Design of Coimagination Support Dialogue System with Pluggable Dialogue System - Towards Long-Term Experiment

  • Seiki TokunagaEmail author
  • Mihoko Otake-Matsuura
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11582)


In this paper, we design a dialogue system which aims to support elderly people’s cognitive function with a conversation by face to face. We have a hypothesis that a kind of group conversation method which is called Coimagination Method (CM) would have merit for a human at a perspective of cognitive function. However, current CM aims to be designed to provide balanced group conversation among participants. Hence, the method has mainly focuses the group conversation, hence it has some limitations such as user have to join the specific location. But, elderly people sometime face difficulty because of some physically or mental problems to do it. In this paper, we try to design a chat system which provides a one-to-one conversation between human and system which is based on the essence of CM and copes the above limitations. In order to design the system, at first we consider an experimental design which would be conducted remotely during long-term as a system requirement, then we design a system which meets the requirement. Moreover, we also develop a prototype system in order to confirm the feasibility of proposed system design.


Conversation Chat bot Dialogue system System design Supporting elderly people 


  1. 1.
    Bowen, J., Teri, L., Kukull, W., McCormick, W., McCurry, S.M., Larson, E.B.: Progression to dementia in patients with isolated memory loss. Lancet 349(9054), 763–765 (1997). Scholar
  2. 2.
    Chalmers, T.C.A., et al.: A method for assessing the quality of a randomized control trial. Control. Clin. Trials 2(1), 31–49 (1981)CrossRefGoogle Scholar
  3. 3.
    Barker, D.J., Van Schaik, P., Simpson, D.S., Corbett, W.A.: Evaluating a spoken dialogue system for recording clinical observations during an endoscopic examination. Med. Inf. Internet Med. 28(2), 85–97 (2003). Scholar
  4. 4.
    Dunkin, J.J., Anderson-Hanley, C.: Dementia caregiver burden. Neurology 51(1 Suppl. 1), S53–S60 (1998)Google Scholar
  5. 5.
  6. 6.
    Higashinaka, R., et al.: Towards an open-domain conversational system fully based on natural language processing. In: COLING (2014)Google Scholar
  7. 7.
    Hill, J., Ford, W.R., Farreras, I.G.: Real conversations with artificial intelligence: a comparison between human-human conversations and human-chatbot conversations. Comput. Hum. Behav. 49, 245–250 (2015).
  8. 8.
  9. 9.
    I.E.T.F.: The Javascript object notation (JSON) data interchange format.
  10. 10.
    Google Inc.: Cloud speech-to-text.
  11. 11.
    Google Inc.: Google JSON style guide.
  12. 12.
    Japanese Government: White Paper for Eldelry PeopleGoogle Scholar
  13. 13.
    Leuski, A., Patel, R., Traum, D., Kennedy, B.: Building effective question answering characters. In: Proceedings of the 7th SIGdial Workshop on Discourse and Dialogue, SigDIAL 2006, pp. 18–27. Association for Computational Linguistics, Stroudsburg(2006)Google Scholar
  14. 14.
    Livingston, G., et al.: Dementia prevention, intervention, and care. Neurology 390, 2673–2734 (2017)Google Scholar
  15. 15.
    Misu, T., Kawahara, T.: Speech-based interactive information guidance system using question-answering technique. In: 2007 IEEE International Conference on Acoustics, Speech and Signal Processing - ICASSP 2007, vol. 4, pp. IV-145–IV-148, April 2007Google Scholar
  16. 16.
    Otake, M., Kato, M., Takagi, T., Asama, H.: Development of coimagination method towards cognitive enhancement via image based interactive communication. In: RO-MAN 2009 - The 18th IEEE International Symposium on Robot and Human Interactive Communication, pp. 835–840, September 2009Google Scholar
  17. 17.
    Serban, I.V., Sordoni, A., Bengio, Y., Courville, A.C., Pineau, J.: Hierarchical neural network generative models for movie dialogues. CoRR abs/1507.04808 (2015)Google Scholar
  18. 18.
    Suzuki, H., et al.: Cognitive intervention through a training program for picture book reading in community-dwelling older adults: a randomized controlled trial. BMC Geriatr. 14(1), 122 (2014). Scholar
  19. 19.
    Traum, D., et al.: New dimensions in testimony: digitally preserving a Holocaust survivor’s interactive storytelling. In: Schoenau-Fog, H., Bruni, L.E., Louchart, S., Baceviciute, S. (eds.) ICIDS 2015. LNCS, vol. 9445, pp. 269–281. Springer, Cham (2015). Scholar
  20. 20.
    Truong, H.P., Parthasarathi, P., Pineau, J.: MACA: a modular architecture for conversational agents. In: Proceedings of the 18th Annual SIGdial Meeting on Discourse and Dialogue, pp. 93–102. Association for Computational Linguistics (2017).
  21. 21.
    Walker, M.A.: An application of reinforcement learning to dialogue strategy selection in a spoken dialogue system for email. CoRR abs/1106.0241 (2011)Google Scholar
  22. 22.
    Wolters, M.K., Kelly, F., Kilgour, J.: Designing a spoken dialogue interface to an intelligent cognitive assistant for people with dementia. Health Inf. J. 22(4), 854–866 (2016)CrossRefGoogle Scholar
  23. 23.
    Zhang, S., Dinan, E., Urbanek, J., Szlam, A., Kiela, D., Weston, J.: Personalizing dialogue agents: I have a dog, do you have pets too? CoRR abs/1801.07243 (2018)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  1. 1.Center for Advanced Intelligence ProjectRIKENChuo-kuJapan

Personalised recommendations