G. Carenini, and J. Moore. International Conference on Natural Language Generation, page 47--54. (2000)
Abstract
We propose an argumentation strategy for generating evaluative arguments that can be applied in systems serving as personal assistants or advisors. By following guidelines from argumentation theory and by employing a quantitative model of the user's preferences, the strategy generates arguments that are tailored to the user, properly arranged and concise. Our proposal extends the scope of previous approaches both in terms of types of arguments generated, and in terms of compliance with...
International Conference on Natural Language Generation
year
2000
pages
47--54
posted-at
2005-11-22 14:57:43
priority
0
citeulike-article-id
404493
comment
The authors propose a good summary of the guidelines provided by argumenative theory.
They then use Ädditive Multiattribute Value Function" to model the user values and preference and compute a strategy for the argument generation.
%0 Conference Paper
%1 carenini00strategy
%A Carenini, G.
%A Moore, J.
%B International Conference on Natural Language Generation
%D 2000
%K argument, argumentation, generation
%P 47--54
%T A Strategy for Generating Evaluative Arguments
%U http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.13.2981
%X We propose an argumentation strategy for generating evaluative arguments that can be applied in systems serving as personal assistants or advisors. By following guidelines from argumentation theory and by employing a quantitative model of the user's preferences, the strategy generates arguments that are tailored to the user, properly arranged and concise. Our proposal extends the scope of previous approaches both in terms of types of arguments generated, and in terms of compliance with...
@inproceedings{carenini00strategy,
abstract = {{We propose an argumentation strategy for generating evaluative arguments that can be applied in systems serving as personal assistants or advisors. By following guidelines from argumentation theory and by employing a quantitative model of the user's preferences, the strategy generates arguments that are tailored to the user, properly arranged and concise. Our proposal extends the scope of previous approaches both in terms of types of arguments generated, and in terms of compliance with...}},
added-at = {2010-12-17T18:47:41.000+0100},
author = {Carenini, G. and Moore, J.},
biburl = {https://www.bibsonomy.org/bibtex/227a4336846acf9b7cad782c104ccde10/mortimer_m8},
booktitle = {International Conference on Natural Language Generation},
citeulike-article-id = {404493},
citeulike-linkout-0 = {http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.13.2981},
comment = {The authors propose a good summary of the guidelines provided by argumenative theory.
They then use "Additive Multiattribute Value Function" to model the user values and preference and compute a strategy for the argument generation.},
interhash = {9bfc8d443125a67985cca4de5dd10826},
intrahash = {27a4336846acf9b7cad782c104ccde10},
keywords = {argument, argumentation, generation},
pages = {47--54},
posted-at = {2005-11-22 14:57:43},
priority = {0},
timestamp = {2010-12-20T11:11:25.000+0100},
title = {{A Strategy for Generating Evaluative Arguments}},
url = {http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.13.2981},
year = 2000
}