Abstract
In this short paper, we evaluate the prospects of automatic dialogue script generation from text for presentation by a team of Embodied Conversational Agents (ECAs). We describe an experiment comparing user perception and preference between plain text and video ECA presentations modes and between monologue and dialogue presentation styles. Our results show that most users are not indifferent of the presentation mode and the user’s preference is guided by the perceived understanding and enjoyment of the presentation.
The research reported in this paper was carried out as part of the CODA (COherent Dialogue Automatically generated from text) project. The project was funded by the UK’s Engineering and Physical Sciences Research Council under Grant EP/G020981/1. The authors would like to thank Ms Sara Winter for preparing the video materials for the experiment.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
André, E., Rist, T., van Mulken, S., Klesen, M., Baldes, S.: The automated design of believable dialogues for animated presentation teams. In: Embodied Conversational Agents, pp. 220–255. MIT Press, Cambridge (2000)
Carlson, L., Marcu, D.: Discourse tagging reference manual. Technical Report ISI-TR-545, ISI (September 2001)
Cavazza, M., Charles, F.: Dialogue Generation in Character-based Interactive Storytelling. In: Proceedings of the AAAI First Annual Artificial Intelligence and Interactive Digital Entertainment Conference, Marina Del Rey, California, USA (2005)
Cohn, T., Lapata, M.: Large margin synchronous generation and its application to sentence compression. In: Procs. of EMNLP-CONLL, Prague, pp. 73–82 (2007)
Craig, S., Gholson, B., Ventura, M., Graesser, A., and the Tutoring Research Group: Overhearing dialogues and monologues in virtual tutoring sessions. International Journal of Artificial Intelligence in Education 11, 242–253 (2000)
Nadamoto, A., Tanaka, K.: Complementing your TV-viewing by web content automatically-transformed into TV-program-type content. In: Proceedings 13th Annual ACM International Conference on Multimedia, pp. 41–50. ACM Press, New York (2005)
Nakasone, A., et al.: A 3D Internet based experimental framework for integrating traffic simulation and multi-user immersive driving. In: 4th Int’l Conference on Simulation Tools and Techniques (2011)
Piwek, P., Hernault, H., Prendinger, H., Ishizuka, M.: T2D: Generating Dialogues Between Virtual Agents Automatically from Text. In: Pelachaud, C., Martin, J.-C., André, E., Chollet, G., Karpouzis, K., Pelé, D. (eds.) IVA 2007. LNCS (LNAI), vol. 4722, pp. 161–174. Springer, Heidelberg (2007), doi:10.1007/978-3-540-74997-4
Piwek, P., Stoyanchev, S.: Generating Expository Dialogue from Monologue: Motivation, Corpus and Preliminary Rules. In: Proc. of NAACL, Los Angeles, USA (2010)
Piwek, P., Stoyanchev, S.: Data-Oriented Monologue-to-Dialogue Generation. In: Proc. of ACL/HLT, Portland, USA (2011)
Reiter, E.: An Architecture for Data to Text Systems. In: Procs. of ENLG-2007, Schloss Dagstuhl, Germany, pp. 97–104 (2007)
Rus, V., Graesser, A., Stent, A., Walker, M., White, M.: Text-to-Text Generation. In: Dale, R., White, M. (eds.) Shared Tasks and Comparative Evaluation in Natural Language Generation: Workshop Report, Arlington, Virginia (2007)
Stock, O., Zancanaro, M.: Multimodal Intelligent Information Presentation. Text, Speech and Language Technology, vol. 27. Springer, Heidelberg (2005)
Stoyanchev, S., Piwek, P.: The CODA System for Monologue-to-Dialogue Generation. In: Proc. of SIGDIAL, Portland, USA (2011)
Stoyanchev, S., Piwek, P.: Constructing the CODA Corpus: a Parallel Corpus of Monologues and Expository Dialogues. In: Proc. of LREC, Malta (2010)
Stoyanchev, S., Piwek, P.: Harvesting re-usable high-level rules for expository dialogue generation. In: Proc. of INLG, Trim, Ireland (2010)
Suzuki, S.V., Yamada, S.: Persuasion through overheard communication by life-like agents. In: Procs of the 2004 IEEE/WIC/ACM International Conference on Intelligent Agent Technology, Beijing (September 2004)
Deemter, K.v., Krenn, B., Piwek, P., Klesen, M., Schroeder, M., Baumann, S.: Fully Generated Scripted Dialogue for Embodied Agents. Artificial Intelligence Journal 172(10), 1219–1244 (2008)
Williams, S., Piwek, P., Power, R.: Generating Monologue and Dialogue to Present Personalised Medical Information to Patients. In: Procs ENLG 2007, Schloss Dagstuhl, Germany, pp. 167–170 (2007)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2011 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Stoyanchev, S., Piwek, P., Prendinger, H. (2011). Comparing Modes of Information Presentation: Text versus ECA and Single versus Two ECAs. In: Vilhjálmsson, H.H., Kopp, S., Marsella, S., Thórisson, K.R. (eds) Intelligent Virtual Agents. IVA 2011. Lecture Notes in Computer Science(), vol 6895. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-23974-8_41
Download citation
DOI: https://doi.org/10.1007/978-3-642-23974-8_41
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-23973-1
Online ISBN: 978-3-642-23974-8
eBook Packages: Computer ScienceComputer Science (R0)