Book | Chapter
Generating texts in different styles
pp. 59-75
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.
Publication details
Published in:
Argamon Shlomo, Burns Kevin, Dubnov Shlomo (2010) The structure of style: algorithmic approaches to understanding manner and meaning. Dordrecht, Springer.
Pages: 59-75
DOI: 10.1007/978-3-642-12337-5_4
Full citation:
Reiter Ehud, Williams Sandra (2010) „Generating texts in different styles“, In: S. Argamon, K. Burns & S. Dubnov (eds.), The structure of style, Dordrecht, Springer, 59–75.