The Open UniversitySkip to content

Generating Dialogues for Virtual Agents Using Nested Textual Coherence Relations

Hernault, Hugo; Piwek, Paul; Prendinger, Helmut and Ishizuka, Mitsuru (2008). Generating Dialogues for Virtual Agents Using Nested Textual Coherence Relations. In: ed. Intelligent Virtual Agents, Volume 5208. Springer, pp. 139–145.

Full text available as:
PDF (Not Set) - Requires a PDF viewer such as GSview, Xpdf or Adobe Acrobat Reader
Download (176Kb)
DOI (Digital Object Identifier) Link:
Google Scholar: Look up in Google Scholar


This paper describes recent advances on the Text2Dialogue system we are currently developing. Our system enables automatic transformation of monological text into a dialogue. The dialogue is then 'acted out' by virtual agents, using synthetic speech and gestures. In this paper, we focus on the monologue-to-dialogue transformation, and describe how it uses textual coherence relations to map text segments to query–answer pairs between an expert and a layman agent. By creating mapping rules for a few well-selected relations, we can produce coherent dialogues with proper assignment of turns for the speakers in a majority of cases.

Item Type: Book Chapter
ISBN: 3-540-85482-7, 978-3-540-85482-1
ISSN: 0302-9743
Academic Unit/Department: Mathematics, Computing and Technology > Computing & Communications
Mathematics, Computing and Technology
Interdisciplinary Research Centre: Centre for Research in Computing (CRC)
Item ID: 12126
Depositing User: Paul Piwek
Date Deposited: 27 Oct 2008 02:28
Last Modified: 14 Jan 2016 22:03
Share this page:


Scopus Citations

Actions (login may be required)

Policies | Disclaimer

© The Open University   + 44 (0)870 333 4340