Article contents
Automatic generation of short answer questions for reading comprehension assessment
Published online by Cambridge University Press: 13 January 2016
Abstract
Writing items for reading comprehension assessment is time-consuming. Automating part of the process can help test-designers to develop assessments more efficiently and consistently. This paper presents an approach to automatically generating short answer questions for reading comprehension assessment. Our major contribution is to introduce Lexical Functional Grammar (LFG) as the linguistic framework for question generation, which enables systematic utilization of semantic and syntactic information. The approach can efficiently generate questions of better quality than previous high-performing question generation systems, and uses paraphrasing and sentence selection to improve the cognitive complexity and effectiveness of questions.
- Type
- Articles
- Information
- Copyright
- Copyright © Cambridge University Press 2016
References
- 10
- Cited by