Advertisement

DFKI-LT at QA@CLEF 2007

  • Bogdan Sacaleanu
  • Günter Neumann
  • Christian Spurk
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 5152)

Abstract

In this paper we present our QA@CLEF 2007 version of Quantico, a cross-language open domain question answering (QA) system for German and English document collections. The main features of the system are: use of a preemptive off-line document annotation with linguistic information; online extraction of abbreviation-expansion pairs and appositional constructions for the answer extraction; use of online translation services for the crosslingual scenarios; use of redundancy as an indicator of good answer candidates; selection of the best answers based on distance metrics defined over graph representations of the answer’s context. The results of evaluating the system’s performance by QA@CLEF 2007 were as follows: for the German-German run we achieved an overall accuracy (ACC) of 30 %; for English-German 18.5 % (ACC); for German-English 7 % (ACC), for Spanish-English 10 % (ACC) and for the Portuguese-German run 7 % (ACC).

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Sacaleanu, B., Neumann, G.: DFKI-LT at the CLEF 2006 Multiple Language Question Answering Track. In: Working Notes for the CLEF 2006 Workshop, Alicante, Spain, September 20–22 (2006)Google Scholar
  2. Neumann, G., Piskorski, J.: A Shallow Text Processing Core Engine. Journal of Computational Intelligence 18(3), 451–476 (2002)CrossRefGoogle Scholar
  3. Neumann, G., Sacaleanu, B.: Experiments on Robust NL Question Interpretation and Multilayered Document Annotation for a Cross-Language Question/Answering System. In: Peters, C., Clough, P., Gonzalo, J., Jones, G.J.F., Kluck, M., Magnini, B. (eds.) CLEF 2004. LNCS, vol. 3491, pp. 411–422. Springer, Heidelberg (2005)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2008

Authors and Affiliations

  • Bogdan Sacaleanu
    • 1
  • Günter Neumann
    • 1
  • Christian Spurk
    • 1
  1. 1.German Research Center for Artificial Intelligence (DFKI), Language Technology LabSaarbrückenGermany

Personalised recommendations