Section: New Results

Combining Argumentation Theory and Natural Language Processing

Participants : Elena Cabrio, Serena Villata.

With the growing use of the Social Web, an increasing number of applications for exchanging opinions with other people are becoming available online. To cut in on a debate, the participants need first to evaluate the opinions of the other users to detect whether they are in favor or against the debated issue. An automated framework to detect the relations among the arguments represented by the natural language formulation of the users opinions is therefore needed. The work in this area proposes the use of natural language techniques to identify the arguments and their relations. In particular, the textual entailment approach is adopted, i.e. a generic framework for applied semantics, where linguistic objects are mapped by means of semantic inferences at a textual level. Textual entailment is then coupled with an abstract bipolar argumentation system which allows to identify the arguments that are accepted in the considered online debate.

The same framework is also experimented to support the management of argumentative discussions in wiki-like platforms. The results of this research have been published in [16] , [28] , [29] .