Advertisement

A Re-examination of IR Techniques in QA System

  • Yi Chang
  • Hongbo Xu
  • Shuo Bai
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3248)

Abstract

The performance of Information Retrieval in the Question Answering system is not satisfactory from our experiences in TREC QA Track. In this article, we take a comparative study to re-examine IR techniques on document retrieval and sentence level retrieval respectively. Our study shows: 1) query reformulation should be a necessary step to achieve a better retrieval performance; 2) The techniques for document retrieval are also effective in sentence level retrieval, and single sentence will be the appropriate retrieval granularity.

Keywords

Vector Space Model Question Answering Document Retrieval Single Sentence Information Retrieval Technique 
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.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Allan, J., Wade, C., Bolivar, A.: Retrieval and Novelty Detection at the Sentence Level. In: Proceedings of the 26th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval (2003)Google Scholar
  2. 2.
    Chang, Y., Xu, H., Bai, S.: TREC 2003 Question Answering Track at CAS-ICT. In: Proceedings of the 12th Text REtrieval Conference (2003)Google Scholar
  3. 3.
    Clarke, C.L.A., Cormack, G.V., Kisman, D.I.E., Lynam, T.R.: Question Answering by Passage Selection (MultiText experiments for TREC-9). In: Proceedings of the 9th Text REtrieval Conference (2000)Google Scholar
  4. 4.
    Harman, D., Candela, G.: A Very Fast Prototype Retrieval System Using Statistical Rankin. SIGIR Forum, 100–110 (1989)Google Scholar
  5. 5.
    Moldovan, D., Harabagiu, S., Girju, R., Morarescu, P., Lacatusu, F., Novischi, A., Badulescu, A., Bolohan, O.: LCC Tools for Question Answering. In: Proceedings of the 11th Text REtrieval Conference (2002)Google Scholar
  6. 6.
    Monz, C.: Document Retrieval in the Context of Question Answering. In: Proceedings of the 25th European Conference on IR Research (2003)Google Scholar
  7. 7.
    Roberts, I., Gaizauskas, R.: Evaluating Passage Retrieval Approaches for Question Answering, http://www.dcs.shef.ac.uk/research/resmes/papers/CS0306.pdf
  8. 8.
    Soubbotin, M.M., Soubbotin, S.M.: Use of Patterns for Detection of Likely Answer Strings: A Systematic Approach. In: Proceedings of the 11th Text REtrieval Conference (2002)Google Scholar
  9. 9.
    Srihari, R., Li, W.: Information Extraction Supported Question Answer. In: Proceedings of the 8th Text REtrieval Conference (1999)Google Scholar
  10. 10.
    Tellex, S., Katz, B., Lin, J., Fernandes, A., Marton, G.: Quantitative Evaluation of Passage Retrieval Algorithms for Question Answering. In: Proceedings of the 26th annual international ACM SIGIR conference on Research and Development in Information Retrieval (2003)Google Scholar
  11. 11.
    Voorhees, E.M.: Overview of TREC 2002 Question Answering Track. In: Proceedings of the 11th Text REtrieval Conference (2002)Google Scholar
  12. 12.
    Xu, H., Zhang, H., Bai, S.: ICT Experiments in TREC-11 QA Main Task. In: Proceedings of the 11th Text REtrieval Conference (2002)Google Scholar
  13. 13.
    Xu, H., Yang, Z., Wang, B., Liu, B., Cheng, J., Liu, Y., Yang, Z., Cheng, X., Bai, S.: TREC-11 Experiments at CAS-ICT: Filtering and Web. In: Proceedings of the 11th Text REtrieval Conference (2002)Google Scholar
  14. 14.
    Yang, Y., Liu, X.: A re-examination of text categorization methods. In: Proceedings of the 22nd Annual International ACM SIGIR Conference on Research and Development in Information Retrieval (1999)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2005

Authors and Affiliations

  • Yi Chang
    • 1
  • Hongbo Xu
    • 1
  • Shuo Bai
    • 1
  1. 1.Institute of Computing TechnologyChinese Academy of SciencesBeijingChina

Personalised recommendations