ABSTRACT
Empathy plays a pivotal role in human communication, and thus, it is an essential capability that any human-centered dialogue system should possess. Early research on empathetic response generation often focused on directly capturing the emotional state of the context using fixed emotion labels. However, the logical aspects exhibited in human conversations heavily rely on experiential and knowledge-based resources within the brain. This implies that whether the aim is to acquire more nuanced emotional states or to generate responses enriched with comprehensive information, the incorporation of external knowledge as supplementary information in empathetic dialogue systems is imperative. In response to this challenge, we propose a novel approach for extracting external knowledge. This is achieved by designing two components: a fine-grained knowledge graph constructed using the context and an external knowledge base, and coarse-grained knowledge acquisition based on COMET. These two scales of knowledge are then integrated with the context using methods like context refinement. This not only make the model to gain a deeper understanding of the user's context but also enhances the expression of empathy in the dialogue system. We conducted extensive experiments on the EMPATHETICDIALOGUES dataset and demonstrated the superiority of our approach over the baseline model.
CCS CONCEPTS • Computing methodologies∼Artificial intelligence∼Natural language processing∼Discourse, dialogue and pragmatics
- Zandie, R., & Mahoor, M. H. (2020). Emptransfo: A multi-head transformer architecture for creating empathetic dialog systems. arXiv preprint arXiv:2003.02958.Google Scholar
- Welivita, A., & Pu, P. (2020). A taxonomy of empathetic response intents in human social conversations. arXiv preprint arXiv:2012.04080.Google Scholar
- Zheng, C., Liu, Y., Chen, W., Leng, Y., & Huang, M. (2021). Comae: A multi-factor hierarchical framework for empathetic response generation. arXiv preprint arXiv:2105.08316.Google Scholar
- Sabour, S., Zheng, C., & Huang, M. (2022, June). Cem: Commonsense-aware empathetic response generation. In Proceedings of the AAAI Conference on Artificial Intelligence (Vol. 36, No. 10, pp. 11229-11237).Google Scholar
- Veličković, P., Cucurull, G., Casanova, A., Romero, A., Lio, P., & Bengio, Y. (2017). Graph attention networks. arXiv preprint arXiv:1710.10903.Google Scholar
- Majumder, N., Hong, P., Peng, S., Lu, J., Ghosal, D., Gelbukh, A., ... & Poria, S. (2020). MIME: MIMicking emotions for empathetic response generation. arXiv preprint arXiv:2010.01454.Google Scholar
- Jiang, S., Ren, P., Monz, C., & de Rijke, M. (2019, May). Improving neural response diversity with frequency-aware cross-entropy loss. In The World Wide Web Conference (pp. 2879-2885).Google Scholar
- Lin, Z., Madotto, A., Shin, J., Xu, P., & Fung, P. (2019). Moel: Mixture of empathetic listeners. arXiv preprint arXiv:1908.07687.Google Scholar
- Li, Q., Chen, H., Ren, Z., Ren, P., Tu, Z., & Chen, Z. (2019). EmpDG: Multiresolution interactive empathetic dialogue generation. arXiv preprint arXiv:1911.08698.Google Scholar
- Rashkin, H., Smith, E. M., Li, M., & Boureau, Y. L. (2018). Towards empathetic open-domain conversation models: A new benchmark and dataset. arXiv preprint arXiv:1811.002.Google Scholar
Index Terms
- Mixed Knowledge-enhance Empathetic Dialogue Generation
Recommendations
Fine-Grained Knowledge Enhancement for Empathetic Dialogue Generation
Advanced Data Mining and ApplicationsAbstractAn engaging dialogue system is supposed to generate empathetic responses, which requires a cognitive understanding of users’ situations and an affective perception of their emotions. Most of the existing work only focuses on modeling the latter, ...
Improving Empathetic Dialogue Generation with Semantics Decoupling
IJCKG '22: Proceedings of the 11th International Joint Conference on Knowledge GraphsEmpathetic dialogue generation is dedicated to generating responses to empathize with users by perceiving and understanding context emotions and dialogue situations. Existing works typically emphasize that an empathetic response needs to express ...
A Speech Understanding and Dialog System with a Homogeneous Linguistic Knowledge Base
This article presents the speech understanding and dialog system EVAR. All levels of linguistic knowledge are used both to control the analysis process and for the interpretation of an utterance. All kinds of knowledge are integrated in a homogeneous ...
Comments