Advertisement

A Knowledge Selection Model in Pointer-Generator Dialogue Systems

  • An WangEmail author
  • MingXue Liao
  • Pin Lv
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 1075)

Abstract

Conversation generation is one of the core problems in natural language processing. In this paper, we present a new model for knowledge grounded conversations. Our model is enhanced by copying mechanism, which can produce a response with tokens either copied from conversation history or be generated from states. Besides, to utilize related knowledge precisely, we add attention mechanism to select the most related knowledge for each decoding step. Furthermore, we use beam search to reduce the generation of meaningless responses. Evaluations show that our model achieves better performance than other baselines.

Keywords

Dialogue systems Knowledge selection Copying mechanism 

References

  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., van Merrienboer, B., Bahdanau, D., Bengio, Y.: On the properties of neural machine translation: encoder–decoder approaches. In: Proceedings of SSST-8, Eighth Workshop on Syntax, Semantics and Structure in Statistical Translation, pp. 103–111. Association for Computational Linguistics (2014).  https://doi.org/10.3115/v1/W14-4012. https://www.aclweb.org/anthology/W14-4012
  3. 3.
    Dinan, E., Roller, S., Shuster, K., Fan, A., Auli, M., Weston, J.: Wizard of Wikipedia: knowledge-powered conversational agents. arXiv preprint arXiv:1811.01241 (2018)
  4. 4.
    Ghazvininejad, M., Brockett, C., Chang, M.W., Dolan, B., Gao, J., Yih, W.t., Galley, M.: A knowledge-grounded neural conversation model. In: Thirty-Second AAAI Conference on Artificial Intelligence (2018)Google Scholar
  5. 5.
    Li, J., Galley, M., Brockett, C., Gao, J., Dolan, B.: A diversity-promoting objective function for neural conversation models. In: Proceedings of NAACL-HLT, pp. 110–119 (2016a)Google Scholar
  6. 6.
    Li, J., Monroe, W., Jurafsky, D.: A simple, fast diverse decoding algorithm for neural generation. arXiv preprint arXiv:1611.08562 (2016b)
  7. 7.
    Liu, S., Chen, H., Ren, Z., Feng, Y., Liu, Q., Yin, D.: Knowledge diffusion for neural dialogue generation. In: Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 1489–1498 (2018)Google Scholar
  8. 8.
    Papineni, K., Roukos, S., Ward, T., Zhu, W.J.: Bleu: a method for automatic evaluation of machine translation. In: Proceedings of the 40th Annual Meeting on Association for Computational Linguistics, pp. 311–318. Association for Computational Linguistics (2002)Google Scholar
  9. 9.
    See, A., Liu, P.J., Manning, C.D.: Get to the point: Summarization with pointer-generator networks. In: Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 1073–1083 (2017)Google Scholar
  10. 10.
    Seo, M., Kembhavi, A., Farhadi, A., Hajishirzi, H.: Bidirectional attention flow for machine comprehension. arXiv preprint arXiv:1611.01603 (2016)
  11. 11.
    Shang, L., Lu, Z., Li, H.: Neural responding machine for short-text conversation. In: Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), vol. 1, pp. 1577–1586 (2015)Google Scholar
  12. 12.
    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
  13. 13.
    Vinyals, O., Le, Q.V.: A neural conversational model. arXiv preprint arXiv:1506.05869 (2015)
  14. 14.
    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: Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 2204–2213 (2018)Google Scholar
  15. 15.
    Zhou, H., Young, T., Huang, M., Zhao, H., Xu, J., Zhu, X.: Commonsense knowledge aware conversation generation with graph attention. In: IJCAI (2018)Google Scholar
  16. 16.
    Zhou, K., Prabhumoye, S., Black, A.W.: A dataset for document grounded conversations. In: Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing (2018)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2020

Authors and Affiliations

  1. 1.University of Chinese Academy of Sciences, UCASBeijingPeople’s Republic of China
  2. 2.Institute of SoftwareChinese Academy of Sciences, ISCASBeijingPeople’s Republic of China

Personalised recommendations