fully understand the speakers’ emotional needs in dialogues and to generate appropriate empathetic responses. Existing works mainly focus on the overall coarse-grained emotion of the context while neglecting different utterances’ fine-grained emotions, which leads to the inability to detect the speakers’ fine-grained emotional changes during a conversation. However, in real-life dialogue scenarios, the speaker usually carries an initial emotional state that changes continuously during the conversation. Therefore, understanding a series of emotional states can help to better understand speakers’ emotions and generate empathetic responses. To address this issue, we propose a Multi-Scale Emotional flow model called MuSE, which simulates speakers’ emotional flow. First, we introduce a fine-grained expansion strategy to transform context into an emotional flow graph that combines multi-scale coarse and fine-grained information. This emotional flow graph captures speakers’ constant emotional changes at each turn of a conversation. And then, the emotion node and the situational node are introduced to the emotional flow graph respectively in order to extend the speakers’ initial emotion into the ensuing conversation. Finally, we conduct experiments on the public EMPATHETIC DIALOGUES dataset. The experimental results demonstrate that the MuSE model achieves superior performance under both automatic evaluation and human evaluation metrics compared with the existing baseline models. Our code is available at https://github.com/DericZhao/MuSE.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Bosselut, A., Rashkin, H., Sap, M., Malaviya, C., Celikyilmaz, A., Choi, Y.: Comet: commonsense transformers for automatic knowledge graph construction. In: Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pp. 4762–4779 (2019)
Gao, J., et al.: Improving empathetic response generation by recognizing emotion cause in conversations. In: Findings of the association for computational linguistics: EMNLP 2021 (2021)
Ghosal, D., Majumder, N., Poria, S., Chhaya, N., Gelbukh, A.: Dialoguegcn: A graph convolutional neural network for emotion recognition in conversation. In: Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pp. 154–164 (2019)
Hartmann, J.: Emotion english distilroberta-base (2022). https://huggingface.co/j-hartmann/emotion-english-distilroberta-base/
Keskin, S.C.: From what isn’t empathy to empathic learning process. Procedia Soc. Behav. Sci. 116, 4932–4938 (2014)
Kim, H., Kim, B., Kim, G.: Perspective-taking and pragmatics for generating empathetic responses focused on emotion causes. In: Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pp. 2227–2240 (2021)
Kipf, T.N., Welling, M.: Semi-supervised classification with graph convolutional networks. In: International Conference on Learning Representations (2017). https://openreview.net/forum?id=SJU4ayYgl
Li, J., Galley, M., Brockett, C., Gao, J., Dolan, W.B.: A diversity-promoting objective function for neural conversation models. In: Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pp. 110–119 (2016)
Li, Q., Chen, H., Ren, Z., Ren, P., Tu, Z., Chen, Z.: Empdg: Multi-resolution interactive empathetic dialogue generation. In: Proceedings of the 28th International Conference on Computational Linguistics, pp. 4454–4466 (2020)
Lin, C.Y.: Rouge: A package for automatic evaluation of summaries. In: Text summarization branches out, pp. 74–81 (2004)
Lin, Z., Madotto, A., Shin, J., Xu, P., Fung, P.: Moel: mixture of empathetic listeners. In: Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pp. 121–132 (2019)
Majumder, N., et al.: Mime: Mimicking emotions for empathetic response generation. In: Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 8968–8979 (2020)
Paiva, A., Leite, I., Boukricha, H., Wachsmuth, I.: Empathy in virtual agents and robots: a survey. ACM Trans. Interact. Intell. Syst. (TiiS) 7(3), 1–40 (2017)
Pang, J., Xu, H., Song, S., Zou, B., He, X.: Mfdg: A multi-factor dialogue graph model for dialogue intent classification. In: Machine Learning and Knowledge Discovery in Databases: European Conference, ECML PKDD 2022, Grenoble, France, September 19–23, 2022, Proceedings, Part II. pp. 691–706. Springer (2023). https://doi.org/10.1007/978-3-031-26390-3_40
Papineni, K., Roukos, S., Ward, T., Zhu, W.J.: Bleu: a method for automatic evaluation of machine translation. In: Proceedings of the 40th annual meeting of the Association for Computational Linguistics, pp. 311–318 (2002)
Peng, W., Hu, Y., Xing, L., Xie, Y., Sun, Y., Li, Y.: Control globally, understand locally: A global-to-local hierarchical graph network for emotional support conversation. In: Raedt, L.D. (ed.) Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence, IJCAI 2022, Vienna, Austria, 23–29 July 2022, pp. 4324–4330. ijcai.org (2022). https://doi.org/10.24963/ijcai.2022/600, https://doi.org/10.24963/ijcai.2022/600
Pennington, J., Socher, R., Manning, C.D.: Glove: Global vectors for word representation. In: Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 1532–1543 (2014)
Qin, L., Li, Z., Che, W., Ni, M., Liu, T.: Co-gat: A co-interactive graph attention network for joint dialog act recognition and sentiment classification. In: Proceedings of the AAAI Conference on Artificial Intelligence. vol. 35, pp. 13709–13717 (2021)
Rashkin, H., Smith, E.M., Li, M., Boureau, Y.L.: Towards empathetic open-domain conversation models: A new benchmark and dataset. In: Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pp. 5370–5381 (2019)
Sabour, S., Zheng, C., Huang, M.: Cem: Commonsense-aware empathetic response generation. In: Proceedings of the AAAI Conference on Artificial Intelligence. vol. 36, pp. 11229–11237 (2022)
Sap, M., et al.: Atomic: An atlas of machine commonsense for if-then reasoning. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 33, pp. 3027–3035 (2019)
Savani, B.: Bert base go emotion. https://huggingface.co/bhadresh-savani/bert-base-go-emotion (2021)
Tu, Q., Li, Y., Cui, J., Wang, B., Wen, J.R., Yan, R.: Misc: A mixed strategy-aware model integrating comet for emotional support conversation. In: Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 308–319 (2022)
Vaswani, A., et al.: Attention is all you need. Adv. Neural Inform. Process. Syst. 30 (2017)
Wang, J., Cheng, Y., Li, W.: Care: Causality reasoning for empathetic responses by conditional graph generation. In: Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, EMNLP 2022 (2022)
Wang, J., Li, W., Lin, P., Mu, F.: Empathetic response generation through graph-based multi-hop reasoning on emotional causality. Knowl.-Based Syst. 233, 107547 (2021)
Wang, L., et al.: Empathetic dialogue generation via sensitive emotion recognition and sensible knowledge selection. In: Findings of the Association for Computational Linguistics: EMNLP 2022, pp. 4634–4645. Association for Computational Linguistics, Abu Dhabi, United Arab Emirates (Dec 2022), https://aclanthology.org/2022.findings-emnlp.340
Zhang, T., Kishore, V., Wu, F., Weinberger, K.Q., Artzi, Y.: Bertscore: Evaluating text generation with bert. In: International Conference on Learning Representations (2020). https://openreview.net/forum?id=SkeHuCVFDr
Zhao, W., Zhao, Y., Lu, X.: Cauain: Causal aware interaction network for emotion recognition in conversations. In: Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence, IJCAI, pp. 4524–4530 (2022)
Acknowledgments
This work is supported by the National Natural Science Foundation of China (61672144, 61872072).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Ethics declarations
Ethics Statement
We do not observe direct ethical and security issues arising from the emotional dialogue itself. The public dataset used in this paper may contain user privacy, but it has been made harmless in the earliest published dataset papers.
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Zhao, D., Han, D., Yuan, Y., Wang, C., Song, S. (2023). MuSE: A Multi-scale Emotional Flow Graph Model for Empathetic Dialogue Generation. In: Koutra, D., Plant, C., Gomez Rodriguez, M., Baralis, E., Bonchi, F. (eds) Machine Learning and Knowledge Discovery in Databases: Research Track. ECML PKDD 2023. Lecture Notes in Computer Science(), vol 14170. Springer, Cham. https://doi.org/10.1007/978-3-031-43415-0_29
Download citation
DOI: https://doi.org/10.1007/978-3-031-43415-0_29
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-43414-3
Online ISBN: 978-3-031-43415-0
eBook Packages: Computer ScienceComputer Science (R0)