Automatic knowledge generation for a persuasion dialogue system with enthymemes

Persuasion dialogues in multi-agent systems are required in situations in which agents debate to defend their viewpoint on a certain topic. In this work, we introduce a dialogue system for persuasion dialogues in which participants can exchange and complete enthymemes using structured argumentation as the underlying knowledge representation formalism. In our approach, the dialogue system provides the means to create arguments from enthymemes by generating assumptions based solely on the enthymeme's structure. Then, arguments are used to determine the dialectical status of the dialogue. We prove that under minimal restrictions, agents involved in a persuasion dialogue can reach an agreement successfully, and they can acquire knowledge such that their mental model is consistent with the outcome of the dialogue.