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 AISB 2008 Symposium on Style in Text: Creative Generation and Identification of Authorship, 1-4 Apr 2008, University of Aberdeen, UK, The Society for the Study of Artificial Intelligence and Simulation of Behaviour, pp. 26–33.

URL: https://aisb.org.uk/wp-content/uploads/2019/12/Fin...

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.

Viewing alternatives

Look up in Google Scholar

Download history

Item Actions

Export

About

CORE (COnnecting REpositories)