Automatic Question Generation: From NLU to NLG

Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 9684)


Questioning has been shown to improve learning outcomes, and automatic question generation can greatly facilitate the inclusion of questions in learning technologies such as intelligent tutoring systems. The majority of prior QG systems use parsing software and transformation algorithms to create questions. In contrast, the approach described here infuses natural language understanding (NLU) into the natural language generation (NLG) process by first analyzing the central semantic content of each independent clause in each sentence. Then question templates are matched to what the sentence is communicating in order to generate higher quality questions. This approach generated a higher percentage of acceptable questions than prior state-of-the-art systems.


  1. 1.
    Ali, H., Chali, Y., Hasan, S.: Automation of question generation from sentences. In: Proceedings of QG2010: The Third Workshop on Question Generation (2010)Google Scholar
  2. 2.
    Allen, J.: Natural Language Understanding. The Benjamin/Cummings Publishing Company, Redwood City (1995)MATHGoogle Scholar
  3. 3.
    Anderson, R., Biddle, W.: On asking people questions about what they are reading. In: Bower, G. (ed.) Psychology of learning and motivation, vol. 9. Elsevier (1975)Google Scholar
  4. 4.
    Bransford, J., Brown, A., Cocking, R.R.: How People Learn. National Academy Press, Washington, DC (2004)Google Scholar
  5. 5.
    Chali, Y., Hasan, S.: Towards Topic-to-Question Generation. Computational Linguistics. MIT Press, Cambridge (2015)Google Scholar
  6. 6.
    Chomsky, N.: Syntactic Structures. Mouton, The Hague (1957)Google Scholar
  7. 7.
    Ding, N., Melloni, L., Zhang, H., Tian, X., Poeppel, D.: Cortical tracking of hierarchical linguistic structures in connected speech. Nat. Neurosci. 19(1), 158–164 (2015)CrossRefGoogle Scholar
  8. 8.
    Gates, D.: Automatically generating reading comprehension look-back strategy: questions from expository texts. DTIC Document (2008)Google Scholar
  9. 9.
    Gates, D.: Generating look-back strategy questions from expository texts. In: The Workshop on the Question Generation Shared Task and Evaluation Challenge, NSF, Arlington (2008)Google Scholar
  10. 10.
    Graesser, A., Halpern, D., Hakel, M.: Principles of Learning. Task Force on Lifelong Learning at Work and at Home, Washington, DC (2008)Google Scholar
  11. 11.
    Heilman, M., Smith, N.: Question generation via overgenerating transformations and ranking. DTIC Document (2009)Google Scholar
  12. 12.
    Heilman, M., Smith, N.: Good question! statistical ranking for question generation. In: Human Language Technologies: The 2010 Annual Conference of the North American Chapter of the Association for Computational Linguistics, ACL (2010)Google Scholar
  13. 13.
    Heilman, M.: Automatic Factual Question Generation from Text. Carnegie Mellon University, Pittsburgh (2011)Google Scholar
  14. 14.
    Heilman, M., Smith, N.: Rating computer-generated questions with Mechanical Turk. In: Proceedings of the NAACL HLT 2010 Workshop on Creating Speech and Language Data with Amazon’s Mechanical Turk, ACL (2010)Google Scholar
  15. 15.
    Huang, Y.-T., Mostow, J.: Evaluating human and automated generation of distractors for diagnostic multiple-choice cloze questions to assess children’s reading comprehension. In: Conati, C., Heffernan, N., Mitrovic, A., Verdejo, M.F. (eds.) AIED 2015. LNCS, vol. 9112, pp. 155–164. Springer, Heidelberg (2015)CrossRefGoogle Scholar
  16. 16.
    Indurkhya, N., Damerau, F.: Handbook of Natural Language Processing, vol. 2. CRC Press, Boca Raton (2010)Google Scholar
  17. 17.
    Jurafsky, D., Martin, J.: Speech & Language Processing. Pearson Education, Upper Saddle River (2008)Google Scholar
  18. 18.
    Kroeger, P.: Analyzing Grammar: An Introduction. Cambridge University Press, Cambridge (2005)CrossRefGoogle Scholar
  19. 19.
    Le, N.-T., Kojiri, T., Pinkwart, N.: Automatic question generation for educational applications – the state of art. In: van Do, T., Thi, H.A.L., Nguyen, N.T. (eds.) Advanced Computational Methods for Knowledge Engineering. AISC, vol. 282, pp. 325–338. Springer, Heidelberg (2014)CrossRefGoogle Scholar
  20. 20.
    Liu, M., Calvo, R.A., Rus, V.: Automatic question generation for literature review writing support. In: Aleven, V., Kay, J., Mostow, J. (eds.) ITS 2010, Part I. LNCS, vol. 6094, pp. 45–54. Springer, Heidelberg (2010)CrossRefGoogle Scholar
  21. 21.
    Liu, M., Calvo, R., Rus, V.: G-Asks: an intelligent automatic question generation system for academic writing support. Dialogue and Discourse 3(2), 101–124 (2012). Special Issue on Question GenerationCrossRefGoogle Scholar
  22. 22.
    Lindberg, D., Popowich, F., Nesbit, J., Winne, P.: Generating natural language questions to support learning on-line. In: European Conference for Natural Language Generation (2013)Google Scholar
  23. 23.
    Mannem, P., Prasad, R., Joshi, A.: Question generation from paragraphs at UPenn: QGSTEC system description. In: Proceedings of QG2010: The Third Workshop on Question Generation (2010)Google Scholar
  24. 24.
    Mazidi, K., Nielsen, R.D.: Pedagogical evaluation of automatically generated questions. In: Trausan-Matu, S., Boyer, K.E., Crosby, M., Panourgia, K. (eds.) ITS 2014. LNCS, vol. 8474, pp. 294–299. Springer, Heidelberg (2014)CrossRefGoogle Scholar
  25. 25.
    Mazidi, K., Nielsen, R.D.: Leveraging multiple views of text for automatic question generation. In: Conati, C., Heffernan, N., Mitrovic, A., Verdejo, M.F. (eds.) AIED 2015. LNCS, vol. 9112, pp. 257–266. Springer, Heidelberg (2015)CrossRefGoogle Scholar
  26. 26.
    Pashler, H., Bain, P., Bottge, B., Graesser, A., Koedinger, K., McDaniel, M., Metcalfe, J.: Organizing Instruction and Study to Improve Student Learning. IES Practice Guide, NCER (2007)Google Scholar
  27. 27.
    Peverly, S., Wood, R.: The effects of adjunct questions and feedback on improving the reading comprehension skills of learning-disabled adolescents. Contemp. Educ. Psychol. 26(1), 25–43 (2001). ElsevierCrossRefGoogle Scholar
  28. 28.
    Piwek, P., Boyer, K.: Varieties of question generation: introduction to thisspecial issue. Dialogue and Discourse 3, 1–9 (2012)CrossRefGoogle Scholar
  29. 29.
    Roediger, H., Karpicke, J.: The power of testing memory: basic research and implications for educational practice. Perspectives on Psychological Science, vol. 1. SAGE (2006)Google Scholar
  30. 30.
    Roediger, H., Karpicke, J., Pyc, M.: Inexpensive techniques to improve education: applying cognitive psychology to enhance educational practice. J. Appl. Res. Memory Cogn. 1(4), 242–248 (2012)CrossRefGoogle Scholar
  31. 31.
    Rothkopf, E.: Learning from written instructive materials: an exploration of the control of inspection behavior by test-like events. Am. Educ. Res. J. (1966)Google Scholar
  32. 32.
    Rus, V., Cai, Z., Graesser, A.C.: Experiments on generating questions about facts. In: Gelbukh, A. (ed.) CICLing 2007. LNCS, vol. 4394, pp. 444–455. Springer, Heidelberg (2007)CrossRefGoogle Scholar
  33. 33.
    Rus, V., Wyse, B., Piwek, P., Lintean, M., Stoyanchev, S., Moldovan, C.: A detailed account of the first question generation shared task evaluation challenge. Dialogue Discourse 3(2), 177–204 (2012)CrossRefGoogle Scholar
  34. 34.
    Snow, R., O’Connor, B., Jurafsky, D., Ng, A.: Cheap and fast–but is it good?: evaluating non-expert annotations for natural language tasks. In: Proceedings of the conference on empirical methods in natural language processing, ACL (2008)Google Scholar
  35. 35.
    VanLehn, K., Graesser, A., Jackson, G., Jordan, P., Olney, A., Rose, C.: When are tutorial dialogues more effective than reading? Cogn. Sci. 31(1), 3–62 (2007)CrossRefGoogle Scholar
  36. 36.
    Weizenbaum, J.: ELIZA a computer program for the study of natural language communication between man and machine. Commun. ACM 9(1), 36–45 (1966)CrossRefGoogle Scholar
  37. 37.
    Wolfe, J.: Automatic question generation from text-an aid to independent study. ACM SIGCUE Outlook, vol. 10. ACM (1976)Google Scholar
  38. 38.
    Wolfe, J.: Reading Retention as a Function of Method for Generating Interspersed Questions. ERIC (1977)Google Scholar
  39. 39.
    Woolf, B.: Building Intelligent Interactive Tutors: Student-centered Strategies for Revolutionizing e-Learning. Morgan Kaufmann, Burlington (2010)Google Scholar
  40. 40.
    Wyse, B., Piwek, P.: Generating questions from openlearn study units. In: Proceedings, The 2nd Workshop on Question Generation, vol. 1 (2009)Google Scholar

Copyright information

© Springer International Publishing Switzerland 2016

Authors and Affiliations

  1. 1.Department of Computer Science and EngineeringUniversity of North TexasDentonUSA

Personalised recommendations