AutoTutor is an intelligent tutoring system that helps students learn science, technology, and other technical subject matters by holding conversations with the student in natural language. AutoTutor's dialogues are organized around difficult questions and problems that require reasoning and explanations in the answers. The major components of AutoTutor include an animated conversational agent, dialogue management, speech act classification, a curriculum script, semantic evaluation of student contributions, and electronic documents (e.g., textbook and glossary). This chapter describes the computational components of AutoTutor, the similarity of these components to human tutors, and some challenges in handling smooth dialogue. We describe some ways that AutoTutor has been evaluated with respect to learning gains, conversation quality, and learner impressions. AutoTutor is sufficiently modular that the content and dialogue mechanisms can be modified with authoring tools. AutoTutor has spawned a number of other agent-based learning environments, such as AutoTutor-lite, Operation Aries!, and Guru. © 2012, IGI Global.
Applied Natural Language Processing: Identification, Investigation and Resolution
Graesser, A., D'Mello, S., Hu, X., Cai, Z., Olney, A., & Morgan, B. (2011). AutoTutor. Applied Natural Language Processing: Identification, Investigation and Resolution, 169-187. https://doi.org/10.4018/978-1-60960-741-8.ch010