Applications of Argumentation Schemes

Argumentation schemes capture common, stereotypical patterns of reasoning which are nondeductive and nonmonotonic. As interest in understanding these schemes from a theoretical point of view grows, so too does an awareness within computational work that these schemes might yield powerful techniques in a range of domains. This paper aims to perform two functions. First, to briefly review the literature on argumentation schemes, including the key works by Hastings, Walton and Kienpointner, and to set it in a broader context, adducing concerns from deductivism and presumptive, nonmonotonic reasoning. The second is to consider the various roles argumentation schemes might play in Artificial Intelligence, and in particular to consider (i) how schemes might be characterized as planning operators in domains such as natural language generation, with operationalized schemes representing means of achieving specific (e.g. persuasive) goals; (ii) how schemes might be exploited in AI domains typically characterized by a deductive (if argumentation theoretic) basis for communication, such as communication between intelligent agents; (iii) how schemes might be used in teaching critical thinking, and how they might be characterized in pedagogical software; (iv) more broadly, the representation tasks that can be facilitated using argumentation schemes (drawing particularly upon the wide−ranging discussions held at the Symposium on Argument and Computation held in Scotland in July 2000); and (v) the role that critical questions associated with schemes have in generative, representational and pedagogical aspects of argumentation in AI. The paper concludes with desiderata for a theoretical understanding of argumentation schemes, motivated by the demands of the AI applications discussed, with the aim of stimulating and outlining further foundational research in the area.