Question Generation via Overgenerating Transformations and Ranking

Michael Heilman and Noah A. Smith

We have developed a system for automatically generating literal reading comprehension questions about informational texts in English.

Papers

• M. Heilman. 2011. Automatic Factual Question Generation from Text. Ph.D. Dissertation, Carnegie Mellon University. CMU-LTI-11-004. [PDF]
• M. Heilman and N. A. Smith. 2010. Good Question! Statistical Ranking for Question Generation. In Proc. of NAACL/HLT. [PDF] [errata]
• M. Heilman and N. A. Smith. 2009. Question Generation via Overgenerating Transformations and Ranking. Language Technologies Institute, Carnegie Mellon University Technical Report CMU-LTI-09-013. [PDF] [errata]

Code

• Code for the whole system: QuestionGeneration-10-01-12.tar.gz
• Code for just the java implementation of the Supersense Tagger (Ciaramita and Altun, EMNLP 2006) that is used in the system: SupersenseTagger-10-01-12.tar.gz
• Code for just the simplification stage of our system: Simplified Factual Statement Extraction.
• Code for just the coreference resolution component of the system: ARKref.

Note: we do not provide technical support for this code.