Title :
A syntactical approach to diagnosing multiple bugs in an intelligent tutoring system
Author :
Huang, Zhongping ; Tokuda, Naoyuki
Author_Institution :
Dept. of Comput. Sci., Utsunomiya Univ., Japan
fDate :
3/1/1996 12:00:00 AM
Abstract :
This paper develops a buggy model-based intelligent tutoring system (ITS) capable of diagnosing multiple bugs, pinpointing not only their types but also their exact locations involved. The procedural grammar of context free type is used not only to decompose a complicated procedure involving possible steps of both correct and incorrect arithmetic into simplest, `primitive´ procedures but also to express control knowledge essential to implementing an efficient parser. An efficient parser is implemented by narrowing down the search space, exploiting the control knowledge, the selection and consistency conditions in selecting rules in parsing. Parsing of superficial symptoms such as a student´s errors in arithmetic essentially reveals the deep structure of the buggy knowledge of the student so that teachers may now devise and offer a more effective means of instructions for acquiring the correct skill of arithmetic
Keywords :
context-free grammars; intelligent tutoring systems; ITS; buggy model-based intelligent tutoring system; context-free procedural grammar; correct arithmetic; efficient parser; incorrect arithmetic; multiple bug diagnosis; superficial symptoms; Arithmetic; Computational complexity; Computer bugs; Computer errors; Computer science; Error correction; Humans; Intelligent structures; Intelligent systems; Legged locomotion;
Journal_Title :
Systems, Man and Cybernetics, Part A: Systems and Humans, IEEE Transactions on
DOI :
10.1109/3468.485756