Agentized, Contextualized Filters for Information Management

  • David A. Evans
  • Gregory Grefenstette
  • Yan Qu
  • James G. Shanahan
  • Victor M. Sheftel
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 2926)

Abstract

When people read or write documents, they spontaneously generate new information needs: for example, to understand the text they are reading; to find additional information related to the points they are making in their drafts. Simultaneously, each Information Object (IO) (i.e., word, entity, term, concept, phrase, proposition, sentence, paragraph, section, document, collection, etc.) someone reads or writes also creates context for the other IOs in the same discourse. We present a conceptual model of Agentized, Contextualized Filters (ACFs)–agents that identify an appropriate context for an information object and then actively fetch and filter relevant information concerning the information object in other information sources the user has access to. We illustrate the use of ACFs in a prototype knowledge management system called ViviDocs.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Genesereth, M.R., Ketchpel, S.P.: Software agents. Communication of the ACM 37(7) (1994)Google Scholar
  2. 2.
    Evans, D.A., Shanahan, J.G., Xiang, T., Roma, N., Stoica, E., Sheftel, V.M., Montgomery, J., Bennett, J., Fujita, S., Grefenstette, G.: Topic-specific optimization and structuring. In: Voorhees, E.M., Harman, D.K. (eds.) The Tenth Text REtrieval Conference (TREC-2001). NIST Special Publication 500-250, pp. 132–141. U.S. Government Printing Office, Washington (2002)Google Scholar
  3. 3.
    Zhai, C., Jansen, P., Stoica, E., Grot, N., Evans, D.A.: Threshold calibration in CLARIT adaptive filtering. In: Voorhees, E.M., Harman, D.K. (eds.) The Seventh Text REtrieval Conference (TREC-7). NIST Special Publication 500-242, pp. 149–156. U.S. Government Printing Office, Washington (1999)Google Scholar
  4. 4.
    Evans, D.A., Grefenstette, G., Shanahan, J.G., Sheftel, V.M., Qu, Y., Hull, D.A.: Modeling QA as investigative discourse: creating networks of functionally-linked information objects. In: ARDA AQUAINT Workshop, Monterey, California (2002)Google Scholar
  5. 5.
    Bush, V.: As we may think. Atlantic Monthly 176(1), 101–108 (1945)Google Scholar
  6. 6.
    Evans, D.A., Ginther-Webster, K., Hart, M., Lefferts, R.G., Monarch, I.A.: Automatic Indexing Using Selective NLP and First-Order Thesauri. In: Lichnerowicz, A. (ed.) Proceedings of RIAO 1991, pp. 624–644. Elsevier, Amsterdam (1991)Google Scholar
  7. 7.
    Evans, D.A., Lefferts, R.G.: CLARIT-TREC Experiments. Information Processing and Management 31(3), 385–395 (1995)CrossRefGoogle Scholar
  8. 8.
    Budzik, J., Hammond, K.J.: User interactions with everyday applications as context for just-in-time information access. In: Proceedings of the 2000 International Conference on Intelligent User Interfaces, ACM Press, New Orleans (2000)Google Scholar
  9. 9.
    Rhodes, B.J., Starner, T.: Remembrance Agent: a continuously running automated information retrieval system. In: Proceedings of the First International Conference on the Practical Application of Intelligent Agents and Multi Agent Technology, pp. 487–495 (1996)Google Scholar
  10. 10.
    Rhodes, B.J., Maes, P.: Just-in-time information retrieval agents. IBM Systems Journal (special issue on the MIT Media Laboratory) 39(3&4), 685–704 (2000)Google Scholar
  11. 11.
    Shanahan, J.G., Grefenstette, G.: Meta-document and method of managing meta-documents. European Patent # EP1143356. Pending (2001) (Filing Date: April 4, 2001)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2004

Authors and Affiliations

  • David A. Evans
    • 1
  • Gregory Grefenstette
    • 1
  • Yan Qu
    • 1
  • James G. Shanahan
    • 1
  • Victor M. Sheftel
    • 1
  1. 1.Clairvoyance CorporationPittsburghUSA

Personalised recommendations