Association Computation for Information Access

  • Akihiko Takano
Part of the Lecture Notes in Computer Science book series (LNCS, volume 2843)


GETA (Generic Engine for Transposable Association) is a software that provides efficient generic computation for association. It enables the quantitative analysis of various proposed methods based on association, such as measuring similarity among documents or words. Scalable implementation of GETA can handle large corpora of twenty million documents, and provides the implementation basis for the effective information access of next generation.

DualNAVI is an information retrieval system which is a successful example to show the power and the flexibility of GETA-based computation for association. It provides the users with rich interaction both in document space and in word space. Its dual view interface always returns the retrieved results in two views: a list of titles for document space and “Topic Word Graph” for word space. They are tightly coupled by their cross-reference relation, and inspires the users with further interactions. The two-stage approach in the associative search, which is the key to its efficiency, also facilitates the content-based correlation among databases. In this paper we describe the basic features of GETA and DualNAVI.


Relevance Feedback Information Access Information Retrieval System Generic Engine Target Database 
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.
    BACE (Bio Association CEntral) (August 2000),
  2. 2.
    Butler, D.: Souped-up search engines. Nature 405, 112–115 (2000)CrossRefGoogle Scholar
  3. 3.
    GETA (Generic Engine for Transposable Association) (July 2002),
  4. 4.
    Hisamitsu, T., Niwa, Y., Tsujii, J.: Measuring Representativeness of Terms. In: Proceedings of IRAL 1999, pp. 83–90 (1999)Google Scholar
  5. 5.
    Hisamitsu, T., Niwa, Y., Tsujii, J.: A Method of Measuring Term Representativeness. In: Proceedings of COLING 2000, pp. 320–326 (2000)Google Scholar
  6. 6.
    Iwayama, M., Tokunaga, T.: Hierarchical Bayesian Clustering for Automatic Text Classification. In: Proceedings of IJCAI 1995, pp. 1322–1327 (1995)Google Scholar
  7. 7.
    Iwayama, M.: Relevance reedback with a small number of relevance judgements: incremental relevance feedback vs. document clustering. In: Proceedings of ACM SIGIR 2000, pp. 10–16 (2000)Google Scholar
  8. 8.
    Nishioka, S., Niwa, Y., Iwayama, M., Takano, A.: DualNAVI: An information retrieval interface. In: Proceedings of JSSST WISS 1997, pp. 43–48 (1997) (in Japanese)Google Scholar
  9. 9.
    Niwa, Y., Nishioka, S., Iwayama, M., Takano, A.: Topic graph generation for query navigation: Use of frequency classes for topic extraction. In: Proceedings of NLPRS 1997, pp. 95–100 (1997)Google Scholar
  10. 10.
    Niwa, Y., Iwayama, M., Hisamitsu, T., Nishioka, S., Takano, A., Sakurai, H., Imaichi, O.: Interactive Document Search with DualNAVI. In: Proceedings of NTCIR 1999, pp. 123–130 (1999)Google Scholar
  11. 11.
    Singhal, C., Buckley, C., Mitra, M.: Pivoted Document Length Normalization. In: Proceedings of ACM SIGIR 1996, pp. 21–29 (1996)Google Scholar
  12. 12.
    Takano, Y., Niwa, S., Nishioka, M., Iwayama, T., Hisamitsu, O.: Information Access Based on Associative Calculation. In: Jeffery, K., Hlaváč, V., Wiedermann, J. (eds.) SOFSEM 2000. LNCS, vol. 1963, pp. 187–201. Springer, Heidelberg (2000)CrossRefGoogle Scholar
  13. 13.
    Takano, A., Niwa, Y., Nishioka, S., Hisamitsu, T., Iwayama, M., Imaichi, O.: Associative Information Access using DualNAVI. In: Proceedings of NLPRS 2001, pp. 771–772 (2001)Google Scholar
  14. 14.
    Webcat Plus (Japanese Books Information Service) (October 2002),

Copyright information

© Springer-Verlag Berlin Heidelberg 2003

Authors and Affiliations

  • Akihiko Takano
    • 1
  1. 1.National Institute of InformaticsTokyoJapan

Personalised recommendations