Automatic question generation from documents for E-learning. (14th August 2012)

• Record Type: Journal Article
• Authors: Sathiyamurthy, K.; Geetha, T.V.
• Is Part Of: International journal of metadata, semantics and ontologies. Volume 7:Number 1(2012)
• Page Start: 16
• Page End: 24
• Publication Date: 2012-08-14
• Subjects: blooms taxonomy -- ontology -- LDA -- latent dirichlet allocation -- question generation; Metadata -- Periodicals; Semantic Web -- Periodicals; Ontologies (Information retrieval) -- Periodicals; Data structures (Computer science) -- Periodicals; Information theory -- Periodicals; 005.74
• Languages: English
• ISSNs: 1744-2621

Abstract

Question generation is an important module for e-learning systems. The task of manually extracting questions for each concept according to the cognitive level of the learner is a tiresome job. Automatic extraction of questions from documents for e-learning could simplify the task of assessing the students knowledge on the subject through questions that cover all the concepts learnt and of varying difficulty. To assess students according to their learning mental ability, questions in this work are matched with different levels of blooms taxonomy. The generated questions are evaluated based on question evaluation metric and with the proposed domain and topic coverage measure.