Learning Logical Descriptions for Document Understanding: A Rough Sets-Based Approach

  • Emmanuelle Martienne
  • Mohamed Quafafou
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1424)

Abstract

Inductive learning systems in a logical framework are prone to difficulties when dealing with huge amount of information. In particular, the learning cost is greatly increased, and it becomes difficult to find descriptions of concepts in a reasonable time. In this paper, we present a learning approach based on Rough Set Theory, and more especially on its basic notion of concept approximation. In accordance with RST, a learning process is splitted into three steps, namely (1) partitioning of knowledge, (2) approximation of the target concept, and finally (3) induction of a logical description of this concept. The second step of approximation reduces the volume of the learning data, by computing well-chosen portions of the background knowledge which represent approximations of the concept to learn. Then, only one of these portions is used during the induction of the description, which allows for reducing the learning cost. In the first part of this paper, we report how RST’s basic notions namely indiscernibility, as well as lower and upper approximations of a concept have been adapted in order to cope with a logical framework. In the remainder of the paper, some empirical results obtained with a concrete implementation of the approach, i.e., the EAGLE system, are given. These results show the relevance of the approach, in terms of learning cost gain, on a learning problem related to the document understanding.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Botta M. 1994, Learning First Order Theories, Lecture Notes in Artificial Intelligence, 869, pp. 356–365.Google Scholar
  2. 2.
    Champesme M. 1995, Using Empirical Subsumption to Reduce the Search Space in Learning, In Proceedings of the International Conference on Conceptual Structures (ICCS’95), Santa Cruz, California, USA.Google Scholar
  3. 3.
    Esposito F., Malerba D. & Semeraro G. 1993, Automated Acquisition of Rules for Document Understanding, In proceedings of the 2nd International Conference on Document Analysis and Recognition, Tsukuba Science City, Japan, pp. 650–654.Google Scholar
  4. 4.
    Martienne E. & Quafafou M. 1998, Learning Fuzzy Relational Descriptions Using the Logical Framework and Rough Set Theory, In proceedings of the International Conferenc on Fuzzy Systems (FUZZ-IEEE’98), to appear.Google Scholar
  5. 5.
    Mitchell T.M. 1982, Generalization as search, Artificial Intelligence, 18, 203–226.CrossRefMathSciNetGoogle Scholar
  6. 6.
    Muggleton S. 1991, Inductive Logic Programming, New Generation Computing, 8(4), 295–318.MATHGoogle Scholar
  7. 7.
    Muggleton S. 1995, Inverse entailment and PROGOL, New Generation Computing, 13; 245–286.CrossRefGoogle Scholar
  8. 8.
    Ndellec C., Ad H., Bergadano F. & Tausend B. 1996, Declarative Bias in ILP, Advances in Inductive Logic Programming, De Raedt L. Ed., IOS Press, pp. 82–103.Google Scholar
  9. 9.
    Pawlak Z. 1991, Rough Sets: Theorical Aspects of Reasoning About Data, Kluwer Academic Publishers, Dordrecht, Netherlands.Google Scholar
  10. 10.
    Pazzani M. & Kibler D. 1992, The utility of knowledge in inductive learning, Machine Learning, 9(1).Google Scholar
  11. 11.
    Quafafou M. 1997, Learning Flexible Concepts from Uncertain Data, In Proceedings of the tenth International Symposium on Methodologies for Intelligent Systems (ISMIS’97), Charlotte, USA.Google Scholar
  12. 12.
    Quafafou M. 1997, α-RST: A Generalization of Rough Sets Theory, In Proceedings of the tenth International Conference on Rough Sets and Soft Computing (RSSC’97).Google Scholar
  13. 13.
    Quinlan J.R. 1990, Learning Logical Definitions from Relations,Machine Learning, 5, J. Mostow (Ed.), 239–266.Google Scholar
  14. 14.
    Tausend B. 1995, A guided tour through hypothesis spaces in ILP, Lectures notes in Artificial Intelligence: ECML 95, Springer-Verlag Ed., 912, pp. 245–259.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1998

Authors and Affiliations

  • Emmanuelle Martienne
    • 1
  • Mohamed Quafafou
    • 1
  1. 1.Institut de Recherche en Informatique de Nantes (IRIN)Nantes cedex 3

Personalised recommendations