Effective assessments are essential for training and personnel development. Developing quality assessments is labor-intensive. This could lead to a shortage of assessments that can significantly impact the Army’s ability to develop their personnel and a Soldier’s ability to plan their career growth. There is a unique opportunity to harness the powers of data science and artificial intelligence to address this problem.
Recent developments have brought artificial intelligence to the point where it would be possible to generate some forms of assessments automatically by learning from past data. This project seeks to develop an assessment development tool called QGen that will use a combination of advanced machine learning approaches to automatically generate multiple-choice questions from text documents.
We propose a human-in-the-loop solution where users will be able to edit or override generated questions, and manually add new ones. QGen will address assessments at recall and comprehension levels. It will also generate questions for procedural descriptions in text. With the automation of the bulk of the assessments of these skills, Army trainers and instructional designers can focus their resources on higher-order skills. As a result of this effort, Soldiers will also have a larger bank of self-assessments to prepare for promotions and other career goals.