Bayesian reasoning in an abductive mechanism for argument generation and analysis

Abstract

Our argumentation system, NAG, uses Bayesian networks in a user model and in a normative model to assemble and assess arguments which balance persuasiveness with normative correctness. Attentional focus is simulated in both models to select relevant subnetworks for Bayesian propagation. The subnetworks are expanded in an iterative abductive process until argumentative goals are achieved in both models, when the argument is presented to the user. Introduction In this paper, we describe the operation of our argument generation-analysis system, NAG (Nice Argument Generator) . Given a goal proposition, NAG generates nice arguments, i.e., arguments that are normatively strong while also being persuasive for the target audience. NAG also analyzes users' arguments, and prepares rebuttals if appropriate. The focus of this paper is on the generation aspect of our work. Figure 1 shows the main modules of NAG. The Strategist may receive as input a goal proposition or a usergenerated argument. Du...