Computer-aided generation of multiple-choice tests

Abstract

This paper describes a novel computer-aided procedure for generating multiple-choice tests from electronic instructional documents. In addition to employing various NLP techniques including term extraction and shallow parsing, the program makes use of language resources such as a corpus and WordNet. The system generates test questions and distractors, offering the user the option to post-edit the test items.

Improve the Output from a MCQ Test Item Generator Using Statistical NLP

“…The domain expert had drawn the material for the course from a specified document from the policy library. The theories were applied within a simulation as opposed to a reprogramming of the question generator [4]. [5] in order to ensure careful and thorough application of the theories.…”

“…The sentences resulting from the pre-processing were inserted into the source documents in place of the extracted sentences and then the amended documents were used as source documents during the manual simulation of the operation of the MCQ test item generator [4], [5].…”

“…However, some problems have been encountered when applying natural language processing techniques to these documents in the past, and so an adapted form [3] of a popular theory about discourse structure [11] is applied to the source documents as a final stage in the preprocessing before the MCQ test item generator software [4]. [5] is applied.…”

“…However an internal study proved that creating and updating the item bank manually is an expensive process. I am therefore investigating various ways to automatically generate MCQ test items, the most promising one being the application of a MCQ test item generator [4]. [5].…”

“…The creators of this system were the only researchers in the field who expressed an interest in collaborating in order to make their system more usable for our domain. The MCQ test item generator [4]. [5] uses the following steps to generate MCQ test items:…”