OntoQue: A Question Generation Engine for Educational Assesment Based on Domain Ontologies

Al-Yahya, Maha

doi:10.1109/icalt.2011.124

Cited by 32 publications

(21 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Developing an ontology-based question generator which integrates the stem templates and generation strategies introduced by Papasalouros et al (2017;2011), Cubric andTosic (2017), Grubisic (2012); Grubisic et al (2013), and2011). The generator could be used to generate questions from any domain ontology.…”

Section: Introductionmentioning

confidence: 99%

“…The property-based strategy, which uses the object, datatype, and annotation properties in the ontologies. Papasalouros et al (2017;2011) defined the class, terminology, and property-based generation strategies which traverse the domain ontology and auto-generate the multiple choice question's correct answer (key) and incorrect answers (distracters). The three main strategies contain several sub-strategies which specify the classes, individuals or properties from which the question's key and distractors are generated.…”

Section: Introductionmentioning

confidence: 99%

“…She defined question stem templates aimed only to assess students' cognition at the knowledge level in Bloom's taxonomy (Al-Yahya 2014;2011). Al-Yahya followed Grubisic's steps in allowing distracters to be randomly selected from the domain ontology.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Evaluating the quality of the ontology-based auto-generated questions

Demaidi

Gaber

Filer

2017

Smart Learn. Environ.

View full text Add to dashboard Cite

An ontology is a knowledge representation structure which has been used in Virtual Learning Environments (VLEs) to describe educational courses by capturing the concepts and the relationships between them. Several ontology-based question generators used ontologies to auto-generate questions, which aimed to assess students' at different levels in Bloom's taxonomy. However, the evaluation of the questions was confined to measuring the qualitative satisfaction of domain experts and students. None of the question generators tested the questions on students and analysed the quality of the auto-generated questions by examining the question's difficulty, and the question's ability to discriminate between high ability and low ability students. The lack of quantitative analysis resulted in having no evidence on the quality of questions, and how the quality is affected by the ontology-based generation strategies, and the level of question in Bloom's taxonomy (determined by the question's stem templates). This paper presents an experiment carried out to address the drawbacks mentioned above by achieving two objectives. First, it assesses the auto-generated questions' difficulty, discrimination, and reliability using two statistical methods: Classical Test Theory (CTT) and Item Response Theory (IRT). Second, it studies the effect of the ontology-based generation strategies and the level of the questions in Bloom's taxonomy on the quality of the questions. This will provide guidance for developers and researchers working in the field of ontology-based question generators, and help building a prediction model using machine learning techniques.

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Evaluating the quality of the ontology-based auto-generated questions

Demaidi

Gaber

Filer

2017

Smart Learn. Environ.

View full text Add to dashboard Cite

show abstract

“…Algumas formas alternativas para a GQ são apresentadas em [Al-Yahya 2011] e [Zheng et al 2011]. O sistema OntoQue [Al-Yahya 2011] usa ontologias de domínio para gerar items de avaliação de três tipos: múltipla escolha, verdadeiro ou falso e de preenchimento.…”

Section: Revisão De Literaturaunclassified

Geração Automática de Questões a Partir do Reconhecimento de Entidades Nomeadas em Textos Didáticos

Pirovani

Spalenza

Oliveira

2017

Anais Do XXVIII Simpósio Brasileiro De Informática Na Educação (SBIE 2017)

View full text Add to dashboard Cite

Abstract. Learning evaluation is fundamental for the detection of methodological problems of the teaching practices. An effective assessment of teaching should address much of the content of the discipline and evaluate the comprehension of this content by the learners. In this work, we present a strategy that aims at automatic question generation from named entities identified in teaching texts. Therefore, we are proposing a tool that will save time of the teacher. In our experiments, free-text and fill-in-the-blank questions were generated from 10 types of named entities identified in a History textbook. We found 7195 named entities and we generate 6917 questions.Resumo. A avaliação de aprendizagemé fundamental para a detecção dos problemas metodológicos do ensino. Uma verificação eficiente do ensino deve abordar boa parte do conteúdo da disciplina e avaliar a compreensão desse conteúdo pelos aprendizes. Neste trabalho apresentamos uma estratégia que visa a geração automática de questões a partir das entidades nomeadas identificadas em textos didáticos. Portanto, estamos propondo uma ferramenta que poupará tempo do professor. Em nossos experimentos, questões discursivas e questões de preenchimento foram geradas a partir de 10 tipos de entidades nomeadas identificadas em um livro didático de História. Encontramos 7195 entidades nomeadas e geramos 6917 questões. IntroduçãoA avaliação de aprendizagemé uma ferramenta fundamental para enfatizar os problemas do ensino. O objetivo da avaliaçãoé apoiar e incentivar o processo de construção do conhecimento do estudante, seja de forma presencial ouà distância [Behar et al. 2010]. Uma verificação eficiente do ensino deve abordar boa parte do conteúdo da disciplina, onde estudantes são avaliados segundo a leitura e compreensão do texto. A proposta deste trabalhoé auxiliar o professor na geração de questões para compor exercícios e avaliações a partir de conteúdos chave do texto, observando as relações entre entidades como sugerido por [Moraes 2003].De acordo com [Rus et al. 2008], Geração de Questões (GQ)é a geração automática de questões a partir de textos escritos em linguagem natural, dados brutos e bases de conhecimento. Essaé uma tarefa importante que pode ser utilizada pelo professor, possibilitando diminuir o tempo e esforço necessários durante sua execução manual.Nosúltimos anos, muitas comunidades de pesquisa têm se interessado na geração automática de questões para propósitos educacionais [Le et al. 2014]. A GQ pode ser

show abstract

“…Recently, a handful of studies explored the generation of MCQs from ontologies (Al-Yahya 2011;Fairon 1999;Holohan 2005Holohan , 2006Papasalouros, Kotis, and Kanaris 2008;Zitko et al 2008;Zoumpatianos, Papasalouros, and Kotis 2011), but very little research has been done on theoretical, empirical and evaluation aspects. Most of the proposed methodologies generate questions of the form ''What is X?''…”

Section: Introductionmentioning

confidence: 99%

ALT-C 2012 Conference Proceedings - A confrontation with reality

Supplement¹

2012

Research in Learning Technology

View full text Add to dashboard Cite

EDITORIAL Editorial for proceedings papersHere are the Proceedings Papers of the 2012 ALT Conference ''A confrontation with reality'', held in Manchester, England. Each paper reports on a piece of research, possibly in its early stages, states a point of view or summarises an area of work, perhaps giving new insights. This supplement contains 18 papers, an increase over previous years.The conference has five themes which are:. Problem solving Á finding effective solutions to technical problems and using learning technology to solve institutional problems. . Openness and sharing Á methods and frameworks for collaboration and sharing of knowledge and resources between practitioners and between providers, and the evidence to justify this. . Entrepreneurialism Á moving resources from where they have low yield for learning and for learners to where their yield is higher. . Mainstreaming Á applying learning technology on a large scale in pioneering ways that enthuse learners and are welcomed by teachers and administrators. . Sustainability Á of technologies, models and approaches.Problem solving is the bread and butter of learning technology practitioners. Two papers look at new solutions to familiar pedagogic problems. Essa and Ayad (2012) discuss how to use predictive and statistical techniques to identify those students most at risk of not completing a learning programme Á in a way that also helps to identify an appropriate intervention to address the learners' difficulties. Taylor (2012) looks at the problem of using video effectively in a physiotherapy context to support learners on placements, rather than relying on occasional face to face visits.The other three papers on problem solving are more focussed on the actual techniques being used. Mor and Craft (2012) report on a workshop looking at all aspects of the evolving use of learning design Á from tools through methods and frameworks. Alsubait, Parsia and Sattler (2012) propose an ontological approach to automatic generation of analogy questions in multiple choice format. Flavin (2012) discusses, in part through survey results, the increasing role of disruptive technologies Á those that were not designed for education but have become widely adopted by learners.The largest number of proceedings papers is in the area of openness and sharing. This area often coincides with the need to confront reality in terms of the limited resources available. McGuigan and Golden (2012) report on the introduction of a standardised online tutoring system for learners gaining a Teaching Qualification in Further Education: the system provides generic email, blog and micro-blog facilities and allows support to be roster-based. Cochrane (2012) reflects on three failed m-learning projects, identifying critical failure factors by comparing them with a larger number of successful ones. A significant cause of failure is not updating pedagogy to match the introduced technology. Two further papers on openness and sharing have a discipline base. Reinhardt and Rosen (2012) report on...

show abstract

OntoQue: A Question Generation Engine for Educational Assesment Based on Domain Ontologies

Cited by 32 publications

References 5 publications

Evaluating the quality of the ontology-based auto-generated questions

Evaluating the quality of the ontology-based auto-generated questions

Geração Automática de Questões a Partir do Reconhecimento de Entidades Nomeadas em Textos Didáticos

ALT-C 2012 Conference Proceedings - A confrontation with reality

Contact Info

Product

Resources

About