Skip to content Skip to navigation
University of Warwick
  • Study
  • |
  • Research
  • |
  • Business
  • |
  • Alumni
  • |
  • News
  • |
  • About

University of Warwick
Publications service & WRAP

Highlight your research

  • WRAP
    • Home
    • Search WRAP
    • Browse by Warwick Author
    • Browse WRAP by Year
    • Browse WRAP by Subject
    • Browse WRAP by Department
    • Browse WRAP by Funder
    • Browse Theses by Department
  • Publications Service
    • Home
    • Search Publications Service
    • Browse by Warwick Author
    • Browse Publications service by Year
    • Browse Publications service by Subject
    • Browse Publications service by Department
    • Browse Publications service by Funder
  • Help & Advice
University of Warwick

The Library

  • Login
  • Admin

Ontologies for automatic question generation

Tools
- Tools
+ Tools

Ibrahim Teo, Noor Hasimah (2019) Ontologies for automatic question generation. PhD thesis, University of Warwick.

[img]
Preview
PDF
WRAP_Theses_IbrahimTeo_2019.pdf - Submitted Version - Requires a PDF viewer.

Download (2126Kb) | Preview
Official URL: http://webcat.warwick.ac.uk/record=b3469934~S15

Request Changes to record.

Abstract

Assessment is an important tool for formal learning, especially in higher education. At present, many universities use online assessment systems where questions are entered manually into a question bank system. This kind of system requires the instructor’s time and effort to construct questions manually. The main aim of this thesis is, therefore, to contribute to the investigation of new question generation strategies for short/long answer questions in order to allow for the development of automatic factual question generation from an ontology for educational assessment purposes. This research is guided by four research questions: (1) How well can an ontology be used for generating factual assessment questions? (2) How can questions be generated from course ontology? (3) Are the ontological question generation strategies able to generate acceptable assessment questions? and (4) Do the topic-based indexing able to improve the feasibility of AQGen.

We firstly conduct ontology validation to evaluate the appropriateness of concept representation using a competency question approach. We used revision questions from the textbook to obtain keyword (in revision questions) and a concept (in the ontology) matching. The results show that only half of the ontology concepts matched the keywords. We took further investigation on the unmatched concepts and found some incorrect concept naming and later suggest a guideline for an appropriate concept naming. At the same time, we introduce validation of ontology using revision questions as competency questions to check for ontology completeness. Furthermore, we also proposed 17 short/long answer question templates for 3 question categories, namely definition, concept completion and comparison.

In the subsequent part of the thesis, we develop the AQGen tool and evaluate the generated questions. Two Computer Science subjects, namely OS and CNS, are chosen to evaluate AQGen generated questions. We conduct a questionnaire survey from 17 domain experts to identify experts’ agreement on the acceptability measure of AQGen generated questions. The experts’ agreements for acceptability measure are favourable, and it is reported that three of the four QG strategies proposed can generate acceptable questions. It has generated thousands of questions from the 3 question categories. AQGen is updated with question selection to generate a feasible question set from a tremendous amount of generated questions before. We have suggested topic-based indexing with the purpose to assert knowledge about topic chapters into ontology representation for question selection. The topic indexing shows a feasible result for filtering question by topics.

Finally, our results contribute to an understanding of ontology element representation for question generations and how to automatically generate questions from ontology for education assessment.

Item Type: Thesis (PhD)
Subjects: L Education > LB Theory and practice of education
Q Science > QA Mathematics > QA76 Electronic computers. Computer science. Computer software
Library of Congress Subject Headings (LCSH): Web-based instruction, Ontologies (Information retrieval), Semantic Web
Official Date: October 2019
Dates:
DateEvent
October 2019UNSPECIFIED
Institution: University of Warwick
Theses Department: Department of Computer Science
Thesis Type: PhD
Publication Status: Unpublished
Supervisor(s)/Advisor: Joy, Mike
Format of File: pdf
Extent: xiii, 184 leaves : illustrations
Language: eng

Request changes or add full text files to a record

Repository staff actions (login required)

View Item View Item

Downloads

Downloads per month over past year

View more statistics

twitter

Email us: wrap@warwick.ac.uk
Contact Details
About Us