A study of recent techniques to estimate the difficulty of exam questions from text

Add to your list(s) Download to your calendar using vCal

• Luca Benedetto (University of Cambridge)
• Friday 21 October 2022, 12:00-13:00
• FW09.

If you have a question about this talk, please contact Michael Schlichtkrull.

Abstract: Question Difficulty Estimation (QDE) from text is the application of Natural Language Processing techniques to estimate a value, either numerical or categorical, which represents the difficulty of an exam question. In recent years, it gained a fair amount of research attention as it enables to partially overcome the limitations of traditional approaches to QDE , which are either subjective (manual calibration) or require to show newly created questions to students (pretesting), which is undesirable. In this presentation, I will give an introduction to the field, present some of the state of the art approaches, and outline opportunities for further research.

Bio: Dr. Luca Benedetto is a Research Associate at the University of Cambridge, working within the NLIP group and the ALTA institute. Previously, he obtained his PhD from Politecnico di MIlano and worked as a Data Scientist in Cloud Academy. His research interests cover the automated evaluation and creation of learning and assessment content, and the modeling of student’s knowledge level.

This talk is part of the NLIP Seminar Series series.

This talk is included in these lists:

• All Talks (aka the CURE list)
• Cambridge Centre for Data-Driven Discovery (C2D3)
• Cambridge Forum of Science and Humanities
• Cambridge Language Sciences
• Cambridge talks
• Chris Davis' list
• Department of Computer Science and Technology talks and seminars
• FW09
• Graduate-Seminars
• Guy Emerson's list
• Interested Talks
• Language Sciences for Graduate Students
• NLIP Seminar Series
• PMRFPS's
• Simon Baker's List
• Trust & Technology Initiative - interesting events
• bld31
• ndk22's list
• ob366-ai4er
• rp587

Note that ex-directory lists are not shown.