Constructive learning of translations based on dictionaries

  • Noriko Sugimoto
  • Kouichi Hirata
  • Hiroki Ishizaka
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1160)


Learning a translation based on a dictionary is to extract a binary relation over strings from given examples based on information supplied by the dictionary. In this paper, we introduce a restricted elementary formal system called a regular TEFS to formalize translations and dictionaries. Then, we propose a learning algorithm that identifies a translation defined by a regular TEFS from positive and negative examples. The main advantage of the learning algorithm is constructive, that is, the produced hypothesis reflects the examples directly. The learning algorithm generates the most specific clauses from examples by referring to a dictionary, generalizes these clauses, and then removes too strong clauses from them. As a result, the algorithm can learn translations over context-free languages.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    S. Arikawa, S. Miyano, A. Shinohara, T. Shinohara, and A. Yamamoto. Algorithmic learning theory with elementary formal systems. IEICE Transaction on Information and Systems., E75-D:405–414, 1992.Google Scholar
  2. 2.
    S. Arikawa, T. Shinohara, and A. Yamamoto. Learning elementary formal systems. Theoretical Computer Science, 97–113, 1992.Google Scholar
  3. 3.
    R. B. Banerji. Learning theories in a subset of a polyadic logic. In Proc. Computational Learning Theory '88, 281–295, 1988.Google Scholar
  4. 4.
    H. Ishizaka. Inductive inference of regular languages based on model inference. International journal of Computer Mathematics, 27:67–83, 1989.Google Scholar
  5. 5.
    H. Ishizaka. Polynomial time learnability of simple deterministic languages. Machine Learning, 5(2):151–164, 1990.Google Scholar
  6. 6.
    X. Ling. Learning and invention of Horn clause theories — a constructive method. In Z. W. Ras, editor, Methodologies for Intelligent System, 4:323–331, NorthHolland, 1989.Google Scholar
  7. 7.
    S. Muggleton. Inductive logic programming. Academic Press, 1992.Google Scholar
  8. 8.
    S. Muggleton and W. Buntine. Machine invention of first-order predicates by inverting resolution. In Proc. 5th International Conference on Machine Learning, 339–352, 1988.Google Scholar
  9. 9.
    E. Shapiro. Inductive inference of theories from facts. Research report 192, Yale Univ., 1981.Google Scholar
  10. 10.
    T. Shinohara. Rich classes inferable from positive data: length-bounded elementary formal system. Information and computation, 108:175–186, 1994.CrossRefGoogle Scholar
  11. 11.
    A. Yamamoto. Procedural semantics and negative information of elementary formal system. Journal of Logic Programming, 13:89–97, 1992.MathSciNetGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1996

Authors and Affiliations

  • Noriko Sugimoto
    • 1
  • Kouichi Hirata
    • 1
  • Hiroki Ishizaka
    • 1
  1. 1.Department of Artificial IntelligenceKyushu Institute of TechnologyIizukaJapan

Personalised recommendations