论文信息 - Generating Questions from OpenLearn study units

Generating Questions from OpenLearn study units

OpenLearn is a large online educational repository which can be used as a resource for developing and testing Question Generation (QG) systems. OpenLearn is described in detail and its advantages are discussed. To illustrate the use of OpenLearn for QG, a QG system, Ceist 2 , is presented which generates questions from OpenLearn content. Ceist is also offered as a case study for how existing NLP tools can be used to build a QG system, and should provide useful information to those considering the development of their own QG system.

Paul Piwek | Brendan Wyse | P. Piwek | B. Wyse | Brendan Wyse

[1] Beth Ann Hockey,et al. XTAG System - A Wide Coverage Grammar for English , 1994, COLING.

[2] James H. Martin,et al. Speech and language processing: an introduction to natural language processing , 2000 .

[3] Virginia Reviewer-Teller,et al. Review of Speech and language processing: an introduction to natural language processing, computational linguistics, and speech recognition by Daniel Jurafsky and James H. Martin. Prentice Hall 2000. , 2000 .

[4] Dan Klein,et al. Accurate Unlexicalized Parsing , 2003, ACL.

[5] Tilman Becker,et al. Question Answering by Searching Large Corpora With Linguistic Methods , 2004, TREC.

[6] Roger Levy,et al. Tregex and Tsurgeon: tools for querying and manipulating tree data structures , 2006, LREC.

[7] Arthur C. Graesser,et al. NLGML: A Markup Language for Question Generation , 2006 .

[8] Tianyong Hao,et al. Automatic Question Generation for Learning Evaluation in Medicine , 2007, ICWL.