GERP: A Personality-Based Emotional Response Generation Model
Source abstract
Abstract
It is important for chatbots to emotionally communicate with users. However, most emotional response generation models generate responses simply based on a specified emotion, neglecting the impacts of speaker’s personality on emotional expression. In this work, we propose a novel model named GERP to generate emotional responses based on the pre-defined personality. GERP simulates the emotion conversion process of humans during the conversation to make the chatbot more anthropomorphic. GERP adopts the OCEAN model to precisely define the chatbot’s personality. It can generate the response containing the emotion predicted based on the personality. Specifically, to select the most-appropriate response, a proposed beam evaluator was integrated into GERP. A Chinese sentiment vocabulary and a Chinese emotional response dataset were constructed to facilitate the emotional response generation task. The effectiveness and superiority of the proposed model over five baseline models was verified by the experiments.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Topic Modeling · Sentiment Analysis and Opinion Mining · Emotion and Mood Recognition
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
School of Software Engineering, Tongji University, Shanghai 200070, China
School of Humanities, Tongji University, Shanghai 200070, China
Funding
National Natural Science Foundation of China · Fundamental Research Funds for the Central Universities
References (36)
Show source-provided references
1. A Survey of Open Domain Dialogue Systems Based on Deep Learning
2. A Survey of Research on Text Emotional Dialogue Systems
3. Ghosh, S., Chollet, M., Laksana, E., Morency, L.P., and Scherer, S. (2017). Affect-lm: A neural language model for customizable affective text generation. arXiv.10.18653/v1/P17-1059 ↗
4. Yuan, J., Zhao, H., Zhao, Y., Cong, D., Qin, B., and Liu, T. (2017, January 8–12). Babbling-the hit-scir system for emotional conversation generation. Proceedings of the Natural Language Processing and Chinese Computing: 6th CCF International Conference, NLPCC 2017, Dalian, China.
5. Zhou, H., Huang, M., Zhang, T., Zhu, X., and Liu, B. (2018, January 2–7). Emotional chatting machine: Emotional conversation generation with internal and external memory. Proceedings of the AAAI Conference on Artificial Intelligence, New Orleans, LA, USA.10.1609/aaai.v32i1.11325 ↗
6. Asghar, N., Poupart, P., Hoey, J., Jiang, X., and Mou, L. (2018, January 26–29). Affective neural response generation. Proceedings of the Advances in Information Retrieval: 40th European Conference on IR Research, ECIR 2018, Grenoble, France.10.1007/978-3-319-76941-7_12 ↗
7. Kong, X., Li, B., Neubig, G., Hovy, E., and Yang, Y. (2019). An adversarial approach to high-quality, sentiment-controlled neural dialogue generation. arXiv.
8. Shen, L., and Feng, Y. (2020). CDL: Curriculum dual learning for emotion-controllable response generation. arXiv, arXiv:2005.00329.10.18653/v1/2020.acl-main.52 ↗
9. Topic-enhanced emotional conversation generation with attention mechanism10.1016/j.knosys.2018.09.006 ↗
10. Li, J., and Sun, X. (2018). A syntactically constrained bidirectional-asynchronous approach for emotional conversation generation. arXiv.10.18653/v1/D18-1071 ↗
11. Ma, Z., Dou, Z., Zhu, Y., Zhong, H., and Wen, J.R. (July, January Canada). One chatbot per person: Creating personalized chatbots based on implicit user profiles. Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval, Virtual Event.
12. Li, J., Galley, M., Brockett, C., Spithourakis, G.P., Gao, J., and Dolan, B. (2016). A persona-based neural conversation model. arXiv.10.18653/v1/P16-1094 ↗
13. Qian, Q., Huang, M., Zhao, H., Xu, J., and Zhu, X. (2017). Assigning personality/identity to a chatting machine for coherent conversation generation. arXiv.10.24963/ijcai.2018/595 ↗
14. Zhang, S., Dinan, E., Urbanek, J., Szlam, A., Kiela, D., and Weston, J. (2018). Personalizing dialogue agents: I have a dog, do you have pets too?. arXiv.10.18653/v1/P18-1205 ↗
15. Xing, Y., and Fernández, R. (2018). Automatic evaluation of neural personality-based chatbots. arXiv.10.18653/v1/W18-6524 ↗
16. Lessio, N., and Morris, A. (2020, January 11–14). Toward Design Archetypes for Conversational Agent Personality. Proceedings of the 2020 IEEE International Conference on Systems, Man, and Cybernetics (SMC), Toronto, ON, Canada.10.1109/SMC42975.2020.9283254 ↗
17. Emotional States and Personality Profiles in Conversational AI
18. Consistency of the factorial structures of personality ratings from different sources10.1037/h0057198 ↗
19. Social adaptation and five major factors of personality
20. Evidence for a three-factor theory of emotions10.1016/0092-6566(77)90037-X ↗
21. Ekman, P.E., and Davidson, R.J. (1994). The Nature of Emotion: Fundamental Questions, Oxford University Press.
22. Analysis of the big-five personality factors in terms of the PAD temperament model10.1080/00049539608259510 ↗
23. Relationships among three general approaches to personality description10.1080/00223980.1995.9914929 ↗
24. Wen, Z., Cao, J., Yang, R., Liu, S., and Shen, J. (2021). Automatically Select Emotion for Response via Personality-affected Emotion Transition. arXiv.10.18653/v1/2021.findings-acl.444 ↗
25. Song, Z., Zheng, X., Liu, L., Xu, M., and Huang, X.J. (August, January 28). Generating responses with a specific emotion in dialog. Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, Florence, Italy.
26. Bahdanau, D., Cho, K., and Bengio, Y. (2014). Neural machine translation by jointly learning to align and translate. arXiv.
27. Construction of emotional vocabulary ontology
28. Turney, P.D. (2002). Thumbs up or thumbs down? Semantic orientation applied to unsupervised classification of reviews. arXiv.10.3115/1073083.1073153 ↗
29. Wang, L., and Xia, R. (2017, January 7–11). Sentiment lexicon construction with representation learning based on hierarchical sentiment supervision. Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, Copenhagen, Denmark.10.18653/v1/D17-1052 ↗
30. Pennington, J., Socher, R., and Manning, C.D. (2014, January 25–29). Glove: Global vectors for word representation. Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), Doha, Qatar.10.3115/v1/D14-1162 ↗
31. Vinyals, O., and Le, Q. (2015). A neural conversational model. arXiv.
32. Yu, L., Zhang, W., Wang, J., and Yu, Y. (2017, January 4–9). Seqgan: Sequence generative adversarial nets with policy gradient. Proceedings of the AAAI Conference on Artificial Intelligence, San Francisco, CA, USA.10.1609/aaai.v31i1.10804 ↗
33. Papineni, K., Roukos, S., Ward, T., and Zhu, W.J. (2002, January 6–12). Bleu: A method for automatic evaluation of machine translation. Proceedings of the 40th annual meeting of the Association for Computational Linguistics, Philadelphia, PA, USA.10.3115/1073083.1073135 ↗
34. Goodfellow, I.J., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courville, A., and Bengio, Y. (2014). Generative Adversarial Networks. arXiv.
35. A model of inductive bias learning10.1613/jair.731 ↗
36. Reinforcement learning: A survey10.1613/jair.301 ↗