Learning Good Decompositions of Complex Questions

  • Yllias Chali
  • Sadid A. Hasan
  • Kaisar Imam
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7337)


This paper proposes a supervised approach for automatically learning good decompositions of complex questions. The training data generation phase mainly builds on three steps to produce a list of simple questions corresponding to a complex question: i) the extraction of the most important sentences from a given set of relevant documents (which contains the answer to the complex question), ii) the simplification of the extracted sentences, and iii) their transformation into questions containing candidate answer terms. Such questions, considered as candidate decompositions, are manually annotated (as good or bad candidates) and used to train a Support Vector Machine (SVM) classifier. Experiments on the DUC data sets prove the effectiveness of our approach.


Support Vector Machine Complex Question Computational Linguistics Responsiveness Score Supervise Model 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Chali, Y., Joty, S.R., Hasan, S.A.: Complex Question Answering: Unsupervised Learning Approaches and Experiments. Journal of Artificial Intelligence Research 35, 1–47 (2009)MathSciNetzbMATHGoogle Scholar
  2. 2.
    Harabagiu, S., Lacatusu, F., Hickl, A.: Answering complex questions with random walk models. In: Proceedings of the 29th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 220–227. ACM (2006)Google Scholar
  3. 3.
    Hickl, A., Wang, P., Lehmann, J., Harabagiu, S.: Ferret: Interactive question-answering for real-world environments. In: Proceedings of the COLING/ACL on Interactive Presentation Sessions, pp. 25–28 (2006)Google Scholar
  4. 4.
    Lacatusu, F., Hickl, A., Harabagiu, S.: Impact of question decomposition on the quality of answer summaries. In: Proceedings of the Fifth International Conference on Language Resources and Evaluation, LREC 2006 (2006)Google Scholar
  5. 5.
    Pasca, M.: Open-domain question answering from large text collections, 2nd edn. Center for the Study of Language and Information (2003)Google Scholar
  6. 6.
    Harabagiu, S., Hickl, A.: Methods for using textual entailment in open-domain question answering. In: Proceedings of the 21st International Conference on Computational Linguistics and the 44th Annual Meeting of the Association for Computational Linguistics, ACL, pp. 905–912 (2006)Google Scholar
  7. 7.
    Moschitti, A., Quarteroni, S., Basili, R., Manandhar, S.: Exploiting Syntactic and Shallow Semantic Kernels for Question/Answer Classificaion. In: Proceedings of the 45th Annual Meeting of the Association of Computational Linguistics, pp. 776–783. ACL, Prague (2007)Google Scholar
  8. 8.
    MacCartney, B., Grenager, T., de Marneffe, M., Cer, D., Manning, C.D.: Learning to Recognize Features of Valid Textual Entailments. In: Proceedings of the Human Language Technology Conference of the North American Chapter of the ACL, New York, USA, vol. 4148 (2006)Google Scholar
  9. 9.
    Heilman, M., Smith, N.A.: Extracting simplified statements for factual question generation. In: Proceedings of the Third Workshop on Question Generation (2010)Google Scholar
  10. 10.
    Wang, W., Hao, T., Liu, W.: Automatic Question Generation for Learning Evaluation in Medicine. In: Leung, H., Li, F., Lau, R., Li, Q. (eds.) ICWL 2007. LNCS, vol. 4823, pp. 242–251. Springer, Heidelberg (2008)CrossRefGoogle Scholar
  11. 11.
    Chen, W., Aist, G., Mostow, J.: Generating Questions Automatically from Informational Text. In: Proceedings of the 2nd Workshop on Question Generation (AIED 2009), pp. 17–24 (2009)Google Scholar
  12. 12.
    Hickl, A., Lehmann, J., Williams, J., Harabagiu, A.: Experiments with interac- tive question-answering. In: Proceedings of the 43rd Annual Meeting of the Association for Computational Linguistics ACL 2005, pp. 60–69 (2005)Google Scholar
  13. 13.
    McConnell, C.C., Mannem, P., Prasad, R., Joshi, A.: A New Approach to Ranking Over-Generated Questions. In: Proceedings of the AAAI Fall Symposium on Question Generation (2011)Google Scholar
  14. 14.
    Sekine, S.: Proteus Project OAK System (English Sentence Analyzer) (2002),
  15. 15.
    Fellbaum, C.: WordNet - An Electronic Lexical Database. MIT Press, Cambridge (1998)zbMATHGoogle Scholar
  16. 16.
    Li, X., Roth, D.: Learning Question Classifiers. In: Proceedings of the 19th International Conference on Computational Linguistics, Taipei, Taiwan, pp. 1–7 (2002)Google Scholar
  17. 17.
    Lin, C.Y.: ROUGE: A Package for Automatic Evaluation of Summaries. In: Proceedings of Workshop on Text Summarization Branches Out, Post-Conference Workshop of Association for Computational Linguistics, Barcelona, Spain, pp. 74–81 (2004)Google Scholar
  18. 18.
    Cortes, C., Vapnik, V.N.: Support Vector Networks. Machine Learning 20, 273–297 (1995)zbMATHGoogle Scholar
  19. 19.
    Joachims, T.: Making large-Scale SVM Learning Practical. In: Advances in Kernel Methods - Support Vector Learning (1999)Google Scholar
  20. 20.
    Hsu, C., Chang, C., Lin, C.: A Practical Guide to Support Vector Classification, National Taiwan University, Taipei 106, Taiwan (2008),
  21. 21.
    Cohen, J.: A Coefficient of Agreement for Nominal Scales. Educational and Psychological Measurement 20(1), 37–46 (1960)CrossRefGoogle Scholar
  22. 22.
    Landis, J.R., Koch, G.G.: The Measurement of Observer Agreement for Categorical Data. Biometrics 33(1), 159–174 (1977)MathSciNetzbMATHCrossRefGoogle Scholar
  23. 23.
    Zajic, D., Dorr, B.J., Lin, J., Schwartz, R.: Multi-candidate reduction: Sentence compression as a tool for document summarization tasks. Information Processing and Management 43, 1549–1570 (2007)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2012

Authors and Affiliations

  • Yllias Chali
    • 1
  • Sadid A. Hasan
    • 1
  • Kaisar Imam
    • 1
  1. 1.University of LethbridgeLethbridgeCanada

Personalised recommendations