T2D: Generating Dialogues Between Virtual Agents Automatically from Text

Piwek, Paul; Hernault, Hugo; Prendinger, Helmut and Ishizuka, Mitsuru (2007). T2D: Generating Dialogues Between Virtual Agents Automatically from Text. In: Proceedings of 7th International Conference on Intelligent Virtual Agents, 17-19 September 2007, Paris.

Full text available as:

Preview

PDF (Not Set) - Requires a PDF viewer such as GSview, Xpdf or Adobe Acrobat Reader Download (673Kb)

URL:	http://www.springerlink.com/content/p6265q6h813120...
DOI (Digital Object Identifier) Link:	http://dx.doi.org/doi:10.1007/978-3-540-74997-4_16
Google Scholar:	Look up in Google Scholar

Abstract

The Text2Dialogue (T2D) system that we are developing allows digital content creators to generate attractive multi-modal dialogues presented by two virtual agents–by simply providing textual information as input. We use Rhetorical Structure Theory (RST) to decompose text into segments and to identify rhetorical discourse relations between them. These are then 'acted out' by two 3D agents using synthetic speech and appropriate conversational gestures. In this paper, we present version 1.0 of the T2D system and focus on the novel technique that it uses for mapping rhetorical relations to question–answer pairs, thus transforming (monological) text into a form that supports dialogues between virtual agents.

Item Type:	Conference Item
ISBN:	3-540-74996-9, 978-3-540-74996-7
ISSN:	1611-3349
Keywords:	Embodied Conversational Agents, Virtual Agents, Intelligent Agents, Multimedia, Dialogue, Natural Language Generation
Academic Unit/Department:	Mathematics, Computing and Technology > Computing
Interdisciplinary Research Centre:	Centre for Research in Computing (CRC)
Item ID:	12182
Depositing User:	Paul Piwek
Date Deposited:	31 Oct 2008 00:32
Last Modified:	25 Jan 2011 16:07
URI:	http://oro.open.ac.uk/id/eprint/12182

Available Versions of this Item

• T2D: Generating Dialogues Between Virtual Agents Automatically from Text. (deposited 18 Sep 2007)
  • T2D: Generating Dialogues Between Virtual Agents Automatically from Text. (deposited 31 Oct 2008 00:32) [Currently Displayed]

Actions (login may be required)

	View Item
RDF+XMLBibTeXRDF+N-TriplesJSONDublin CoreAtomOAI-ORE Resource Map (Atom Format)Simple MetadataReferMETSOAI-ORE Resource Map (RDF Format)HTML CitationASCII CitationMultiline CSVRefMan RIS Format (UTF-8)OpenURL ContextObjectEndNoteMODSOpenURL ContextObject in SpanMPEG-21 DIDLEP3 XMLRefMan RIS FormatRDF+N3Eprints Application Profile	Public: Report issue / request change