BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:A study of recent techniques to estimate the difficulty of exam qu
 estions from text - Luca Benedetto (University of Cambridge)
DTSTART:20221021T110000Z
DTEND:20221021T120000Z
UID:TALK185147@talks.cam.ac.uk
CONTACT:Michael Schlichtkrull
DESCRIPTION:Abstract: Question Difficulty Estimation (QDE) from text is th
 e application of Natural Language Processing techniques to estimate a valu
 e\, either numerical or categorical\, which represents the difficulty of a
 n exam question. In recent years\, it gained a fair amount of research att
 ention as it enables to partially overcome the limitations of traditional 
 approaches to QDE\, which are either subjective (manual calibration) or re
 quire to show newly created questions to students (pretesting)\, which is 
 undesirable.\nIn this presentation\, I will give an introduction to the fi
 eld\, present some of the state of the art approaches\, and outline opport
 unities for further research.\n\nBio:\nDr. Luca Benedetto is a Research As
 sociate 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 inter
 ests cover the automated evaluation and creation of learning and assessmen
 t content\, and the modeling of student’s knowledge level.
LOCATION:FW09
END:VEVENT
END:VCALENDAR