Acquisition of New Knowledge to Manage Conversation in TutorJ

Abstract

This paper presents new conversation modules developed for TutorJ to support the use of meta-cognitive strategies in the learners. TutorJ is an Intelligent Tutoring System able to interact with users to assess their skills, and improve their knowledge in a specific domain. New models are devoted to plan the conversation and to acquire new knowledge from semi-structured data sources. Conversation planning is based on probabilistic techniques. Knowledge acquisition is based on retrieval, transformation and alignment of data from wikis to enrich the replies to students questions.