Communications of the ACM
Putting Answers to the Test
A new algorithm developed at Pennsylvania State University creates plausible answers designed to distract students from the correct answer in multiple choice exams.
Credit: wordpress.com
Researchers at Pennsylvania State University (Penn State) have developed an algorithm that creates plausible answers designed to distract students from the correct answer in multiple choice exams, thus simplifying the process for instructors while making the exam more challenging for students.
Under existing models of creating answers, distractors are selected based on a weighted combination of similarities using the exam creator's guidelines.
The Penn State method uses machine and deep learning to learn the "unknown" relation between the question and "good" distractors from existing multiple choice questions, says Penn State's Chen Liang. "The idea is to learn from a large amount of real multiple choice questions instead of using heuristics as existing methods do," he says.
From Penn State News
View Full Article
Abstracts Copyright © 2018 Information Inc., Bethesda, Maryland, USA
No entries found