Kvasir generates relevant questions of varying complexity for a given text using Natural Language Generation (NLG) methods and validation by a tutor. While question answering is an effective way of improving reading comprehension, tutors have limited time for asking individualized questions and providing personalized feedback. Through its Human-in-the-Loop (HITL) approach, Kvasir provides tutors and teachers with a resource for making a complex and time-consuming task easier.
CTO, CleventMihai Dascălu is a Professor of Computer Science at University Politehnica of Bucharest, and has extensive experience in national and international research projects with more than 250 published papers. Dascălu holds the US patent #9734144, as well as 4 Romanian patent applications. Moreover, Dascălu obtained a Senior Fulbright scholarship in 2015 and is a corresponding member of the Academy of Romanian Scientists.