Advanced Features of Argumentation for Argument Mining

This chapter addresses a few complex challenges for argument mining and for argumentation more generally. It discusses two topics that are crucial in argument mining: first, the need for knowledge and inference to bind a claim with an attack or a support when they are not adjacent, and second, the need to present a synthesis of the arguments that have been mined. Designing an argument synthesis is a delicate task that requires taking into account users' profiles, for example, the type of information that is useful to them, the features which are the most prominent, and the level of granularity they expect. In natural language generation, the main projects on argumentation generation were developed as early as 2000 by I. Zukerman et al. and then by A. Fiedler and H. Horacek.