NLP for assessment in intelligent tutoring systems

Topic Description

E-assessment is an important part of modern tutoring systems. Questions requiring short, free text answers are a valuable form of assessment, but are very difficult to mark because of the variety of possible responses and the noise in response sets. I have previously used machine learning techniques to develop mark schemes: a good project will investigate how to use NLP to build automatic marking systems, or an investigation of which machine learning techniques are most effective on student responses.

Another direction would be to provide personalised feedback to students based on their particular responses. A proposal could be based on investigating how an automatic dialogue system might be used to provide meaningful feedback in an assessment system.

Skills Required:

You should have a good undergraduate or masters degree in Computing or a related subject, and a strong interest in how computers can be used to understand natural language. This project could also be suitable for students from areas such as linguistics or psychology if you are able to show sufficiently advanced programming skills, and how to apply these skills to areas in natural language understanding or dialogue systems.

Background Reading:

Willis, Alistair (2015). Using NLP to support scalable assessment of short free text responses. In: Proceedings of the Tenth Workshop on Innovative Use of NLP for Building Educational Applications, pp. 243–253.

Jordan, Sally and Mitchell, Tom (2009). e-Assessment for learning? The potential of short-answer free text questions with tailored feedback. British Journal of Educational Technology, 40(2), pp. 371–385.

Report an error on this page


Alistair Willis


Paul Piwek