Abstract
Empathetic conversation generation intends to endow the open-domain conversation model with the capability for understanding, interpreting, and expressing emotion. Humans express not only their emotional state but also the stimulus that caused the emotion, i.e., emotion cause, during a conversation. Most existing approaches focus on emotion modeling, emotion recognition and prediction, and emotion fusion generation, ignoring the critical aspect of the emotion cause, which results in generating responses with irrelevant content. Emotion cause can help the model understand the user’s emotion and make the generated responses more content-relevant. However, using the emotion cause to enhance empathetic conversation generation is challenging. Firstly, the model needs to accurately identify the emotion cause without large-scale labeled data. Second, the model needs to effectively integrate the emotion cause into the generation process. To this end, we present an emotion cause extractor using a semi-supervised training method and an empathetic conversation generator using a biased self-attention mechanism to overcome these two issues. Experimental results indicate that our proposed emotion cause extractor improves recall scores markedly compared to the baselines, and the proposed empathetic conversation generator has superior performance and improves the content-relevance of generated responses.
M. Zou and R. Pan–Equal contribution.
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
References
Bao, Y., Ma, Q., Wei, L., Zhou, W., Hu, S.: Multi-granularity semantic aware graph model for reducing position bias in emotion cause pair extraction. In: Findings of the Association for Computational Linguistics: the 60th Conference of the Association for Computational Linguistics (ACL), Dublin, Ireland, pp. 1203–1213. Association for Computational Linguistics (2022)
Chen, Y., Lee, S.Y.M., Li, S., Huang, C.: Emotion cause detection with linguistic constructions. In: Proceedings of the 23rd International Conference on Computational Linguistics (COLING), Beijing, China, pp. 179–187. Tsinghua University Press (2010)
Firdaus, M., Chauhan, H., Ekbal, A., Bhattacharyya, P.: More the merrier: towards multi-emotion and intensity controllable response generation. In: Proceedings of the 35th AAAI Conference on Artificial Intelligence (AAAI), pp. 12821–12829. AAAI Press, Virtual Event (2021)
Gao, J., et al.: Improving empathetic response generation by recognizing emotion cause in conversations. In: Findings of the Association for Computational Linguistics: the 26th Conference on Empirical Methods in Natural Language Processing (EMNLP), Punta Cana, Dominican Republic, pp. 807–819. Association for Computational Linguistics (Virtual Event) (2021)
Huang, M., Zhu, X., Gao, J.: Challenges in building intelligent open-domain dialog systems. ACM Trans. Inf. Syst. 38(3), 1–32 (2020)
Kim, H., Kim, B., Kim, G.: Perspective-taking and pragmatics for generating empathetic responses focused on emotion causes. In: Proceedings of the 26th Conference on Empirical Methods in Natural Language Processing (EMNLP), Punta Cana, Dominican Republic, pp. 2227–2240. Association for Computational Linguistics (Virtual Event) (2021)
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, Los Angeles, USA, pp. 45–53. Association for Computational Linguistics (2010)
Lewis, M., et al.: BART: denoising sequence-to-sequence pre-training for natural language generation, translation, and comprehension. In: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics (ACL), pp. 7871–7880. Association for Computational Linguistics, Online (2020)
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 (COLING), Barcelona, Spain, pp. 4454–4466. International Committee on Computational Linguistics (Online) (2020)
Lin, Z., Madotto, A., Shin, J., Xu, P., Fung, P.: MoEL: mixture of empathetic listeners. In: Proceedings of the 24th Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), Hong Kong, China, pp. 121–132. Association for Computational Linguistics (2019)
Liu, Y., et al.: RoBERTa: a robustly optimized BERT pretraining approach. arXiv preprint arXiv:1907.11692 (2019)
Majumder, N., et al.: MIME: mimicking emotions for empathetic response generation. In: Proceedings of the 25th Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 8968–8979. Association for Computational Linguistics, Online (2020)
Martinovski, B., Traum, D.: The error is the clue: breakdown in human-machine interaction. In: Proceedings of the International Speech Communication Association Tutorial and Research Workshop on Error Handling in Spoken Dialogue Systems, Château-d’Oex, Vaud, Switzerland, pp. 11–16. ISCA Archive (2003)
Prendinger, H., Ishizuka, M.: The empathic companion: a character-based interface that addresses users’ affective states. Appl. Artif. Intell. 19(3–4), 267–285 (2005)
Prendinger, H., Mori, J., Ishizuka, M.: Using human physiology to evaluate subtle expressivity of a virtual quizmaster in a mathematical game. Int. J. Hum. Comput. Stud. 62(2), 231–245 (2005)
Radford, A., et al.: Language models are unsupervised multitask learners. OpenAI blog 1(8), 9 (2019)
Rashkin, H., Smith, E.M., Li, M., Boureau, Y.: Towards empathetic open-domain conversation models: a new benchmark and dataset. In: Proceedings of the 57th Conference of the Association for Computational Linguistics (ACL), Florence, Italy, pp. 5370–5381. Association for Computational Linguistics (2019)
Sabour, S., Zheng, C., Huang, M.: CEM: commonsense-aware empathetic response generation. In: Proceedings of the 36th AAAI Conference on Artificial Intelligence (AAAI), pp. 11229–11237. AAAI Press, Virtual Event (2022)
Serban, I.V., Lowe, R., Charlin, L., Pineau, J.: Generative deep neural networks for dialogue: a short review. arXiv preprint arXiv:1611.06216 (2016)
Shen, L., Feng, Y.: CDL: curriculum dual learning for emotion-controllable response generation. In: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics (ACL), pp. 556–566. Association for Computational Linguistics, Online (2020)
Shen, L., Zhang, J., Ou, J., Zhao, X., Zhou, J.: Constructing emotional consensus and utilizing unpaired data for empathetic dialogue generation. In: Findings of the Association for Computational Linguistics: the 26th Conference on Empirical Methods in Natural Language Processing (EMNLP), Punta Cana, Dominican Republic, pp. 3124–3134. Association for Computational Linguistics (Virtual Event) (2021)
Shin, J., Xu, P., Madotto, A., Fung, P.: Generating empathetic responses by looking ahead the user’s sentiment. In: Proceedings of the 45th International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Barcelona, Spain, pp. 7989–7993. IEEE (2020)
Song, Z., Zheng, X., Liu, L., Xu, M., Huang, X.: Generating responses with a specific emotion in dialog. In: Proceedings of the 57th Conference of the Association for Computational Linguistics (ACL), Florence, Italy, pp. 3685–3695. Association for Computational Linguistics (2019)
Turcan, E., Wang, S., Anubhai, R., Bhattacharjee, K., Al-Onaizan, Y., Muresan, S.: Multi-task learning and adapted knowledge models for emotion-cause extraction. In: Findings of the Association for Computational Linguistics: The Joint Conference of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (ACL-IJCNLP), pp. 3975–3989. Association for Computational Linguistics, Online Event (2021)
Vaswani, A., et al.: Attention is all you need. In: Proceedings of the 30th Conference on Annual Conference Neural Information Processing Systems (NeurIPS), Long Beach, USA, pp. 5998–6008. MIT Press (2017)
Welivita, A., Pu, P.: A taxonomy of empathetic response intents in human social conversations. In: Proceedings of the 28th International Conference on Computational Linguistics (COLING), Barcelona, Spain, pp. 4886–4899. International Committee on Computational Linguistics (Online) (2020)
Wolf, T., Sanh, V., Chaumond, J., Delangue, C.: TransferTransfo: a transfer learning approach for neural network based conversational agents. arXiv preprint arXiv:1901.08149 (2019)
Xia, R., Ding, Z.: Emotion-cause pair extraction: a new task to emotion analysis in texts. In: Proceedings of the 57th Conference of the Association for Computational Linguistics (ACL), Florence, Italy, pp. 1003–1012. Association for Computational Linguistics (2019)
Zhang, T., Kishore, V., Wu, F., Weinberger, K.Q., Artzi, Y.: BERTScore: evaluating text generation with BERT. In: Proceedings of the 8th International Conference on Learning Representations (ICLR), Addis Ababa, Ethiopia. OpenReview.net (2020)
Zheng, C., Liu, Y., Chen, W., Leng, Y., Huang, M.: CoMAE: a multi-factor hierarchical framework for empathetic response generation. In: Findings of the Association for Computational Linguistics: The Joint Conference of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (ACL-IJCNLP), pp. 813–824. Association for Computational Linguistics, Online (2021)
Zhou, H., Huang, M., Zhang, T., Zhu, X., Liu, B.: Emotional chatting machine: emotional conversation generation with internal and external memory. In: Proceedings of the 32nd AAAI Conference on Artificial Intelligence (AAAI), New Orleans, USA, pp. 730–739. AAAI Press (2018)
Zhou, L., Gao, J., Li, D., Shum, H.: The design and implementation of Xiaoice, an empathetic social chatbot. Comput. Linguist. 46(1), 53–93 (2020)
Acknowledgements
This work was supported by the Joint Project of Tianjin University-Bohai Bank Joint Laboratory for Artificial Intelligence Technology Innovation and Bayescom.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Zou, M., Pan, R., Zhang, S., Zhang, X. (2022). Using Extracted Emotion Cause to Improve Content-Relevance for Empathetic Conversation Generation. In: Sun, M., et al. Chinese Computational Linguistics. CCL 2022. Lecture Notes in Computer Science(), vol 13603. Springer, Cham. https://doi.org/10.1007/978-3-031-18315-7_8
Download citation
DOI: https://doi.org/10.1007/978-3-031-18315-7_8
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-18314-0
Online ISBN: 978-3-031-18315-7
eBook Packages: Computer ScienceComputer Science (R0)