Sentence Retrieval with LSI and Topic Identification

  • David Parapar
  • Álvaro Barreiro
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3936)

Abstract

This paper presents two sentence retrieval methods. We adopt the task definition done in the TREC Novelty Track: sentence retrieval consists in the extraction of the relevant sentences for a query from a set of relevant documents for that query. We have compared the performance of the Latent Semantic Indexing (LSI) retrieval model against the performance of a topic identification method, also based on Singular Value Decomposition (SVD) but with a different sentence selection method. We used the TREC Novelty Track collections from years 2002 and 2003 for the evaluation. The results of our experiments show that these techniques, particularly sentence retrieval based on topic identification, are valid alternative approaches to other more ad-hoc methods devised for this task.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Harman, D.: Overview of the TREC 2002 Novelty Track. In: The Eleventh Text REtrieval Conference, pp. 17–28. NIST Special Publication 500-251 (2002)Google Scholar
  2. 2.
    White, R.W., Jose, J.M., Ruthven, I.: Using top-ranking sentences to facilitate effective information access. JASIST 56(10), 1113–1125 (2005)CrossRefGoogle Scholar
  3. 3.
    Larkey, L.S., Allan, J., Connell, M.E., Bolivar, A., Wade, C.: UMass at TREC 2002: Cross Language and Novelty Tracks. In: The Eleventh Text REtrieval Conference, pp. 721–732. NIST Special Publication 500-251 (2002)Google Scholar
  4. 4.
    Zhang, M., Song, R., Lin, C., Ma, S., Jiang, Z., Jin, Y., Liu, Y., Zhao, L.: THU TREC 2002: Novelty Track Experiments. In: The Eleventh Text REtrieval Conference, pp. 591–595. NIST Special Publication 500-251 (2002)Google Scholar
  5. 5.
    Berry, M.W., Dumais, S.T., Letsche, T.A.: Computational Methods for Intelligent Information Access. In: Supercomputing 1995: Proceedings of the 1995 ACM/IEEE conference on Supercomputing (1995)Google Scholar
  6. 6.
    Deerwester, S.C., Dumais, S.T., Landauer, T.K., Furnas, G.W., Harshman, R.A.: Indexing by Latent Semantic Analysis. JASIS 41(6), 391–407 (1990)CrossRefGoogle Scholar
  7. 7.
    Gong, Y., Liu, X.: Generic text summarization using relevance measure and latent semantic analysis. In: SIGIR 2001, Proceedings of the 24th Annual International ACM SIGIR conference on Research and Development in Information Retrieval, pp. 19–25 (2001)Google Scholar
  8. 8.
    Soboroff, I., Harman, D.: Overview of the TREC 2003 Novelty Track. In: The Twelfth Text REtrieval Conference, pp. 38–53. NIST Special Publication 500-255 (2003)Google Scholar
  9. 9.
    Telcordia Technologies: LSI Software Home, http://lsi.research.telcordia.com
  10. 10.
  11. 11.
    Dumais, S.: Enhancing Performance in Latent Semantic Indexing. TM-ARH- 017527 Technical Report, Bellcore (1990)Google Scholar
  12. 12.
    Cronen-Townsend, S., Zhou, Y., Croft, W.B.: Predicting Query Performance. In: SIGIR 2002, Proceedings of the 25th Annual International ACM SIGIR conference on Research and Development in Information Retrieval, pp. 299–306 (2002)Google Scholar
  13. 13.
    He, B., Ounis, I.: Inferring query performance using pre-retrieval predictors. In: Apostolico, A., Melucci, M. (eds.) SPIRE 2004. LNCS, vol. 3246, pp. 43–54. Springer, Heidelberg (2004)CrossRefGoogle Scholar
  14. 14.
    Buckley, C.: Why current IR engines fail. In: SIGIR 2004, Proceedings of the 27th Annual International ACM SIGIR conference on Research and Development in Information Retrieval, pp. 584–585 (2004)Google Scholar
  15. 15.
    Soboroff, I.: Overview of the TREC 2004 Novelty Track. In: The Thirteenth Text REtrieval Conference Proceedings. NIST Special Publication 500-261 (2004)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • David Parapar
    • 1
  • Álvaro Barreiro
    • 1
  1. 1.IR Lab, Department of Computer ScienceUniversity of A CoruñaA CoruñaSpain

Personalised recommendations