PersonaGAN: Personalized Response Generation via Generative Adversarial Networks

Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 12112)


Current personalized dialogue systems do not thoroughly model the context to capture richer information, and still tend to generate short, incoherent and boring responses. To tackle these problems, in this paper we propose a generative adversarial network model PersonaGAN for personalized dialogue generation. In addition to hierarchical modeling of context, we introduce a speaker-aware encoder in the generator to capture richer context information. Besides, we apply adversarial training to personalized dialogue generation task via using a transformer-based matching model as discriminator. The discriminator could give higher rewards for the responses which look like human written and lower rewards for machine generated responses. Such training strategy encourages the generator to generate responses which are grammatically fluent, informative and logically coherent with context. We evaluate the proposed model on a public available dataset and yield promising results on both automatic and human evaluation, which show that our model can generate more coherent and personalized responses while ensuring fluency.


Response generation Personalization Generative adversarial network 



The work was supported by the National Key R&D Program of China under grant 2018YFB1004700, National Natural Science Foundation of China (61872074, 61772122), and the CETC Joint fund.


  1. 1.
    Goodfellow, I.J., et al.: Generative adversarial nets. In: NIPS, pp. 2672–2680 (2014)Google Scholar
  2. 2.
    Goyal, A., Lamb, A., Zhang, Y., Zhang, S., Courville, A.C., Bengio, Y.: Professor forcing: A new algorithm for training recurrent networks. In: NIPS, pp. 4601–4609 (2016)Google Scholar
  3. 3.
    Kusner, M.J., Hernández-Lobato, J.M.: GANS for sequences of discrete elements with the Gumbel-softmax distribution. CoRR abs/1611.04051 (2016)Google Scholar
  4. 4.
    Li, J., Galley, M., Brockett, C., Gao, J., Dolan, B.: A diversity-promoting objective function for neural conversation models. In: NAACL, pp. 110–119 (2016)Google Scholar
  5. 5.
    Li, J., Galley, M., Brockett, C., Spithourakis, G.P., Gao, J., Dolan, W.B.: A persona-based neural conversation model. In: ACL, pp. 994–1003 (2016)Google Scholar
  6. 6.
    Li, J., Monroe, W., Shi, T., Jean, S., Ritter, A., Jurafsky, D.: Adversarial learning for neural dialogue generation. In: EMNLP, pp. 2157–2169 (2017)Google Scholar
  7. 7.
    Lian, R., Xie, M., Wang, F., Peng, J., Wu, H.: Learning to select knowledge for response generation in dialog systems. In: IJCAI, pp. 5081–5087 (2019)Google Scholar
  8. 8.
    Majumder, N., Poria, S., Hazarika, D., Mihalcea, R., Gelbukh, A.F., Cambria, E.: DialogueRNN: an attentive RNN for emotion detection in conversations. In: AAAI, pp. 6818–6825 (2019)Google Scholar
  9. 9.
    Pennington, J., Socher, R., Manning, C.D.: Glove: global vectors for word representation. In: EMNLP, pp. 1532–1543 (2014)Google Scholar
  10. 10.
    Qian, Q., Huang, M., Zhao, H., Xu, J., Zhu, X.: Assigning personality/profile to a chatting machine for coherent conversation generation. In: IJCAI, pp. 4279–4285 (2018)Google Scholar
  11. 11.
    Serban, I.V., Sordoni, A., Bengio, Y., Courville, A.C., Pineau, J.: Building end-to-end dialogue systems using generative hierarchical neural network models. In: AAAI, pp. 3776–3784 (2016)Google Scholar
  12. 12.
    Shang, L., Lu, Z., Li, H.: Neural responding machine for short-text conversation. In: ACL, pp. 1577–1586 (2015)Google Scholar
  13. 13.
    Song, H., Zhang, W., Cui, Y., Wang, D., Liu, T.: Exploiting persona information for diverse generation of conversational responses. In: IJCAI, pp. 5190–5196 (2019)Google Scholar
  14. 14.
    Soria-Comas, J., Domingo-Ferrer, J.: Big data privacy: challenges to privacy principles and models. Data Sci. Eng. 1(1), 21–28 (2016). Scholar
  15. 15.
    Sutskever, I., Vinyals, O., Le, Q.V.: Sequence to sequence learning with neural networks. In: NIPS, pp. 3104–3112 (2014)Google Scholar
  16. 16.
    Vaswani, A., et al.: Attention is all you need. In: NIPS, pp. 5998–6008 (2017)Google Scholar
  17. 17.
    Weizenbaum, J.: ELIZA - a computer program for the study of natural language communication between man and machine. Commun. ACM 9(1), 36–45 (1966)CrossRefGoogle Scholar
  18. 18.
    Williams, J.D., Young, S.J.: Partially observable Markov decision processes for spoken dialog systems. Comput. Speech Lang. 21(2), 393–422 (2007)CrossRefGoogle Scholar
  19. 19.
    Xing, C., Wu, Y., Wu, W., Huang, Y., Zhou, M.: Hierarchical recurrent attention network for response generation. In: AAAI, pp. 5610–5617 (2018)Google Scholar
  20. 20.
    Xu, J., Ren, X., Lin, J., Sun, X.: Diversity-promoting GAN: a cross-entropy based generative adversarial network for diversified text generation. In: EMNLP, pp. 3940–3949 (2018)Google Scholar
  21. 21.
    Yavuz, S., Rastogi, A., Chao, G., Hakkani-Tür, D.: Deepcopy: grounded response generation with hierarchical pointer networks. CoRR abs/1908.10731 (2019)Google Scholar
  22. 22.
    Yu, L., Zhang, W., Wang, J., Yu, Y.: SeqGan: sequence generative adversarial nets with policy gradient. In: AAAI, pp. 2852–2858 (2017)Google Scholar
  23. 23.
    Zhang, S., Dinan, E., Urbanek, J., Szlam, A., Kiela, D., Weston, J.: Personalizing dialogue agents: i have a dog, do you have pets too? In: ACL, pp. 2204–2213 (2018)Google Scholar
  24. 24.
    Zheng, Y., Chen, G., Huang, M., Liu, S., Zhu, X.: Personalized dialogue generation with diversified traits. CoRR abs/1901.09672 (2019)Google Scholar
  25. 25.
    Zhu, Q., Cui, L., Zhang, W., Wei, F., Liu, T.: Retrieval-enhanced adversarial training for neural response generation. In: ACL, pp. 3763–3773 (2019)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2020

Authors and Affiliations

  1. 1.School of Computer Science and EngineeringNortheastern UniversityShenyangChina

Personalised recommendations