Using a domain ontology and semantic search in an elearning environment
Download
1 / 22

Using a domain-ontology and semantic search in an eLearning ... - PowerPoint PPT Presentation


  • 322 Views
  • Uploaded on

Using a domain-ontology and semantic search in an eLearning environment Lothar Lemnitzer, Kiril Simov, Petya Osenova, Eelco Mossel and Paola Monachesi International Conference on Engineering Education, Instructional Technology, Assessment, and E-learning (EIAE 07), December 2007

loader
I am the owner, or an agent authorized to act on behalf of the owner, of the copyrighted work described.
capcha
Download Presentation

PowerPoint Slideshow about 'Using a domain-ontology and semantic search in an eLearning ...' - jana


An Image/Link below is provided (as is) to download presentation

Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author.While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server.


- - - - - - - - - - - - - - - - - - - - - - - - - - E N D - - - - - - - - - - - - - - - - - - - - - - - - - -
Presentation Transcript
Using a domain ontology and semantic search in an elearning environment l.jpg

Using a domain-ontology and semantic search in an eLearning environment

Lothar Lemnitzer, Kiril Simov, Petya Osenova, Eelco Mossel and Paola Monachesi

International Conference on Engineering Education, Instructional Technology, Assessment, and E-learning(EIAE 07), December 2007


Outline of the talk l.jpg
Outline of the Talk environment

  • Introductory notes

  • LT4eL Domain Ontology

  • Ontology-based Lexicon Model

  • Semantic annotation of learning objects

  • Semantic Search

  • Evaluation

  • Conclusions


Introductory notes 1 l.jpg
Introductory notes (1) environment

  • LT4eL European project aims at demonstrating the relevance of language technology and ontologies for improving learning management systems (LMS)

  • Multilingual approach


Slide4 l.jpg

LMS environment

User Profile

LING. PROCESSOR

EN

GE

Lemmatizer, POS, Partial Parser

Ontology

CROSSLINGUAL RETRIEVAL

Lexikon

Lexikon

Lexicon

Lexikon

Lexicon

Lexikon

Lexikon

Lexikon

Lexikon

RO

PT

PL

CZ

BG

DT

MT

PT

GE

PL

RO

DT

MT

EN

CZ

Documents SCORM

Pseudo-Struct.

Basic XML

CONVERTOR 2

Documents SCORM

Documents HTML

Pseudo-Struct

Glossary

CONVERTOR 1

Metadata (Keywords)

Ling. Annot XML

BG

EN

Documents User

(PDF, DOC, HTML,

SCORM,XML)

REPOSITORY


Introductory notes 2 l.jpg
Introductory notes (2) environment

We created and use

  • A domain ontology

  • Lexicons for several languages

  • (Linguistically, semantically) annotated learning objects

    for semantic search


Lt4el domain ontology general issues l.jpg
LT4eL Domain Ontology: general issues environment

  • The domain: Computer Science for Non-Computer Scientists

  • The role of the ontology: indexing of the Los, semantic search


Lt4el domain ontology creation l.jpg
LT4eL Domain Ontology: creation environment

BG

Keywords

annotation

Translation

into EN

EN

PT

Definition

Collection

CZ

Concept

creation

NL

RO

MT

PO


Current state of the ontology l.jpg
Current state of the ontology environment

  • about 750 domain concepts,

  • about 50 concepts from DOLCE

  • about 250 intermediate concepts from OntoWordNet

  • about 200 new concepts extracted from LOs


Ontology based lexicon model 1 l.jpg
Ontology-Based Lexicon Model (1) environment

  • The lexicons represent the main interface between the user's query and the ontology

  • Lexicons for all languages of the project have been created


Ontology based lexicon model 2 l.jpg
Ontology-Based Lexicon Model (2) environment

  • all the important concepts within a domain should be included

  • we allow the lexicons to contain also non-lexicalized phrases (e.g. mapping variety)


Example from the dutch lexicon l.jpg
Example from the Dutch lexicon environment

<entryid="id60">

<owl:Classrdf:about="lt4el:BarWithButtons">

<rdfs:subClassOf>

<owl:Classrdf:about="lt4el:Window"/>

</rdfs:subClassOf>

</owl:Class>

<def>A horizontal or vertical bar as a part of a window,

that contains buttons, icons.</def>

<termglang="nl">

<termshead="1">werkbalk</term>

<term>balk</term>

<termtype="nonlex">balk met knoppen</term>

<term>menubalk</term>

</termg>

</entry>


Semantic annotation of learning objects l.jpg
Semantic Annotation of Learning Objects environment

  • Within the project we performed both types of annotation,:

    • inline

    • through metadata

  • The inline annotation will be used:

    • as a mechanism to validate the coverage of the ontology;

    • for semantic retrieval


Semantic search l.jpg
Semantic Search environment

Aims at improved retrieval of documents

  • Find documents that would not be found by simple full text search; e.g. search for “screen” retrieves documents that contain “monitor”

    Crosslingual

  • Find documents in languages different from search/interface language;

  • Advantage: No need to translate search query


Slide14 l.jpg

Search procedure environment

Search-Term(s)

Search-Concepts

Retrieved Documents

Lexicons:contain term-concept mappings

Ontology: contains concepts

DocumentDatabase

select concepts

Visualisation


Search procedure l.jpg
Search procedure environment

  • Provide a search query in Language L(1)

  • Find terms in lexicons of L(1) that reflect search query

  • Find relevant documents for concepts in L(1), L(2) etc.

  • Rank for set of found documents

  • Create ontology fragment containing necessary information to present concept neighbourhood


Slide16 l.jpg

Search with ILIAS environment


Evaluation of semantic search l.jpg
Evaluation of Semantic Search environment

Aspects:

  • Does semantic search return correct results, i.e. appropriate documents?

  • How easy is it to use semantic search?

  • Are the results better (precision/recall) than with keyword search or full text search?

  • Does semantic search improve learning processes?


Formal evaluation l.jpg
Formal Evaluation environment

Procedure: Search for paragraphs with query

formed on the basis of Concepts from ontology

#Program* + #Slide

formed on the basis of Terms in the lexicons

Program, Software, Editor, Slide

For a variety of languages.


Conclusions l.jpg
Conclusions environment


Conclusions21 l.jpg
Conclusions environment

  • Evaluation experiment showed the superiority of semantic search over simple full text search

  • Our architecture introduces cross-lingual search into the learning process


Contact l.jpg
Contact environment

  • www.lt4el.eu

  • Contact for information: [email protected]


ad