ontology-based knowledge representation for a domain-independent problem-solving its framework...

28
Ontology-Based Knowledge Representation for a Domain-Independent Problem-Solving ITS Framework Jean-François Lebeau, Mikaël Fortin, Amir Abdessemed and André Mayers SWEL'08 @ ITS'08 : Ontologies and Semantic Web for Intelligent Educational Systems In conjunction with the 9th International Conference on Intelligent Tutoring Systems Montréal, Canada, June 23-27, 2008

Upload: brianna-weaver

Post on 20-Jan-2016

215 views

Category:

Documents


1 download

TRANSCRIPT

Page 1: Ontology-Based Knowledge Representation for a Domain-Independent Problem-Solving ITS Framework Jean-François Lebeau, Mikaël Fortin, Amir Abdessemed and

Ontology-Based Knowledge Representation for a Domain-Independent

Problem-Solving ITS Framework

Jean-François Lebeau, Mikaël Fortin, Amir Abdessemed and André Mayers

SWEL'08 @ ITS'08 : Ontologies and Semantic Web for Intelligent Educational

Systems

In conjunction with the 9th International Conference on Intelligent Tutoring Systems

Montréal, Canada, June 23-27, 2008

Page 2: Ontology-Based Knowledge Representation for a Domain-Independent Problem-Solving ITS Framework Jean-François Lebeau, Mikaël Fortin, Amir Abdessemed and

2

Overview

1. Introduction2. ASTUS Framework3. Ontology-based KR Approach4. DL-based representation5. Advantages and limitations 6. Conclusion

Page 3: Ontology-Based Knowledge Representation for a Domain-Independent Problem-Solving ITS Framework Jean-François Lebeau, Mikaël Fortin, Amir Abdessemed and

3

Introduction

Goal : Show an approach to use ontologies to facilitate the modeling of knowledge in ITS

What kind of ITS? Problem-Solving ITS ITS based on a cognitive model ITS following the behavior described in

the KVL Tutoring Framework [VanLehn06]

ITS for well-defined domains Domain-independent ITS

Page 4: Ontology-Based Knowledge Representation for a Domain-Independent Problem-Solving ITS Framework Jean-François Lebeau, Mikaël Fortin, Amir Abdessemed and

4

KVL-Framework

The Task domain is defined with knowledge components

Outer loop (task/problem level) and Inner loop (step level)

A Step corresponds to an action in the learning environment UI

Inferences (learning events) correspond to the mental application of a knowledge component

Steps follows one or more inferences

Page 5: Ontology-Based Knowledge Representation for a Domain-Independent Problem-Solving ITS Framework Jean-François Lebeau, Mikaël Fortin, Amir Abdessemed and

5

Cognitive models

Different knowledge components types for procedural and declarative knowledge

Models built with a production system : Procedural knowledge is modeled with

production rules Declarative knowledge is modeled

with facts Procedural knowledge = compiled

declarative knowledge [Anderson95]

Page 6: Ontology-Based Knowledge Representation for a Domain-Independent Problem-Solving ITS Framework Jean-François Lebeau, Mikaël Fortin, Amir Abdessemed and

6

ASTUS Framework (principles)

1. Domains modeled with a pedagogical POV2. All the knowledge components must :

a) Have a single, precise meaningb) Be modeled with glass-box formalisms when

they are of pedagogical interest and efficient black-box formalisms when they are not

c) Use the formalisms that facilitate their interpretation by the higher-level processes

3. Declarative knowledge has a support role

Page 7: Ontology-Based Knowledge Representation for a Domain-Independent Problem-Solving ITS Framework Jean-François Lebeau, Mikaël Fortin, Amir Abdessemed and

7

ASTUS Framework (system)

User Interface

Simulation kernel (optional)

Domain resources

Learnerresources

Pedagogical agent

Learner model agent

Interfacing agent

Expert agent

Working memory

Domain-Independent Agents (Java processes)

Lab (domain package) Learning Environment (LE)

Shared Working Memory built on top of the Jess Rule Engine

Page 8: Ontology-Based Knowledge Representation for a Domain-Independent Problem-Solving ITS Framework Jean-François Lebeau, Mikaël Fortin, Amir Abdessemed and

8

ASTUS Framework (EA/LA) Expert Agent

Step generation and plan recognition Simulations to verify the model and

evaluate the problems Learner Model Agent

Deduction of the applied knowledge component (when EA faces ambiguities)

Assessment of the learner’s mastery of the knowledge components

Page 9: Ontology-Based Knowledge Representation for a Domain-Independent Problem-Solving ITS Framework Jean-François Lebeau, Mikaël Fortin, Amir Abdessemed and

9

ASTUS Framework (PA/IA) Pedagogical Agent

Generation of feedback according to the outputs of EA and LA (inner loop)

Selection of the next task (outer loop) Interfacing Agent [Fortin08]

Production of the feedback on the UI Step recognition Communication of the knowledge

components to the learner as UI elements

Page 10: Ontology-Based Knowledge Representation for a Domain-Independent Problem-Solving ITS Framework Jean-François Lebeau, Mikaël Fortin, Amir Abdessemed and

10

Knowledge in ASTUS

Declarative knowledge is divided in : Semantic (factual) knowledge Episodic (autobiographical) knowledge Goals (intentions, not state)

Procedural knowledge is divided in : Complex procedures (mental plan) Primitive procedures (step) Rules & Queries (perception and mental

op.)

->CPs, R&Q are inferences

Page 11: Ontology-Based Knowledge Representation for a Domain-Independent Problem-Solving ITS Framework Jean-François Lebeau, Mikaël Fortin, Amir Abdessemed and

11

Semantic components

Chunks (DL-Concepts, OWL-Classes) Concepts (building blocks for problem & solution) Relations (weak, optional or temporary

relationship) Functions (unique relationship) Contexts (one for each “stage” of the task)

Attributes (DL-Roles, OWL-Properties) Used for “defining” features Link a chunk instance to data or to another

instance Unknown value Sharable among different chunks

Page 12: Ontology-Based Knowledge Representation for a Domain-Independent Problem-Solving ITS Framework Jean-François Lebeau, Mikaël Fortin, Amir Abdessemed and

12

Instances Instances (OWL/DL-Individuals)

Usually specific for a task “Static” instances at the chunk level

Classification rules Add “Is-a” relationships to an instance

Instantiation rules Create the relations verified in the KB Find the image of a function or create it

Set of instances (1->N attributes)

Page 13: Ontology-Based Knowledge Representation for a Domain-Independent Problem-Solving ITS Framework Jean-François Lebeau, Mikaël Fortin, Amir Abdessemed and

13

Fraction lab (Semantic)

Common Denominator

Valid Common Denominator

Product of Denominators C.D.

Least Common Denominator

Invalid Common

Denominator

Add-Denominators

C.D.

Denominator

: value (integer)

Fraction Operands

Fraction Operand

Fraction Addition Context

Equivalent Fraction Form

Equivalent Numerator

Form

C.D. Form

num

left op. right op.

eqff

left eq. num right eq. num

denom form

F. Given Fraction Fraction

IA creates a instance from the learner’s input (24)

The action script linked to the PP updates the form

Denom. Answer

answer

: value (24)

F. Least C.D.

Page 14: Ontology-Based Knowledge Representation for a Domain-Independent Problem-Solving ITS Framework Jean-François Lebeau, Mikaël Fortin, Amir Abdessemed and

14

Fraction lab (Procedural)Add

FractionsCP Add

Fractions

Get Equivalent Fraction

Get Sum Fraction

Get Mixed

Number

CP Get Equivalent

Fraction

Get Common Denominator

Get Equivalent Numerator

CP Get A. of D.

C.D.Write

Denominator

PP Write Denominator

Get Least C.D.

CP Get Equivalent Numerator

Write Numerator

PP Write Numerator

CP Get P.of D.

C.D.

CP Get Valid C.D.

the over all sequence

3)

2)1)

the PP from previous slide

the completed complex

procedure

the satisfied goal

the current complex

procedure

the next goal

Get Equivalent Numerator

(FractionOperand leftOp)

Get Equivalent Numerator

(FractionOperand leftOp)

Page 15: Ontology-Based Knowledge Representation for a Domain-Independent Problem-Solving ITS Framework Jean-François Lebeau, Mikaël Fortin, Amir Abdessemed and

15

DL-Based representation Development-time parallel representation using the Web

Ontology Language (OWL-DL variant)

Formal definition of the semantic components Defined classes (set of conditions, restrictions, expressions,

…) Disjoint classes Properties characteristics (inverse, transitive, …)

Why is that useful ? “Avoid” simple/multiple inheritance issues Detect inconsistencies Discover hidden taxonomy relationships

Pellet is used for reasoning Protégé-OWL is used for visualization

Page 16: Ontology-Based Knowledge Representation for a Domain-Independent Problem-Solving ITS Framework Jean-François Lebeau, Mikaël Fortin, Amir Abdessemed and

16

Advantages

1. Handling instances added to the WM A method to handle learner’s input A method to reduce domain-specific efforts

2. Clear distinction between different semantic knowledge components to facilitate their interpretation by LA and PA

3. Expert Systems rules backed up with DL-based ontology checking

Page 17: Ontology-Based Knowledge Representation for a Domain-Independent Problem-Solving ITS Framework Jean-François Lebeau, Mikaël Fortin, Amir Abdessemed and

17

Limitations

1. No OWL representation at runtime Limited interpretation of semantic

knowledge No DL-based reasoning Could use the TBox at runtime

2. No glass-box formalisms for rules Some help still possible if the skill is not

mastered SWRL wouldn’t do much better than Jess

Page 18: Ontology-Based Knowledge Representation for a Domain-Independent Problem-Solving ITS Framework Jean-François Lebeau, Mikaël Fortin, Amir Abdessemed and

18

Conclusion

What the ASTUS aims to offers for developing Problem-Solving ITS

Some advantages of an ontology-based representation for the semantic knowledge in this context

An original way to use ontologies in Problem-Solving ITS

Page 19: Ontology-Based Knowledge Representation for a Domain-Independent Problem-Solving ITS Framework Jean-François Lebeau, Mikaël Fortin, Amir Abdessemed and

19

Future work

1. Link different labs with points of contact in their ontologies (and a shared goal)

2. Develop the top-level ontology to enable the use of problem-solving methods

More complex semantic knowledge components

A way to tackle less well-defined domains

Page 20: Ontology-Based Knowledge Representation for a Domain-Independent Problem-Solving ITS Framework Jean-François Lebeau, Mikaël Fortin, Amir Abdessemed and

20

Questions ?

Also, come to see us at the demo session later today !

Page 21: Ontology-Based Knowledge Representation for a Domain-Independent Problem-Solving ITS Framework Jean-François Lebeau, Mikaël Fortin, Amir Abdessemed and

21

References Anderson, J. R., Corbett, A. T., Koedinger, K. R. et Pelletier, R.,

1995. Cognitive tutors : Lessons learned. Journal of Learning Science 4 (2), 167-207.

Fortin, M., Lebeau, J-F. Abdessemed A., Courtemanche, F. and Mayers, A. A Standard Method of Developping User Interfaces for a Generic ITS. The 9th International Conference on Intelligent Tutoring Systems (ITS 2008). June 23-27, Montréal, Qc, Canada.

VanLehn, K. (2006) The behavior of tutoring systems. International Journal of Artificial Intelligence in Education. 16.

Jess http://www.jessrules.com/ Pellet http://pellet.owldl.com/ Protégé-OWL http://protege.stanford.edu/

Page 22: Ontology-Based Knowledge Representation for a Domain-Independent Problem-Solving ITS Framework Jean-François Lebeau, Mikaël Fortin, Amir Abdessemed and

22

Cut slides follow

Page 23: Ontology-Based Knowledge Representation for a Domain-Independent Problem-Solving ITS Framework Jean-François Lebeau, Mikaël Fortin, Amir Abdessemed and

23

Contexts

Domain-independent contexts : Ontological (static instances) Reasoning (rules-created and inputs) Knowledge Base (context instances)

Domain specific contexts : Used by IA as a Model (MVC) for each

stage of the task where the UI is different -> Complete hierarchy from KB to instances

Page 24: Ontology-Based Knowledge Representation for a Domain-Independent Problem-Solving ITS Framework Jean-François Lebeau, Mikaël Fortin, Amir Abdessemed and

24

Knowledge Base Read access trough queries

Queries return snapshots of instances Only attributes values are saved Episodic knowledge components

Write access trough scripts Trigger : primitive procedures, context

initialization and context transition Effects : Add/Modify/Remove instances

Add always done through a context instance

Page 25: Ontology-Based Knowledge Representation for a Domain-Independent Problem-Solving ITS Framework Jean-François Lebeau, Mikaël Fortin, Amir Abdessemed and

25

Simulation kernel Domain-specific objects grafted to

instances Scripts use them to produce their

effects Useful to generate instances from

calculation Genetics lab

Can also have an internal state Requirement for “simulator-based” labs

Page 26: Ontology-Based Knowledge Representation for a Domain-Independent Problem-Solving ITS Framework Jean-François Lebeau, Mikaël Fortin, Amir Abdessemed and

26

Procedural vs Declarative

Declarative knowledge : Perimeter of a triangle def.: P= a + b + c A representation of a triangle : T{a, b, c} An concrete triangle : T1(a[3], b[4], 5[5])

Procedural knowledge : A skill that creates P1 from T1

Declarative knowledge in a compiled form [Anderson95]

Page 27: Ontology-Based Knowledge Representation for a Domain-Independent Problem-Solving ITS Framework Jean-François Lebeau, Mikaël Fortin, Amir Abdessemed and

27

Page 28: Ontology-Based Knowledge Representation for a Domain-Independent Problem-Solving ITS Framework Jean-François Lebeau, Mikaël Fortin, Amir Abdessemed and

Back