Ranking-Based Semantics for Sets of Attacking Arguments

Bruno Yun (1) , Srdjan Vesic (2) , Madalina Croitoru (3)

1 University of Aberdeen
2 CRIL - Centre de Recherche en Informatique de Lens
3 GRAPHIK - Graphs for Inferences on Knowledge

Argumentation is a process of evaluating and comparing sets of arguments. Ranking-based semantics received a lot of attention recently. All of the semantics introduced so far are applicable to binary attack relations. In this paper, we study a more general case when sets of arguments can jointly attack an argument. We generalise existing postulates for ranking-based semantics to fit this framework, define a general variant of h-categoriser, prove that it converges for every argumentation framework and study the postulates it satisfies. We also study the link between binary and hypergraph version of h-categoriser.

Domaines: Informatique [cs]

Bruno Yun, Srdjan Vesic, Madalina Croitoru. Ranking-Based Semantics for Sets of Attacking Arguments. AAAI 2020 - 34th AAAI Conference on Artificial Intelligence, Feb 2020, New York, United States. pp.3033-3040, ⟨10.1609/aaai.v34i03.5697⟩. ⟨lirmm-02374712⟩