Semantic Refinement GRU-Based Neural Language Generation for Spoken Dialogue Systems

  • Van-Khanh TranEmail author
  • Le-Minh Nguyen
Conference paper
Part of the Communications in Computer and Information Science book series (CCIS, volume 781)


Natural language generation (NLG) plays a critical role in spoken dialogue systems. This paper presents a new approach to NLG by using recurrent neural networks (RNN), in which a gating mechanism is applied before RNN computation. This allows the proposed model to generate appropriate sentences. The RNN-based generator can be learned from unaligned data by jointly training sentence planning and surface realization to produce natural language responses. The model was extensively evaluated on four different NLG domains. The results show that the proposed generator achieved better performance on all the NLG domains compared to previous generators.



This work was supported by the JSPS KAKENHI Grant number JP15K16048.


  1. 1.
    Abadi, M., Agarwal, A., Barham, P., Brevdo, E., Chen, Z., Citro, C., Corrado, G.S., Davis, A., Dean, J., Devin, M., et al.: Tensorflow: large-scale machine learning on heterogeneous distributed systems. arXiv preprint arXiv:1603.04467 (2016)
  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.
    Cheyer, A., Guzzoni, D.: Method and apparatus for building an intelligent automated assistant, US Patent 8,677,377, 18 March 2014Google Scholar
  4. 4.
    Dušek, O., Jurčíček, F.: Sequence-to-sequence generation for spoken dialogue via deep syntax trees and strings. arXiv preprint arXiv:1606.05491 (2016)
  5. 5.
    Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735–1780 (1997)CrossRefGoogle Scholar
  6. 6.
    Karpathy, A., Fei-Fei, L.: Deep visual-semantic alignments for generating image descriptions. In: Proceedings of CVPR, pp. 3128–3137 (2015)Google Scholar
  7. 7.
    Lowe, R., Pow, N., Serban, I., Charlin, L., Pineau, J.: Incorporating unstructured textual knowledge sources into neural dialogue systems. In: NIPS Workshop MLNLU (2015)Google Scholar
  8. 8.
    Mairesse, F., Young, S.: Stochastic language generation in dialogue using factored language models. Comput. Linguist. 40(4), 763–799 (2014)CrossRefGoogle Scholar
  9. 9.
    Mikolov, T.: Recurrent neural network based language model (2010)Google Scholar
  10. 10.
    Oh, A.H., Rudnicky, A.I.: Stochastic language generation for spoken dialogue systems. In: Proceedings of NAACL. ACL (2000)Google Scholar
  11. 11.
    Papineni, K., Roukos, S., Ward, T., Zhu, W.J.: BLEU: a method for automatic evaluation of machine translation. In: Proceedings of ACL, pp. 311–318. ACL (2002)Google Scholar
  12. 12.
    Pennington, J., Socher, R., Manning, C.D.: Glove: global vectors for word representation. In: EMNLP, vol. 14 (2014)Google Scholar
  13. 13.
    Ratnaparkhi, A.: Trainable methods for surface natural language generation. In: Proceedings of NAACL. ACL (2000)Google Scholar
  14. 14.
    Rieser, V., Lemon, O., Liu, X.: Optimising information presentation for spoken dialogue systems. In: Proceedings of ACL, pp. 1009-1018. ACL (2010)Google Scholar
  15. 15.
    Stent, A., Prasad, R., Walker, M.: Trainable sentence planning for complex information presentation in spoken dialog systems. In: Proceedings of ACL, p. 79. ACL (2004)Google Scholar
  16. 16.
    Tran, V.K., Nguyen, L.M.: Natural language generation for spoken dialogue system using RNN encoder-decoder networks. In: CoNLL 2017 (2017)Google Scholar
  17. 17.
    Vinyals, O., Toshev, A., Bengio, S., Erhan, D.: Show and tell: a neural image caption generator. In: CVPR (2015)Google Scholar
  18. 18.
    Wang, B., Liu, K., Zhao, J.: Inner attention based recurrent neural networks for answer selection (2016)Google Scholar
  19. 19.
    Wen, T.H., Gašić, M., Kim, D., Mrkšić, N., Su, P.H., Vandyke, D., Young, S.: Stochastic language generation in dialogue using recurrent neural networks with convolutional sentence reranking. In: Proceedings of SIGDIAL. ACL (2015)Google Scholar
  20. 20.
    Wen, T.H., Gasic, M., Mrksic, N., Rojas-Barahona, L.M., Su, P.H., Vandyke, D., Young, S.: Multi-domain neural network language generation for spoken dialogue systems. arXiv preprint arXiv:1603.01232 (2016)
  21. 21.
    Wen, T.H., Gašic, M., Mrkšic, N., Rojas-Barahona, L.M., Su, P.H., Vandyke, D., Young, S.: Toward multi-domain language generation using recurrent neural networks (2016)Google Scholar
  22. 22.
    Wen, T.H., Gašić, M., Mrkšić, N., Su, P.H., Vandyke, D., Young, S.: Semantically conditioned LSTM-based natural language generation for spoken dialogue systems. In: Proceedings of EMNLP. ACL (2015)Google Scholar
  23. 23.
    Wen, T.H., Vandyke, D., Mrksic, N., Gasic, M., Rojas-Barahona, L.M., Su, P.H., Ultes, S., Young, S.: A network-based end-to-end trainable task-oriented dialogue system. arXiv preprint arXiv:1604.04562 (2016)
  24. 24.
    Zhang, X., Lapata, M.: Chinese poetry generation with recurrent neural networks. In: EMNLP, pp. 670–680 (2014)Google Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2018

Authors and Affiliations

  1. 1.Japan Advanced Institute of Science and Technology, JAISTNomiJapan
  2. 2.University of Information and Communication Technology, ICTU, Thai Nguyen UniversityThai NguyenVietnam

Personalised recommendations