Architecture for Building Conversational Agents that Support Collaborative Learning

Tutorial Dialog Systems that employ Conversational Agents (CAs) to deliver instructional content to learners in one-on-one tutoring settings have been shown to be effective in multiple learning domains by multiple research groups. Our work focuses on extending this successful learning technology to collaborative learning settings involving two or more learners interacting with one or more agents. Experience from extending existing techniques for developing conversational agents into multiple-learner settings highlights two underlying assumptions from the one-learner setting that do not generalize well to the multiuser setting, and thus cause difficulties. These assumptions include what we refer to as the near-even participation assumption and the known addressee assumption. A new software architecture called Basilica that allows us to address and overcome these limitations is a major contribution of this article. The Basilica architecture adopts an object-oriented approach to represent agents as a network composed of what we refer to as behavioral components because they enable the agents to engage in rich conversational behaviors. Additionally, we describe three specific conversational agents built using Basilica in order to illustrate the desirable properties of this new architecture.