Avoiding Echo-Responses in a Retrieval-Based Conversation System

  • Denis FedorenkoEmail author
  • Nikita Smetanin
  • Artem Rodichev
Conference paper
Part of the Communications in Computer and Information Science book series (CCIS, volume 930)


Retrieval-based conversation systems generally tend to highly rank responses that are semantically similar or even identical to the given conversation context. While the system’s goal is to find the most appropriate response, rather than the most semantically similar one, this tendency results in low-quality responses. We refer to this challenge as the echoing problem. To mitigate this problem, we utilize a hard negative mining approach at the training stage. The evaluation shows that the resulting model reduces echoing and achieves better results in terms of Average Precision and Recall@N metrics, compared to the models trained without the proposed approach.


Dialog modeling Response selection Lexical repetition Hard negative mining End-to-end learning 


  1. 1.
    Canévet, O., Fleuret, F.: Efficient sample mining for object detection. In: Proceedings of the 6th Asian Conference on Machine Learning (ACML), No. EPFL-CONF-203847 (2014)Google Scholar
  2. 2.
    Chen, H., Liu, X., Yin, D., Tang, J.: A survey on dialogue systems: recent advances and new frontiers. SIGKDD Explor. Newsl. 19(2), 25–35 (2017). Scholar
  3. 3.
    Feng, M., Xiang, B., Glass, M.R., Wang, L., Zhou, B.: Applying deep learning to answer selection: a study and an open task. In: 2015 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU), pp. 813–820. IEEE (2015)Google Scholar
  4. 4.
    Jurafsky, D., Martin, J.: Dialog systems and chatbots. In: Speech and Language Processing, vol. 3 (2017).
  5. 5.
    Kingma, D., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)
  6. 6.
    Lowe, R., Pow, N., Serban, I., Pineau, J.: The ubuntu dialogue corpus: a large dataset for research in unstructured multi-turn dialogue systems. CoRR abs/1506.08909 (2015).
  7. 7.
    Manning, C.D., Raghavan, P., Schütze, H.: Introduction to Information Retrieval. Cambridge University Press, New York (2008)CrossRefGoogle Scholar
  8. 8.
    Mikolov, T., Chen, K., Corrado, G., Dean, J.: Efficient estimation of word representations in vector space. CoRR abs/1301.3781 (2013).
  9. 9.
    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
  10. 10.
    Schroff, F., Kalenichenko, D., Philbin, J.: FaceNet: a unified embedding for face recognition and clustering. CoRR abs/1503.03832 (2015).
  11. 11.
    Serban, I.V., et al.: A deep reinforcement learning chatbot. arXiv preprint arXiv:1709.02349 (2017)
  12. 12.
    Tan, M., Xiang, B., Zhou, B.: LSTM-based deep learning models for non-factoid answer selection. CoRR abs/1511.04108 (2015).
  13. 13.
    Wang, H., Lu, Z., Li, H., Chen, E.: A dataset for research on short-text conversations. In: Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing, pp. 935–945 (2013)Google Scholar
  14. 14.
    Wu, Y., Wu, W., Zhou, M., Li, Z.: Sequential match network: a new architecture for multi-turn response selection in retrieval-based chatbots. CoRR abs/1612.01627 (2016).
  15. 15.
    Yan, Z., et al.: DocChat: an information retrieval approach for chatbot engines using unstructured documents. In: Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), vol. 1, pp. 516–525 (2016)Google Scholar
  16. 16.
    Zhou, X., et al.: Multi-view response selection for human-computer conversation. In: Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, pp. 372–381 (2016)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2018

Authors and Affiliations

  1. @ Luka, Inc.MoscowRussia

Personalised recommendations