An intelligent tutoring system that generates a natural language dialogue using dynamic multi-level planning Chong Woo Woo a , Martha W. Evens b, * , Reva Freedman c , Michael Glass d , Leem Seop Shim e , Yuemei Zhang f , Yujian Zhou g , Joel Michael h a School of Computer Science, Kookmin University, 861-1 Chongnung-Dong, Sungbuk-Ku, Seoul, Republic of Korea b Computer Science Department, Illinois Institute of Technology, Room 236, 10 West 31st Street, Chicago, IL 60616, USA c Northern Illinois University, De Kalb, IL 60115, USA d Valparaiso University, Valparaiso, IN 46383, USA e HS Tech, Inc., 26500 Agoura Road, Suite #108, Calabasas, CA 91302, USA f Wells Fargo - N9301-01J, 255 Second Avenue South, Minneapolis, MN 55479, USA g WebEx Communications, Inc., 3979 Freedom Circle, Santa Clara, CA 95054, USA h Department of Molecular Biophysics and Physiology, Rush Medical College, 1750 West Harrison, Chicago, IL 60612, USA Received 16 February 2005; received in revised form 14 October 2005; accepted 21 October 2005 Artificial Intelligence in Medicine (2006) 38, 25—46 http://www.intl.elsevierhealth.com/journals/aiim KEYWORDS Intelligent tutoring system; Natural language dialogue; Instructional planning; Dynamic planning; Hierarchical planning; Reactive planning; Language understanding; Dialogue generation Summary Objective: The objective of this research was to build an intelligent tutoring system capable of carrying on a natural language dialogue with a student who is solving a problem in physiology. Previous experiments have shown that students need practice in qualitative causal reasoning to internalize new knowledge and to apply it effec- tively and that they learn by putting their ideas into words. Methods: Analysis of a corpus of 75 hour-long tutoring sessions carried on in keyboard- to-keyboard style by two professors of physiology at Rush Medical College tutoring first-year medical students provided the rules used in tutoring strategies and tactics, parsing, and text generation. The system presents the student with a perturbation to the blood pressure, asks for qualitative predictions of the changes produced in seven important cardiovascular variables, and then launches a dialogue to correct any errors * Corresponding author. Tel.: +1 312 567 5153; fax: +1 312 567 5067. E-mail address: evens@iit.edu (M.W. Evens). 0933-3657/$ — see front matter # 2005 Elsevier B.V. All rights reserved. doi:10.1016/j.artmed.2005.10.004