Paper: Automatic Question Generation using Discourse Cues

ACL ID W11-1401
Title Automatic Question Generation using Discourse Cues
Venue Innovative Use of NLP for Building Educational Applications
Year 2011

In this paper, we present a system that au- tomatically generates questions from natural language text using discourse connectives. We explore the usefulness of the discourse con- nectives for Question Generation (QG) that looks at the problem beyond sentence level. Our work divides the QG task into content se- lection and question formation. Content se- lection consists of finding the relevant part in text to frame question from while question for- mation involves sense disambiguation of the discourse connectives, identification of ques- tion type and applying syntactic transforma- tions on the content. The system is evaluated manually for syntactic and semantic correct- ness.