Can Modern Statistical Parsers Lead to Better Natural Language Understanding for Education?

  • Umair Z. Ahmed
  • Arpit Kumar
  • Monojit Choudhury
  • Kalika Bali
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7181)


We use state-of-the-art parsing technology to build GeoSynth – a system that can automatically solve word problems in geometric constructions. Through our experiments we show that even though off-the-shelf parsers perform poorly on texts containing specialized vocabulary and long sentences, appropriate preprocessing of text before applying the parser and use of extensive domain knowledge while interpreting the parse tree can together help us circumvent parser errors and build robust domain specific natural language understanding modules useful for various educational applications.


NLP for education statistical parsers evaluation of parsers domain adaptation domain ontology 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Mukherjee, Garain, U.: A review of methods for automatic understanding of natural language mathematical problems. Artificial Intelligence Review 29, 93–122 (2008)CrossRefGoogle Scholar
  2. 2.
    Hempelmann, C.F., Rus, V., Graesser, A.C., McNamara, D.S.: Evaluating state-of-the-art Treebank-style parsers for Coh-Metrix and other learning technology environments. In: Proc. of the 2nd Workshop on Building Educational Applications Using NLP, pp. 69–76 (2005)Google Scholar
  3. 3.
    Charniak, E.: Statistical parsing with a context-free grammar and word statistics. In: Proceedings of the Fourteenth National Conference on Artificial Intelligence. AAAI Press/MIT Press, Menlo Park (1997)Google Scholar
  4. 4.
    Gildea, D.: Corpus Variation and Parser Performance. In: Conference on Empirical Methods in Natural Language Processing (EMNLP), Pittsburgh, PA (2001)Google Scholar
  5. 5.
    Gulwani, S., Korthikanti, V., Tiwari, A.: Synthesizing geometry constructions. In: PLDI (2011)Google Scholar
  6. 6.
    Senk, S.L.: Van Hiele levels and achievement in writing geometry proofs. Journal for Research in Mathematics Education 20(3), 309–321 (1989)CrossRefGoogle Scholar
  7. 7.
    Hoffer, A.: Van Hiele-based research. In: Lesh, R., Landau, M. (eds.) Acquisition of Mathematics Concepts and Processes, pp. 205–227. Academic Press, New York (1983)Google Scholar
  8. 8.
    Hoffer, A.: Geometry is more than proof. Mathematics Teacher 74(1), 11–18 (1981)MathSciNetGoogle Scholar
  9. 9.
    National Council of Teachers of Mathematics: Principles and standards for school mathematics, Reston, VA (2000)Google Scholar
  10. 10.
    Klein, D., Manning, C.D.: Accurate Unlexicalized Parsing. In: Proceedings of the 41st Meeting of the Association for Computational Linguistics, Sapporo, Japan, pp. 423–430 (2003)Google Scholar
  11. 11.
    Collins, M.: Three generative, lexicalised models for statistical parsing. In: Proc. of the 35th Annual Meeting of the Association for Computational Linguistic, Madrid, Spain (1997)Google Scholar
  12. 12.
    Bikel, D.M.: Intricacies of Collins’ parsing model. Computational Linguistics 30(4), 479–511 (2004)CrossRefGoogle Scholar
  13. 13.
    Charniak, E.: A Maximum-Entropy-inspired parser. In: Proceedings of the North-American Chapter of Association for Computational Linguistics, Seattle, WA (2000)Google Scholar
  14. 14.
    Aggarwal, R.S.: Exercise: 36-B to 36-E. Foundation Mathematics for Class 8 (2009)Google Scholar
  15. 15.
    Aggarwal, R.S.: Exercise: 10-D, 15-B. Foundation Mathematics for Class 9 (2008)Google Scholar
  16. 16.
    Sekine, S., Collins, M.J.: Evalb. Tool for evaluating bracketing performance of a parser (2005), (accessed April 2011)

Copyright information

© Springer-Verlag Berlin Heidelberg 2012

Authors and Affiliations

  • Umair Z. Ahmed
    • 1
  • Arpit Kumar
    • 1
  • Monojit Choudhury
    • 1
  • Kalika Bali
    • 1
  1. 1.Microsoft Research IndiaBangaloreIndia

Personalised recommendations