Advertisement

An Approach to Teach Nao Dialogue Skills

  • Manuel GrañaEmail author
  • Alexander Triguero
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11486)

Abstract

Endowing social robots with natural interaction abilities, such as following a dialogue that gives the human user a sense of natural interaction, is a current interest in many areas. We are interested in developing the dialogue skills of the Nao robot for its potential use in treatment of children with special educational needs and elder people at risk of isolation. Corpora based dialog system development approaches are not adequate for personalization. In our approach we propose a teacher and introspection approach that may be able to produce highly personalized and entertaining dialog systems. The introspection module would run in the background using generative randomized systems creating new dialog pathways from the patterns learnt by direct teaching interaction.

Notes

Acknowledgments

This work has been partially supported by the EC through project CybSPEED funded by the MSCA-RISE grant agreement No 777720.

References

  1. 1.
    Baumann, T., Kennington, C., Hough, J., Schlangen, D.: Recognising conversational speech: what an incremental ASR should do for a dialogue system and how to get there. In: Jokinen, K., Wilcock, G. (eds.) Dialogues with Social Robots. LNEE, vol. 999, pp. 421–432. Springer, Singapore (2017).  https://doi.org/10.1007/978-981-10-2585-3_35CrossRefGoogle Scholar
  2. 2.
    Bertero, D., Fung, P.: A long short-term memory framework for predicting humor in dialogues. In: Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pp. 130–135 (2016)Google Scholar
  3. 3.
    Bordes, A., Boureau, Y.L., Weston, J.: Learning end-to-end goal-oriented dialog. arXiv preprint arXiv:1605.07683 (2016)
  4. 4.
    Bowden, K.K., Oraby, S., Misra, A., Wu, J., Lukin, S.: Data-driven dialogue systems for social agents. arXiv preprint arXiv:1709.03190 (2017)
  5. 5.
    Cuayáhuitl, H.: Deep reinforcement learning for conversational robots playing games. In: 2017 IEEE-RAS 17th International Conference on Humanoid Robotics (Humanoids), pp. 771–776, November 2017Google Scholar
  6. 6.
    Cuayáhuitl, H.: SimpleDS: a simple deep reinforcement learning dialogue system. In: Jokinen, K., Wilcock, G. (eds.) Dialogues with Social Robots. LNEE, vol. 999, pp. 109–118. Springer, Singapore (2017).  https://doi.org/10.1007/978-981-10-2585-3_8CrossRefGoogle Scholar
  7. 7.
    Dodge, J., et al. Evaluating prerequisite qualities for learning end-to-end dialog systems. arXiv preprint arXiv:1511.06931 (2015)
  8. 8.
    Graves, A., Mohamed, A.R., Hinton, G.: Speech recognition with deep recurrent neural networks. In: 2013 IEEE International Conference on Acoustics, speech and signal processing (ICASSP), pp. 6645–6649. IEEE (2013)Google Scholar
  9. 9.
    Henderson, M.: Machine learning for dialog state tracking: a review. In: Proceedings of The First International Workshop on Machine Learning in Spoken Language Processing (2015)Google Scholar
  10. 10.
    Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735–1780 (1997)CrossRefGoogle Scholar
  11. 11.
    Jurafsky, D., Martin, J.H.: Dialog systems and chatbots. In: Speech and Language Processing, vol. 3. Pearson, London (2014)Google Scholar
  12. 12.
    Khouzaimi, H., Laroche, R., Lefèvre, F.: A methodology for turn-taking capabilities enhancement in spoken dialogue systems using reinforcement learning. Comput. Speech Lang. 47, 93–111 (2018)CrossRefGoogle Scholar
  13. 13.
    Li, J., Monroe, W., Ritter, A., Galley, M., Gao, J., Jurafsky, D.: Deep reinforcement learning for dialogue generation. arXiv preprint arXiv:1606.01541 (2016)
  14. 14.
    Li, J., Monroe, W., Shi, T., Ritter, A.,Jurafsky, D.: Adversarial learning for neural dialogue generation. arXiv preprint arXiv:1701.06547 (2017)
  15. 15.
    Lowe, R., Pow, N., Serban, I., Pineau, J.: The Ubuntu dialogue corpus: a large dataset for research in unstructured multi-turn dialogue systems. arXiv preprint arXiv:1506.08909 (2015)
  16. 16.
    Cruz, A.M., Rincon, A.M.R., Duenas, W.R.R., Torres, D.A.Q., Bohorquez-Heredia, A.F.: What does the literature say about using robots on children with disabilities? Disabil. Rehabil. Assist. Technol. 12(5), 429–440 (2017)CrossRefGoogle Scholar
  17. 17.
    Ozaeta, L., Graña, M.: A view of the state of the art of dialogue systems. In: de Cos Juez, F.J., et al. (eds.) Hybrid Artificial Intelligent Systems, pp. 706–715. Springer, Cham (2018).  https://doi.org/10.1007/978-3-319-92639-1_59CrossRefGoogle Scholar
  18. 18.
    Palangi, H., et al.: Deep sentence embedding using long short-term memory networks: analysis and application to information retrieval. IEEE/ACM Transact. Audio Speech Lang. Process. (TASLP) 24(4), 694–707 (2016)CrossRefGoogle Scholar
  19. 19.
    Pennisi, P., et al.: Autism and social robotics: a systematic review. Autism Res. 9(2), 165–183 (2016)CrossRefGoogle Scholar
  20. 20.
    Sainath, T.N., Vinyals, O., Senior, A., Sak, H.: Convolutional, long short-term memory, fully connected deep neural networks. In: 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 4580–4584. IEEE (2015)Google Scholar
  21. 21.
    Serban, I.V., Lowe, R., Henderson, P., Charlin, L., Pineau, J.: A survey of available corpora for building data-driven dialogue systems. arXiv preprint arXiv:1512.05742 (2015)
  22. 22.
    Serban, I.V., Sordoni, A., Bengio, Y., Courville, A.C., Pineau, J.: Building end-to-end dialogue systems using generative hierarchical neural network models. In: AAAI, vol. 16, pp. 3776–3784 (2016)Google Scholar
  23. 23.
    Serban, I.V., et al.: A hierarchical latent variable encoder-decoder model for generating dialogues. In: AAAI, pp. 3295–3301 (2017)Google Scholar
  24. 24.
    Strub, F., De Vries, H., Mary, J., Piot, B., Courville, A., Pietquin, O.: End-to-end optimization of goal-driven and visually grounded dialogue systems. arXiv preprint arXiv:1703.05423 (2017)
  25. 25.
    Su, P.-H., et al.: On-line active reward learning for policy optimisation in spoken dialogue systems. arXiv preprint arXiv:1605.07669 (2016)
  26. 26.
    Su, P.-H., Vandyke, D., Gasic, M., Mrksic, N., Wen, T.-H., Young, S.: Reward shaping with recurrent neural networks for speeding up on-line policy learning in spoken dialogue systems. arXiv preprint arXiv:1508.03391 (2015)
  27. 27.
    Trieu, H.-L., Iida, H., Bao, N.P.H., Nguyen, L.-M.: Towards developing dialogue systems with entertaining conversations. ICAART 2, 511–518 (2017)Google Scholar
  28. 28.
    Triguero, A., Graña, M.: Teaching NAO to answer.  https://doi.org/10.5281/zenodo.2567595. February 2019
  29. 29.
    Wen, T.-H., et al.: A network-based end-to-end trainable task-oriented dialogue system. arXiv preprint arXiv:1604.04562 (2016)

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  1. 1.Computational Intelligence Group, Department of CCIAUniversity of the Basque CountrySan SebastiánSpain

Personalised recommendations