The Open UniversitySkip to content
 

Three Approaches to Generating Texts in Different Styles

Reiter, Ehud and Williams, Sandra (2008). Three Approaches to Generating Texts in Different Styles. In: Proceedings of the Symposium on Style in text: creative generation and identification of authorship, Volume 7, The Society for the Study of Artificial Intelligence and the Simulation of Behaviour (AISB 2008), 1-4 April 2008, University of Aberdeen, UK.

Full text available as:
[img]
Preview
PDF (Not Set) - Requires a PDF viewer such as GSview, Xpdf or Adobe Acrobat Reader
Download (190Kb)
URL: http://www.aisb.org.uk/convention/aisb08/proc/
Google Scholar: Look up in Google Scholar

Abstract

Natural Language Generation (nlg) systems generate texts in English and other human languages from non-linguistic input data. Usually there are a large number of possible texts that can communicate the input data, and nlg systems must choose one of these. We argue that style can be used by nlg systems to choose between possible texts, and explore how this can be done by (1) explicit stylistic parameters, (2) imitating a genre style, and (3) imitating an individual’s style.

Item Type: Conference Item
Extra Information: Pages 26-33
Academic Unit/Department: Mathematics, Computing and Technology > Computing & Communications
Interdisciplinary Research Centre: Centre for Research in Computing (CRC)
Item ID: 11393
Depositing User: Sandra Williams
Date Deposited: 18 Aug 2008 06:44
Last Modified: 05 Dec 2010 05:44
URI: http://oro.open.ac.uk/id/eprint/11393
Share this page:

Actions (login may be required)

View Item
Report issue / request change

Policies | Disclaimer

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