Estimating Second-Order Arguments in Dialogical Settings

This paper proposes mechanisms for agents to model other agents’ arguments, so that modelling agents can anticipate the likelihood that their interlocutors can constructs arguments in dialogues. In contrast with existing works on “opponent modelling” which treat arguments as abstract entities, the likelihood that an agent can construct an argument is derived from the likelihoods that it possesses the beliefs required to construct the argument. We therefore also address how a modeller can quantify the certainty that its interlocutor possesses beliefs based on previous dialogues, and membership of interlocutors in communities.