Transcript TashwinITS

31st October, 2012
CSE-435
Tashwin Kaur Khurana
Overview
Intelligent Tutoring Systems
 Components of an ITS
 Problems
 Case Based Reasoning in ITS
 CBR Methods
 Examples
 Demo
 Summary
 Research areas

ITS

System that provides personalized tutoring by :
 Generates problem solutions automatically
 Represents the learner’s knowledge acquisition processes
 Diagnoses learner’s approach to the solution
 Provides advices and feedback


Intelligent Tutoring System (ITS) - computer-based training
system that incorporate techniques for communicating / transferring
knowledge and skills to students.
ITS = combination of Computer-Aided Instruction (CAI) and
Artificial Intelligence (AI) technology
Conventional Model
Components
of an ITS and their interaction

The Student
Model

The Pedagogical
or Tutor Model

The Domain
Knowledge
The Student Model

Keeps track of all information related to the learner
:
○
○
○
○


Records performance of all the learners
Problems assigned
Complex uncommon problem solutions
Description of approach to the solution with regard to a
specific problem
Allows system to adapt to learner’s needs
Learner’s performance evaluated as a subset of
an expert’s performance --- Drawback!!
The Tutor Systems

Automatic Cognitive analysis
 Path taken by student
 Goal
 Initial competence
 Learning rate

Gets input from the Student model to
make its decision to reflect the differing
needs of each student.
The Domain Knowledge

Contains the information the tutor is
teaching




Concepts
Rules
Axioms
Facts, etc
Information on how to link the data for
optimum performance of the system
 Should be updated if there are any
changes in the domain !

Individualization
Actions required…


Problems!!!
Problem solving
information about each
student should be stored
for a long time
This knowledge must be
used for subsequent
diagnoses and tutorial
decisions!
Case Based
Reasoning
!!!!!!!!!!!!!!!


How to represent
knowledge so it easily
scales up to large
domain?
How to represent domain
knowledge other than
facts and procedure (i.e.
concepts and mental
model)?
CBR in ITS
Represents the Student model and
Domain Knowledge in the form of cases
 These cases can be used to train the
tutorial system for a particular user or
someone with similar properties as that
user
 Cases:

-
Produced by the learner himself
Experience from other learners
On-demand case generation
Predefined cases given by human tutors
Case Based ITS- Uses of CBR

Problem Solving phase:
Find similar problem solved in the past to provide learner with past
experience feedback.

Case-Based Adaptation:
 Allows interactive system to adapt to a specific user (i.e CHEF cooking tutor).
 Can be used to adapt interface component depending on the user’s
knowledge of the software

Case-Base Teaching:
 Assists the learner by providing with useful cases for learning new information

Types:
Static
(Pre-defined case base)
Adaptive
(adapts case base from learner
experience)
Methods

Different type of CBR methods:
○ Classification Approach
 Systems that provide help on well known pre-analyzed cases
○ Problem Solving Approach
 Systems that diagnose solution proposed by the learner and to
identify the problem solving path used
 Systems that support planning
○ Planning Approach
 Systems that support planning

Representation of cases:
○ Complete cases= Problem definition + detailed solution
○ Snippets or partial cases= Sub goals + solution within of
problems
different contexts
CBITS: Examples

CBITS have been used in many different
areas :
-
Medical: CARE-PARTNER
Project Management
Math : PAT
Jurisprudence
Economics
Programming : ELM-Art, SQL-Tutor,
Chess : CACHET
Auto tutor
Example 1 :: ELM-ART LISP
Tutor
Weber and Specht – (1997)
 Episodic learner model

 Stores knowledge about the user in terms of a
collection of episodes which can be viewed as
cases.
 Every solution stated by the user is diagnosed
completely or partially to find problem errors.
 Keeps track of what components were used and
when.

ELM-PE and ELM-ART - only systems that
use this model
ELM Architecture
Representation of subject domain


Consists of rules and concepts in the form of
hierarchically organized frames
Concepts:
 comprise knowledge about:
○ Programming language LISP
○ Common algorithms and problem solving knowledge
 Consists of:
○ plan transformation leading to semantically equivalent
solutions
○ rules

Rules:
 describe different ways to solve the goal stated by the
concept
 Bug rules
Example 2 :: AutoTutor



Web-based intelligent tutoring system developed by
an interdisciplinary research team - Tutoring Research
Group (TRG);
Student contributions: Text box at the bottom of the
screen.
AutoTutor response: one or a combination of
pedagogically appropriate dialog moves conveyed via
synthesized speech, appropriate intonation, facial
expressions, and gestures and also text form on the
screen.
AUTOTUTOR- Authoring Tools
Case-based help - a case study replicating the
process that teacher would go through to create a
curriculum script using the tool. The scenario was
created through an analysis of think aloud
protocols with actual teachers during the
evaluation process.
 Problems and solutions with the terminology,
interface, or concepts were used to generate the
case study components, which were then
incorporated into an overall composite scenario
accessible at any time during the authoring
process.

Auto tutor
•Strengths
not purely domain-specific
easy creation of curriculum script (no
programming skills needed)
robust behaviour
•Weaknesses
shallow understanding only
performance largely depends on Curriculum
Script
Demo!!
Elm ART:
http://art2.ph-freiburg.de/Lisp-Course

Auto tutor:
http://rhea.memphis.edu/JSONWebServic
e/StartFrame1.htm
 Auto tutor emotions
http://wreg.com/2012/05/01/computertechnology-used-as-tutor/

Summary
•
ITS “give” personalized instruction
•
3 main parts are:
•

The Student Model

The Tutor Model

The Domain Knowledge
CBITS use different approach:

Case-Based Adaptation

Case-Based Teaching (Static or Adaptive)
 Classification
 Problem-Solving
 Planning
Research Areas
Developing Authoring tools
 Increase modularity of ITS
 Natural language Modeling
 Emotion recognition
 Collaborative Learning

ITS are becoming more and more
popular as a good assistant to human
tutors…
 6% of Schools in America are using
these tools to teach students in each
and every area !

Thank you!!