Building Emotional Conversation Systems Using Multi-task Seq2Seq Learning

  • Rui Zhang
  • Zhenyu WangEmail author
  • Dongcheng Mai
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10619)


This paper describes our system designed for the NLPCC 2017 shared task on emotional conversation generation. Our model adopts a multi-task Seq2Seq learning framework to capture the textual information of post sequence and generate responses for each type of emotions simultaneously. Evaluation results suggest that our model is competitive on emotional generation, which achieves 0.9658 on average emotion accuracy. We also observe the emotional interaction in human conversation, and try to explain it as empathy at the psychological level. Finally, our model achieves 325 on total score, 0.545 on average score and won the fourth place on total score.


Conversation generation Emotions Multi-task Seq2Seq 



This work is supported by the Science and Technology Program of Guangdong Province, China (2015B010131003). The authors also thank the editors and reviewers for their constructive editing and reviewing, respectively.


  1. 1.
    André, E., Rehm, M., Minker, W., Bühler, D.: Endowing spoken language dialogue systems with emotional intelligence. In: André, E., Dybkjær, L., Minker, W., Heisterkamp, P. (eds.) ADS 2004. LNCS (LNAI), vol. 3068, pp. 178–187. Springer, Heidelberg (2004). CrossRefGoogle Scholar
  2. 2.
    Bahdanau, D., Cho, K., Bengio, Y.: Neural machine translation by jointly learning to align and translate. arXiv preprint arXiv:1409.0473 (2014)
  3. 3.
    Bellet, P.S., Maloney, M.J.: The importance of empathy as an interviewing skill in medicine. JAMA 266(13), 1831–1832 (1991)CrossRefGoogle Scholar
  4. 4.
    Cho, K., Van Merriënboer, B., Gulcehre, C., Bahdanau, D., Bougares, F., Schwenk, H., Bengio, Y.: Learning phrase representations using RNN encoder-decoder for statistical machine translation. arXiv preprint arXiv:1406.1078 (2014)
  5. 5.
    Chung, J., Gulcehre, C., Cho, K., Bengio, Y.: Empirical evaluation of gated recurrent neural networks on sequence modeling. arXiv preprint arXiv:1412.3555 (2014)
  6. 6.
    Dong, D., Wu, H., He, W., Yu, D., Wang, H.: Multi-task learning for multiple language translation. In: ACL, pp. 1723–1732 (2015)Google Scholar
  7. 7.
    Gu, J., Lu, Z., Li, H., Li, V.O.: Incorporating copying mechanism in sequence-to-sequence learning. arXiv preprint arXiv:1603.06393 (2016)
  8. 8.
    Kim, Y.: Convolutional neural networks for sentence classification. arXiv preprint arXiv:1408.5882 (2014)
  9. 9.
    Liu, C.W., Lowe, R., Serban, I.V., Noseworthy, M., Charlin, L., Pineau, J.: How not to evaluate your dialogue system: an empirical study of unsupervised evaluation metrics for dialogue response generation. arXiv preprint arXiv:1603.08023 (2016)
  10. 10.
    Luong, M.T., Le, Q.V., Sutskever, I., Vinyals, O., Kaiser, L.: Multi-task sequence to sequence learning. arXiv preprint arXiv:1511.06114 (2015)
  11. 11.
    Michal, P., Pawel, D., Wenhan, S., Rafal, R., Kenji, A.: Towards context aware emotional intelligence in machines: computing contextual appropriateness of affective states. In: Proceedings of the Twenty-First International Joint Conference on Artificial Intelligence (IJCAI 2009), pp. 1469–1474. AAAI (2009)Google Scholar
  12. 12.
    Ritter, A., Cherry, C., Dolan, W.B.: Data-driven response generation in social media. In: Proceedings of the Conference on Empirical Methods in Natural Language Processing, pp. 583–593. Association for Computational Linguistics (2011)Google Scholar
  13. 13.
    Shang, L., Lu, Z., Li, H.: Neural responding machine for short-text conversation. arXiv preprint arXiv:1503.02364 (2015)
  14. 14.
    Skowron, M.: Affect listeners: acquisition of affective states by means of conversational systems. In: Esposito, A., Campbell, N., Vogel, C., Hussain, A., Nijholt, A. (eds.) Development of Multimodal Interfaces: Active Listening and Synchrony. LNCS, vol. 5967, pp. 169–181. Springer, Heidelberg (2010). CrossRefGoogle Scholar
  15. 15.
    Skowron, M., Rank, S., Theunis, M., Sienkiewicz, J.: The good, the bad and the neutral: affective profile in dialog system-user communication. In: D’Mello, S., Graesser, A., Schuller, B., Martin, J.-C. (eds.) ACII 2011. LNCS, vol. 6974, pp. 337–346. Springer, Heidelberg (2011). CrossRefGoogle Scholar
  16. 16.
    Sutskever, I., Vinyals, O., Le, Q.V.: Sequence to sequence learning with neural networks. In: Advances in Neural Information Processing Systems, pp. 3104–3112 (2014)Google Scholar
  17. 17.
    Vinyals, O., Le, Q.: A neural conversational model. arXiv preprint arXiv:1506.05869 (2015)
  18. 18.
    Wen, T.H., Gasic, M., Mrksic, N., Su, P.H., Vandyke, D., Young, S.: Semantically conditioned LSTM-based natural language generation for spoken dialogue systems. arXiv preprint arXiv:1508.01745 (2015)
  19. 19.
    Xing, C., Wu, W., Wu, Y., Liu, J., Huang, Y., Zhou, M., Ma, W.Y.: Topic aware neural response generation. In: AAAI, pp. 3351–3357 (2017)Google Scholar
  20. 20.
    Zhou, H., Huang, M., Zhang, T., Zhu, X., Liu, B.: Emotional chatting machine: emotional conversation generation with internal and external memory. arXiv preprint arXiv:1704.01074 (2017)
  21. 21.
    Zhou, H., Huang, M., Zhu, X.: Context-aware natural language generation for spoken dialogue systems. In: COLING, pp. 2032–2041 (2016)Google Scholar

Copyright information

© Springer International Publishing AG 2018

Authors and Affiliations

  1. 1.Department of Software EngineeringSouth China University of TechnologyGuangzhouPeople’s Republic of China

Personalised recommendations