The Open UniversitySkip to content
 

Reference and Gestures in Dialogue Generation: Three Studies with Embodied Conversational Agents

Piwek, Paul; Masthoff, Judith and Bergenstrahle, Malin (2005). Reference and Gestures in Dialogue Generation: Three Studies with Embodied Conversational Agents. In: Proceedings of AISB05 Joint Symposium on Virtual Social Agents Symposium, 12 - 15 April 2005, University of Herfordshire, UK.

Full text available as:
[img]
Preview
PDF (Not Set) - Requires a PDF viewer such as GSview, Xpdf or Adobe Acrobat Reader
Download (818Kb)
URL: http://www.aisb.org.uk/publications/proceedings/pr...
Google Scholar: Look up in Google Scholar

Abstract

This paper reports on three studies into social presence cues which were carried out in the context of the NECA (Net-environment for Embodied Emotional Conversational Agents) project and the EPOCH network. The first study concerns the generation of referring expressions. We adopted an existing algorithm for generating referring expressions such that it could run according to an egocentric and a neutral strategy. In an evaluation study, we found that the two strategies were correlated with the perceived friendliness of the speaker. In the second and the third study, we evaluated the gestures that were generated by the NECA system. In this paper, we briefly summarize the most salient results of these two studies. They concern the effect of gestures on perceived quality of speech and information retention.

Item Type: Conference Item
Academic Unit/Department: Mathematics, Computing and Technology > Computing & Communications
Mathematics, Computing and Technology
Interdisciplinary Research Centre: Centre for Research in Computing (CRC)
Item ID: 12137
Depositing User: Paul Piwek
Date Deposited: 29 Oct 2008 21:16
Last Modified: 23 Feb 2016 23:05
URI: http://oro.open.ac.uk/id/eprint/12137
Share this page:

► Automated document suggestions from open access sources

Download history for this item

These details should be considered as only a guide to the number of downloads performed manually. Algorithmic methods have been applied in an attempt to remove automated downloads from the displayed statistics but no guarantee can be made as to the accuracy of the figures.

Actions (login may be required)

Policies | Disclaimer

© The Open University   + 44 (0)870 333 4340   general-enquiries@open.ac.uk