A Hybrid Framework of Emotion-Aware Seq2Seq Model for Emotional Conversation Generation

  • Xiaohe Li
  • Jiaqing Liu
  • Weihao Zheng
  • Xiangbo Wang
  • Yutao Zhu
  • Zhicheng DouEmail author
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11966)


This paper describes RUCIR’s system in NTCIR-14 Short Text Conversation (STC) Chinese Emotional Conversation Generation (CECG) subtask. In our system, we use the Attention-based Sequence-to-Sequence (Seq2Seq) method as our basic structure to generate emotional responses. This paper introduces (1) an emotion-aware Seq2Seq model and (2) several features to boost the performance of emotion consistency. Official results show that our model performs the best in terms of the overall results across the five given emotion categories.


Emotional Conversation Generation Sequence to sequence model Attention mechanism Copy mechanism 



Zhicheng Dou is the corresponding author. This work was supported by National Key R&D Program of China No. 2018YFC0830703, National Natural Science Foundation of China No. 61872370, and the Fundamental Research Funds for the Central Universities, and the Research Funds of Renmin University of China No. 2112018391.


  1. 1.
    Bahdanau, D., Cho, K., Bengio, Y.: Neural machine translation by jointly learning to align and translate. arXiv preprint arXiv:1409.0473 (2014)
  2. 2.
    Cho, K., et al.: Learning phrase representations using RNN encoder-decoder for statistical machine translation. arXiv preprint arXiv:1406.1078 (2014)
  3. 3.
    Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735–1780 (1997)CrossRefGoogle Scholar
  4. 4.
    Li, J., Galley, M., Brockett, C., Gao, J., Dolan, B.: A diversity-promoting objective function for neural conversation models. arXiv preprint arXiv:1510.03055 (2015)
  5. 5.
    Luong, M.T., Pham, H., Manning, C.D.: Effective approaches to attention-based neural machine translation. arXiv preprint arXiv:1508.04025 (2015)
  6. 6.
    Shang, L., Lu, Z., Li, H.: Neural responding machine for short-text conversation. arXiv preprint arXiv:1503.02364 (2015)
  7. 7.
    Shang, L., et al.: Overview of the NTCIR-13 short text conversation task (2017)Google Scholar
  8. 8.
    Shang, L., Sakai, T., Lu, Z., Li, H., Higashinaka, R., Miyao, Y.: Overview of the NTCIR-12 short text conversation task, pp. 473–484 (2016)Google Scholar
  9. 9.
    Song, Y., Li, C.T., Nie, J.Y., Zhang, M., Zhao, D., Yan, R.: An ensemble of retrieval-based and generation-based human-computer conversation systems. In: Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence, IJCAI-18, pp. 4382–4388. International Joint Conferences on Artificial Intelligence Organization, July 2018Google Scholar
  10. 10.
    Sutskever, I., Vinyals, O., Le, Q.V.: Sequence to sequence learning with neural networks. In: Ghahramani, Z., Welling, M., Cortes, C., Lawrence, N.D., Weinberger, K.Q. (eds.) Advances in Neural Information Processing Systems 27, pp. 3104–3112. Curran Associates, Inc. (2014)Google Scholar
  11. 11.
    Xing, C., et al.: Topic aware neural response generation. In: Thirty-First AAAI Conference on Artificial Intelligence (2017)Google Scholar
  12. 12.
    Xu, L., Lin, H., Pan, Y., Ren, H., Chen, J.: Constructing the affective Lexicon ontology. J. China Soc. Sci. Tech. Inf. 27(2), 180–185 (2008)Google Scholar
  13. 13.
    Zhang, Y., Huang, M.: Overview of NTCIR-14 short text generation subtask: emotion generation challenge. In: Proceedings of the 14th NTCIR Conference (2019)Google Scholar
  14. 14.
    Zhou, H., Huang, M., Zhang, T., Zhu, X., Liu, B.: Emotional chatting machine: emotional conversation generation with internal and external memory. In: Thirty-Second AAAI Conference on Artificial Intelligence (2018)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  • Xiaohe Li
    • 1
  • Jiaqing Liu
    • 1
  • Weihao Zheng
    • 1
  • Xiangbo Wang
    • 1
  • Yutao Zhu
    • 1
  • Zhicheng Dou
    • 1
    Email author
  1. 1.School of InformationRenmin University of ChinaBeijingChina

Personalised recommendations