Combining Logic and Machine Learning for Answering Questions

  • Ingo Glöckner
  • Björn Pelzer
Part of the Lecture Notes in Computer Science book series (LNCS, volume 5706)


LogAnswer is a logic-oriented question answering system developed by the AI research group at the University of Koblenz-Landau and by the IICS at the University of Hagen. The system addresses two notorious problems of the logic-based approach: Achieving robustness and acceptable response times. Its main innovation is the use of logic for simultaneously extracting answer bindings and validating the corresponding answers. In this way the inefficiency of the classical answer extraction/answer validation pipeline is avoided. The prototype of the system, which can be tested on the web, demonstrates response times suitable for real-time querying. Robustness to gaps in the background knowledge and errors of linguistic analysis is achieved by combining the optimized deductive subsystem with shallow techniques by machine learning.


Noun Phrase Relative Clause Word Sense Question Answering Training Item 
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.
    Hartrumpf, S.: Hybrid Disambiguation in Natural Language Analysis. Der Andere Verlag, Osnabrück (2003)Google Scholar
  2. 2.
    Helbig, H.: Knowledge Representation and the Semantics of Natural Language. Springer, Heidelberg (2006)zbMATHGoogle Scholar
  3. 3.
    Glöckner, I.: University of Hagen at QA@CLEF 2008: Answer validation exercise. In: Working notes for the CLEF 2008 workshop, Århus, Denmark (2008)Google Scholar
  4. 4.
    Glöckner, I., Pelzer, B.: Exploring robustness enhancements for logic-based passage filtering. In: Lovrek, I., Howlett, R.J., Jain, L.C. (eds.) KES 2008, Part I. LNCS (LNAI), vol. 5177, pp. 606–614. Springer, Heidelberg (2008)CrossRefGoogle Scholar
  5. 5.
    Witten, I.H., Frank, E.: Data Mining. Practical Machine Learning Tools and Techniques. Morgan Kaufmann, San Francisco (2005)zbMATHGoogle Scholar
  6. 6.
    Glöckner, I.: University of Hagen at QA@CLEF 2007: Answer validation exercise. In: Working Notes for the CLEF 2007 Workshop, Budapest (2007)Google Scholar
  7. 7.
    Glöckner, I.: Towards logic-based question answering under time constraints. In: Proc. of ICAIA 2008, Hong Kong, pp. 13–18 (2008)Google Scholar
  8. 8.
    Pelzer, B., Wernhard, C.: System Description: E-KRHyper. In: Pfenning, F. (ed.) CADE 2007. LNCS (LNAI), vol. 4603, pp. 508–513. Springer, Heidelberg (2007)CrossRefGoogle Scholar
  9. 9.
    Baumgartner, P., Furbach, U., Pelzer, B.: Hyper Tableaux with Equality. In: Pfenning, F. (ed.) CADE 2007. LNCS (LNAI), vol. 4603, pp. 492–507. Springer, Heidelberg (2007)CrossRefGoogle Scholar
  10. 10.
    Baumgartner, P., Furbach, U., Niemelä, I.: Hyper Tableaux. In: JELIA 1996, Proceedings, pp. 1–17 (1996)Google Scholar
  11. 11.
    Sutcliffe, G., Suttner, C.: The TPTP Problem Library: CNF Release v1.2.1. Journal of Automated Reasoning 21(2), 177–203 (1998)MathSciNetCrossRefzbMATHGoogle Scholar
  12. 12.
    Pelzer, B., Glöckner, I.: Combining theorem proving with natural language processing. In: Proc. of the First Int. Workshop on Practical Aspects of Automated Reasoning (PAAR 2008), CEUR Workshop Proceedings, pp. 71–80 (2008)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2009

Authors and Affiliations

  • Ingo Glöckner
    • 1
  • Björn Pelzer
    • 2
  1. 1.Intelligent Information and Communication Systems Group (IICS)University of HagenHagenGermany
  2. 2.Department of Computer Science, Artificial Intelligence Research GroupUniversity of Koblenz-LandauKoblenz

Personalised recommendations