On the Lack of Pragmatic Processing in Artificial Conversational Agents

  • Baptiste JacquetEmail author
  • Olivier Masson
  • Frank Jamet
  • Jean Baratgin
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 876)


With the increasing demand for automated agents able to communicate with humans, a lot of progress has been made in the field of artificial intelligence in order to produce conversational agents able to sustain open or topic-restricted conversations. Still, they remain far from the capacity of interaction displayed by humans. This article highlights the challenges still faced in artificial social interaction regarding the contextualization of utterances within a conversation, either in chatbots or in more complex social robots, through processing of the pragmatic clues of conversations, using current knowledge in psychology and linguistics. It also suggests a number of points of interest for the development of artificial agents aimed at improving their communication with humans, the relevance of their utterances, and the relationship with the people interacting with them. We believe that in order to be recognized as a social agent, an artificial agent must follow similar rules humans follow themselves when conversing with each other.


Pragmatics Natural language processing Cognition Conversations Social artificial agents 


  1. 1.
    Sperber, D., Wilson, D.: Relevance: Communication and Cognition, 2nd edn. Blackwell, Oxford (1995)Google Scholar
  2. 2.
    Saygin, A.P., Cicekli, I.: Pragmatics in human-computer conversations. J. Pragmat. 34(3), 227–258 (2002)CrossRefGoogle Scholar
  3. 3.
    Jacquet, B., Jamet, F., Baratgin, J.: Looking for humanity: the influence of inferences on the humanness of a conversational partner in the turing test. In: 3rd Workshop on Virtual Social Interaction (VSI), CITEC, Bielefeld, Germany (2017)Google Scholar
  4. 4.
    Jacquet, B., Baratgin, J., Jamet, F.: The gricean maxims of quantity and of relation in the turing test. In: 11th International Conference on Human System Interaction (HSI), pp. 332–338 (2018)Google Scholar
  5. 5.
    Chakrabarti, C., Luger, G.F.: Artificial conversations for customer service chatter bots: architecture, algorithms, and evaluation metrics. Expert Syst. Appl. 42(20), 6878–6897 (2015)CrossRefGoogle Scholar
  6. 6.
    Gockley, R., et al.: Designing robots for long-term social interaction. In: International Conference on Intelligent Robots and Systems, pp. 1338–1343 (2005)Google Scholar
  7. 7.
    Masson, O., Baratgin, J., Jamet, F.: NAO robot and the “endowment effect”. In: IEEE International Workshop on Advanced Robotics and its Social Impacts (ARSO), pp. 1–6 (2015)Google Scholar
  8. 8.
    Masson, O., Baratgin, J., Jamet, F.: NAO robot, transmitter of social cues: what impacts?. In: International Conference on Industrial, Engineering and Other Applications of Applied Intelligent Systems, pp. 559–568. Springer, Cham (2017)CrossRefGoogle Scholar
  9. 9.
    Masson, O., Baratgin, J., Jamet, F.: NAO robot as experimenter: social cues emitter and neutralizer to bring new results in experimental psychology. In: IEEE International Conference on Information and Digital Technologies (IDT), pp. 256–264 (2017)Google Scholar
  10. 10.
    Mutlu, B., Shiwa, T., Kanda, T., Ishiguro, H., Hagita, N.: Footing in human-robot conversations: how robots might shape participant roles using gaze cues. In: Proceedings of the 4th ACM/IEEE International Conference on Human Robot Interaction (HRI), pp. 61–68 (2009)Google Scholar
  11. 11.
    Ham, J., Bokhorst, R., Cuijpers, R., van der Pol, D., Cabibihan, J.J.: Making robots persuasive: the influence of combining persuasive strategies (gazing and gestures) by a storytelling robot on its persuasive power. In: International Conference on Social Robotics, pp. 71–83 (2011)CrossRefGoogle Scholar
  12. 12.
    Weizenbaum, J.: ELIZA - a computer program for the study of natural language communication between man and machine. Commun. ACM 9, 36–45 (1966)CrossRefGoogle Scholar
  13. 13.
    Wallace, R.S.: The anatomy of ALICE. In: Parsing the Turing Test, pp. 181–210 (2009)CrossRefGoogle Scholar
  14. 14.
  15. 15.
    Woebot Labs Inc.
  16. 16.
  17. 17.
    Microsoft Inc.
  18. 18.
    Broekens, J., Heerink, M., Rosendal, H.: Assistive social robots in elderly care: a review. Gerontechnology 8(2), 94–103 (2009)CrossRefGoogle Scholar
  19. 19.
    Motley, M.T.: Facial affect and verbal context in conversation: facial expression as interjection. Hum. Commun. Res. 20(1), 3–40 (1993)CrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  • Baptiste Jacquet
    • 1
    • 2
    Email author
  • Olivier Masson
    • 1
    • 2
  • Frank Jamet
    • 1
    • 2
    • 3
  • Jean Baratgin
    • 1
    • 2
    • 4
  1. 1.P-A-R-I-S AssociationParisFrance
  2. 2.Laboratoire CHArt - EA4004 (Université Paris VIII & EPHE)ParisFrance
  3. 3.Université Cergy-Pontoise (UCP)Cergy-Pontoise CedexFrance
  4. 4.Institut Jean-Nicod (IJN), Ecole Normale Supérieure (ENS)ParisFrance

Personalised recommendations