Skip to main content

Timing Prediction of Facilitating Utterance in Multi-party Conversation

  • 353 Accesses

Part of the Communications in Computer and Information Science book series (CCIS,volume 1215)

Abstract

Supporting consensus-building in multi-party conversations is a very important task in intelligent systems. To conduct smooth, active, and productive discussions, we need a facilitator who controls a discussion appropriately. However, it is impractical to assign a good facilitator to each group in the discussion environment. The goal of our study is to develop a digital facilitator system that supports high-quality discussions. One role of the digital facilitator is to generate facilitating utterances in the discussions. To realize the system, we need to predict the timing of facilitating utterances. To apply a machine learning technique to our model, we construct a data set from the AMI corpus, first. For the construction, we use some rules based on the annotation of the corpus. Then, we generate a prediction model with verbal and non-verbal features extracted from discussions. We obtained 0.75 on the F-measure. We compared our model with a baseline method. Our model outperformed the baseline (0.7 vs. 0.5 on the AUC value). In addition, we introduce additional features about the role of participants in the AMI corpus. By using the additional features, the F measure increased by 2 points. The experimental results show the effectiveness of our model.

Keywords

  • Multi-party conversation
  • Timing prediction
  • Facilitation

This is a preview of subscription content, access via your institution.

Buying options

Chapter
USD   29.95
Price excludes VAT (USA)
  • DOI: 10.1007/978-981-15-6168-9_23
  • Chapter length: 13 pages
  • Instant PDF download
  • Readable on all devices
  • Own it forever
  • Exclusive offer for individuals only
  • Tax calculation will be finalised during checkout
eBook
USD   84.99
Price excludes VAT (USA)
  • ISBN: 978-981-15-6168-9
  • Instant PDF download
  • Readable on all devices
  • Own it forever
  • Exclusive offer for individuals only
  • Tax calculation will be finalised during checkout
Softcover Book
USD   109.99
Price excludes VAT (USA)
Fig. 1.
Fig. 2.
Fig. 3.

Notes

  1. 1.

    Five is the mode value of utterances with the Gatekeeper and specific DA tags.

  2. 2.

    For overlaps, we do not handle this feature because the overlap length is usually shorter as compared with the silence length in discussion.

  3. 3.

    Note that our model did not use any DA tags as features.

References

  1. Guidelines for Dialogue Act and Addressee Annotation Version 1.0 (2005)

    Google Scholar 

  2. Bojanowski, P., Grave, E., Joulin, A., Mikolov, T.: Enriching word vectors with subword information. Trans. Assoc. Computat. Linguistics 5, 135–146 (2017)

    CrossRef  Google Scholar 

  3. Carletta, J.: Unleashing the killer corpus: experiences in creating the multi-everything ami meeting corpus. Lang. Res. Eval. 41(2), 181–190 (2007)

    CrossRef  Google Scholar 

  4. Chang, C.-C., Lin, C.-J.: Libsvm: a library for support vector machines. ACM Trans. Intell. Syst. Technol. (TIST) 2(3), 27 (2011)

    Google Scholar 

  5. Ito, T., Imi, Y., Ito, T., Hideshima, E.: COLLAGREE: a facilitator-mediated large-scale consensus support system. In: Proceedings of the 2nd Collective Intelligence Conference (2014)

    Google Scholar 

  6. Kirikihira, R., Shimada, K.: Discussion map with an assistant function for decision-making: a tool for supporting consensus-building. In: Egi, H., Yuizono, T., Baloian, N., Yoshino, T., Ichimura, S., Rodrigues, A. (eds.) International Conference on Collaboration Technologies, pp. 3–18. Springer, Cham (2018). https://doi.org/10.1007/978-3-319-98743-9_1

    CrossRef  Google Scholar 

  7. Lala, D., Milhorat, P., Inoue, K., Ishida, M., Takanashi, K., Kawahara, T.: Attentive listening system with backchanneling, response generation and flexible turn-taking. In: Proceedings of the 18th Annual SIGdial Meeting on Discourse and Dialogue, pp. 127–136 (2017)

    Google Scholar 

  8. Matsuyama, Y., Akiba, I., Fujie, S., Kobayashi, T.: Four-participant group conversation: a facilitation robot controlling engagement density as the fourth participant. Comput. Speech Lang. 33(1), 1–24 (2015)

    CrossRef  Google Scholar 

  9. Mikolov, T., Chen, K., Corrado, G., Dean, J.: Efficient estimation of word representations in vector space. arXiv preprint arXiv:1301.3781 (2013)

  10. Okada, S., et al.: Estimating communication skills using dialogue acts and nonverbal features in multiple discussion datasets. In: Proceedings of the 18th ACM International Conference on Multimodal Interaction, pp. 169–176 (2016)

    Google Scholar 

  11. Omoto, Y., Toda, Y., Ueda, K., Nishida, T.: Analyses of the facilitating behavior by using participant’s agreement and nonverbal behavior. J. Inf. Process. Soc. Japan 52(12), 3659–3670 (2011). (in Japanese)

    Google Scholar 

  12. Sapru, A., Bourlard, H.: Automatic social role recognition in professional meetings using conditional random fields. In: Proceedings of Interspeech (2013)

    Google Scholar 

  13. Sapru, A., Bourlard, H.: Automatic recognition of emergent social roles in small group interactions. IEEE Trans. Multimedia 17(5), 746–760 (2015)

    CrossRef  Google Scholar 

  14. Shiota, T., Yamamura, T., Shimada, K.: Analysis of facilitators’ behaviors in multi-party conversations for constructing a digital facilitator system. In: International Conference on Collaboration Technologies, pp. 145–158 (2018)

    Google Scholar 

  15. Sierra, C., Jennings, N.R., Noriega, P., Parsons, S.: A framework for argumentation-based negotiation. In: Singh, M.P., Rao, A., Wooldridge, M.J. (eds.) ATAL 1997. LNCS, vol. 1365, pp. 177–192. Springer, Heidelberg (1998). https://doi.org/10.1007/BFb0026758

    CrossRef  Google Scholar 

  16. Skantze, G.: Towards a general, continuous model of turn-taking in spoken dialogue using LSTM recurrent neural networks. In: SIGdial Conference (2017)

    Google Scholar 

  17. Vinciarelli, A., Valente, F., Yella, S.H., Sapru, A.: Understanding social signals in multi-party conversations: automatic recognition of socio-emotional roles in the AMI meeting corpus. In: 2011 IEEE International Conference on Systems, Man, and Cybernetics, pp. 374–379 (2011)

    Google Scholar 

  18. Weninger, F., Krajewski, J., Batliner, A., Schuller, B.: The voice of leadership: models and performances of automatic analysis in online speeches. IEEE Trans. Affect. Comput. 3(4), 496–508 (2012)

    CrossRef  Google Scholar 

  19. Yamamura, T., Shimada, K., Kawahara, S.: The Kyutech corpus and topic segmentation using a combined method. In: Proceedings of the 12th Workshop on Asian Language Resources, pp. 95–104 (2016)

    Google Scholar 

Download references

Acknowledgment

This work was supported by JSPS KAKENHI Grant Number 17H01840.

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Kazutaka Shimada .

Editor information

Editors and Affiliations

Rights and permissions

Reprints and Permissions

Copyright information

© 2020 Springer Nature Singapore Pte Ltd.

About this paper

Verify currency and authenticity via CrossMark

Cite this paper

Sembokuya, T., Shimada, K. (2020). Timing Prediction of Facilitating Utterance in Multi-party Conversation. In: Nguyen, LM., Phan, XH., Hasida, K., Tojo, S. (eds) Computational Linguistics. PACLING 2019. Communications in Computer and Information Science, vol 1215. Springer, Singapore. https://doi.org/10.1007/978-981-15-6168-9_23

Download citation

  • DOI: https://doi.org/10.1007/978-981-15-6168-9_23

  • Published:

  • Publisher Name: Springer, Singapore

  • Print ISBN: 978-981-15-6167-2

  • Online ISBN: 978-981-15-6168-9

  • eBook Packages: Computer ScienceComputer Science (R0)