Natural Language Arguments: Results and Challenges

4^th December 2012, 16:00 Ashton Lecture Theatre
Dr. Elena Cabrio and Dr. Serena Villata
INRIA
Sophia Antipolis
France

Abstract

With the growing use of the Social Web, an increasing number of applications
for exchanging opinions with other people are becoming available online.
These applications are widely adopted with the consequence that the number
of opinions about the debated issues increases. In order to cut in on a debate,
the participants need first to evaluate the opinions in favour or against the
debated issue. Argumentation theory proposes algorithms and semantics to
evaluate the set of accepted arguments, given the conflicts among them. The
main problem is how to automatically generate the arguments from the
natural language formulation of the opinions used in these applications.
We address this problem by proposing and evaluating the use of textual
entailment to generate and identify the relations among the arguments. We
evaluate our combined approach on a dataset extracted from Debatepedia
coupling textual entailment together with abstract bipolar argumentation to
identify and label the arguments that are accepted in the considered online
debates. Moreover, since there is not a unique interpretation of the support
relation, and in particular, different combinations of additional attacks among
the arguments involved in a support relation are proposed, we provide a data
driven analysis of the notion of support basing on these natural language
debates.
We discuss and evaluate the support relation among arguments with respect
to the more specific notion of textual entailment in the natural language
processing field, carrying out a comparative evaluation of proposals of
additional attacks on a sample of natural language arguments extracted from
Debatepedia.