Skip to main content
SpringerLink
Log in

Training Agents to Recognize Text by Example

  • Published:
Autonomous Agents and Multi-Agent Systems Aims and scope Submit manuscript

Abstract

An important function of an agent is to be “on the lookout” for bits of information that are interesting to its user, even if these items appear in the midst of a larger body of unstructured information. But how to tell these agents which patterns are meaningful and what to do with the result? Especially when agents are used to recognize text, they are usually driven by parsers which require input in the form of textual grammar rules. Editing grammars is difficult and error-prone for end users. Grammex [“Grammars by Example”] is the first direct manipulation interface designed to allow non-expert users to define grammars interactively. The user presents concrete examples of text that he or she would like the agent to recognize. Rules are constructed by an iterative process, where Grammex heuristically parses the example, displays a set of hypotheses, and the user critiques the system's suggestions. Actions to take upon recognition are also demonstrated by example.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Similar content being viewed by others

References

  1. T. Bonura, and J. Miller, “Drop zones: an extension to LiveDoc,” SigCHI Bull. vol. 30, no. 2, pp. 59-64, April, 1998.

    Google Scholar 

  2. J. Cowie, and W. Lehnert, “Information extraction,” Commun. ACM, vol. 39, no. 2, January 1996.

  3. A. Cypher (ed.), Watch What I Do: Programming by Demonstration, MIT Press: Cambridge, MA, 1993.

    Google Scholar 

  4. P. Langley, “Machine learning and grammar induction,” Mach. Learn. J. vol. 2, pp. 5-8, 1987.

    Google Scholar 

  5. H. Lieberman, “Tinker: a programming by demonstration system for beginning programmers,” in A. Cypher (ed.), Watch What I Do: Programming by Demonstration, MIT Press: Cambridge, MA, 1993.

    Google Scholar 

  6. H. Lieberman, “Integrating user interface agents with conventional applications,” ACM Conf. Intell. User Interfaces, San Francisco, January, 1998. Revised version to appear in Knowledge Syst. J.

  7. D. Maulsby, and I. H. Witten, “Learning to describe data in actions,” in Proc. Programming by Demonstration Workshop, Twelfth Int. Conf. Mach. Learn., Tahoe City, CA, July, 1995, pp. 65-73.

  8. D. Maulsby, “Instructible agents,” Ph.D. Thesis, University of Calgary, Canada, 1994.

    Google Scholar 

  9. J. Miller, and T. Bonura, “From documents to objects: an overview of LiveDoc,” SigCHI Bull. vol. 30, no. 2, pp. 53-59, April, 1998.

    Google Scholar 

  10. B. Myers, “Tourmaline: Text Formatting by Demonstration,” in A. Cypher (ed.), Watch What I Do: Programming by Demonstration, MIT Press: Cambridge, MA, 1993.

    Google Scholar 

  11. B. Nardi, A Small Matter of Programming Perspectives on End User Computing, MIT Press: Cambridge, MA, 1993.

    Google Scholar 

  12. B. Nardi, J. Miller, and D. Wright, “Collaborative, programmable intelligent agents,” Commun. ACM, March, 1998.

  13. M. Pandit, and S. Kalbag, “The selection recognition agent: instant access to relevant information and operations, in Proc. Intell. User Interfaces '97, ACM Press: New York, 1997.

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Media Laboratory, Massachusetts Institute of Technology, Cambridge, MA, 02139, USA

    Henry Lieberman

  2. AT&T Labs West, Menlo Park, CA, 94025, USA

    Bonnie A. Nardi

  3. Apple Computer, 1 Infinite Loop, Cupertino, CA, 95014, USA

    David J. Wright

Authors
  1. Henry Lieberman
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Bonnie A. Nardi
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. David J. Wright
    View author publications

    You can also search for this author in PubMed Google Scholar

Rights and permissions

Reprints and permissions

About this article

Cite this article

Lieberman, H., Nardi, B.A. & Wright, D.J. Training Agents to Recognize Text by Example. Autonomous Agents and Multi-Agent Systems 4, 79–92 (2001). https://doi.org/10.1023/A:1010018830260

Download citation

  • Issue Date:

  • DOI: https://doi.org/10.1023/A:1010018830260

Search

Navigation