The Open UniversitySkip to content
 

Generating texts in different styles

Reiter, Ehud and Williams, Sandra (2010). Generating texts in different styles. In: Argamon, Shlomo; Burns, Kevin and Dubnov, Shlomo eds. The Structure of Style: Algorithmic Approaches to Manner and Meaning. Heidelberg: Springer, pp. 59–78.

Full text available as:
Full text not publicly available
Due to copyright restrictions, this file is not available for public download
Click here to request a copy from the OU Author.
URL: http://www.springer.com/computer/database+manageme...
DOI (Digital Object Identifier) Link: http://dx.doi.org/10.1007/978-3-642-12337-5
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. This decision can partially be based on style (interpreted broadly). We explore three mechanisms for incorporating style into nlg choice-making: (1) explicit stylistic parameters, (2) imitating a genre style, and (3) imitating an individual's style.

Item Type: Book Chapter
Copyright Holders: 2010 Springer-Verlag
ISBN: 3-642-12336-8, 978-3-642-12336-8
Academic Unit/Department: Mathematics, Computing and Technology > Computing & Communications
Interdisciplinary Research Centre: Centre for Research in Computing (CRC)
Related URLs:
Item ID: 24736
Depositing User: Sandra Williams
Date Deposited: 19 Nov 2010 12:10
Last Modified: 11 Dec 2012 05:21
URI: http://oro.open.ac.uk/id/eprint/24736
Share this page:

Altmetrics

Scopus Citations

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