Paper: Generating Natural Language Questions to Support Learning On-Line

ACL ID W13-2114
Title Generating Natural Language Questions to Support Learning On-Line
Venue European Workshop on Natural Language Generation
Session
Year 2013
Authors

When instructors prepare learning materi- als for students, they frequently develop accompanying questions to guide learn- ing. Natural language processing technol- ogy can be used to automatically generate such questions but techniques used have not fully leveraged semantic information contained in the learning materials or the full context in which the question genera- tion task occurs. We introduce a sophisti- cated template-based approach that incor- porates semantic role labels into a system that automatically generates natural lan- guage questions to support online learn- ing. While we have not yet incorporated the full learning context into our approach, our preliminary evaluation and evaluation methodology indicate our approach is a promising one for supporting learning.