Integrating Perceptual Learning with External World Knowledge in a Simulated Student

Systems for smart authoring of automated tutors, like SimStudent, have been mostly applied in well-defined problem-solving domains where little real-world background knowledge is needed, like math. Here we explore the generality of these methods by considering a very different task, article selection in English, where little problem-solving is done, but where complex prior perceptual skills and large amounts of background knowledge are needed. This background knowledge includes the ability to parse text and the extensive understanding of semantics of English words and phrases. We show that good performance can be obtained by coupling SimStudent with appropriate broad-coverage linguistic tools. Performance can be improved further on this task by extending one of the learning mechanisms used by SimStudent so that it will accept less-accurate production rule conditions, and prioritize learned production rules by accuracy. Experimental results show that the extended SimStudent successfully learns the tutored article selection grammar rules, and can be used to discover a student model that predicts human student behavior as well as the human-generated model.

[1]  John R. Anderson,et al.  Rules of the Mind , 1993 .

[2]  Kenneth R. Koedinger,et al.  A Machine Learning Approach for Automatic Student Model Discovery , 2011, EDM.

[3]  Kenneth R. Koedinger,et al.  Efficient Cross-Domain Learning of Complex Skills , 2012, ITS.

[4]  Thomas G. Dietterich.  Learning at the Knowledge Level , 1986, Machine Learning.

[5]  Luc De Raedt,et al.  Proceedings of the 20th European Conference on Artificial Intelligence , 2012 .

[6]  Vincent Aleven,et al.  Concepts, Structures, and Goals: Redefining Ill-Definedness , 2009, Int. J. Artif. Intell. Educ..

[7]  Tessa A. Lau,et al.  Programming by demonstration: an inductive learning formulation , 1998, IUI '99.

[8]  Gordon I. McCalla,et al.  The Fawlty Article Tutor , 1992, Intelligent Tutoring Systems.

[9]  Kenneth R. Koedinger,et al.  A Computational Model of How Learner Errors Arise from Weak Prior Knowledge , 2009 .

[10]  Frank J. Lee,et al.  Production Compilation: A Simple Mechanism to Model Complex Skill Acquisition , 2003, Hum. Factors.

[11]  Frank E. Ritter,et al.  OPTIMIST: A New Conflict Resolution Algorithm for ACT-R , 2004, ICCM.

[12]  J. Bresnan,et al.  Spoken syntax: The phonetics of giving a hand in New Zealand English , 2006 .

[13]  Allen Newell,et al.  Chunking in Soar: The anatomy of a general learning mechanism , 1985, Machine Learning.

[14]  Kenneth R. Koedinger,et al.  Learning Factors Analysis - A General Method for Cognitive Model Evaluation and Improvement , 2006, Intelligent Tutoring Systems.

[15]  Antonija Mitrovic,et al.  ASPIRE: An Authoring System and Deployment Environment for Constraint-Based Tutors , 2009, Int. J. Artif. Intell. Educ..

[16]  H A Simon,et al.  The theory of learning by doing. , 1979, Psychological review.

[17]  H. Simon,et al.  Perception in chess , 1973 .

[18]  Kenneth R. Koedinger,et al.  Creating Features from a Learned Grammar in a Simulated Student , 2012, ECAI.

[19]  Kenneth R. Koedinger,et al.  Analogies, Explanations, and Practice: Examining How Task Types Affect Second Language Grammar Learning , 2010, Intelligent Tutoring Systems.

[20]  Kenneth R. Koedinger,et al.  Automated Student Model Improvement , 2012, EDM.

[21]  Luc De Raedt,et al.  Inductive Logic Programming: Theory and Methods , 1994, J. Log. Program..

[22]  Kurt VanLehn,et al.  Applications of simulated students: an exploration , 1994 .

[23]  Dan Klein,et al.  Accurate Unlexicalized Parsing , 2003, ACL.