Corpus-based learning of generalized parse tree rules for translation

  • H. Altay Güvenir
  • Ayşegül Tunç
Natural Language II: Understanding
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1081)


This paper proposes a learning mechanism to acquire structural correspondences between two languages from a corpus of translated sentence pairs. The proposed mechanism uses analogical reasoning between two translations. Given a pair of translations, the similar parts of the sentences in the source language must correspond the similar parts of the sentences in the target language. Similarly, the different parts should correspond to the respective parts in the translated sentences. The correspondences between the similarities, and also differences are learned in the form of rewrite rules. The system is tested on a small training dataset and produced promising results for further investigation.


Machine Translation Target Language Parse Tree Target Sentence Source Language 
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.
    Arnold D., Balkan L., Humphreys R. Lee, Meijer S. Sadler L.: Machine Translation, NCC Blackwell (1994).Google Scholar
  2. 2.
    Carbonell, J.G.: Derivational Analogy: A Theory of Reconstructive Problem Solving and Expertise Acquisition. In Jude W. Shavlik and Thomas G. Dietterich (eds), Readings in Machine Learning, Morgan Kaufmann (1990) 636–646.Google Scholar
  3. 3.
    Furuse, O. and Iida, H.: Cooperation between Transfer and Analysis in Example-Based Framework, Proceedings of COLING-92 (1992).Google Scholar
  4. 4.
    Hammond, K.J.: (Ed.) Proceedings: Second Case-Based Reasoning Workshop. Pensacola Beach, FL:Morgan Kaufmann, (1989).Google Scholar
  5. 5.
    Kitano, H.: A Comprehensive and Practical Model of Memory-Based Machine Translation. In Ruzena Bajcsy (Ed.) Proceedings of the Thirteenth International Joint Conference on Artificial Intelligence, Morgan Kaufmann V.2 (1993) 1276–1282.Google Scholar
  6. 6.
    Kolodner, J.L.: (Ed.) Proceedings of a Workshop on Case-Based Reasoning. Clear-water Beach, FL:Morgan Kaufmann (1988).Google Scholar
  7. 7.
    Nagao, M. A.: Framework of a Mechanical Translation between Japanese and English by Analogy Principle (1985).Google Scholar
  8. 8.
    Ram, A.: Indexing, Elaboration and Refinement: Incremental Learning of Explanatory Cases. In Janet L. Kolodner (ed.), Case-Based Learning, Kluwer Academic Publishers (1993).Google Scholar
  9. 9.
    Reisbech, C. and Schank, R.: Inside the Case-Based Reasoning, Lawrence Elbaum Associates (1990).Google Scholar
  10. 10.
    Sato, S.: Example-Based Machine Translation, Ph.D. Thesis, Kyoto University (1991).Google Scholar
  11. 11.
    Sato, S. and Nagao, M.: The Memory-Based Translation, Proceedings of COLING-90 (1990).Google Scholar
  12. 12.
    Siskind, J.M.: Lexical Acquisition in the presence of Noise and Homonymy, Proceedings AAAI-94 (1994) 760–766.Google Scholar
  13. 13.
    Stanfill, C. and Waltz, D.: Toward Memory-Based Reasoning. CACM, Vol. 29, No.12 (1991) 185–192.Google Scholar
  14. 14.
    Sumita, E. and Iida, H.: Experiments and Prospects of Example-Based Machine Translation, Proceedings of the 29th Annual Meeting of the Association for Computational Linguistics (1991).Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1996

Authors and Affiliations

  • H. Altay Güvenir
    • 1
  • Ayşegül Tunç
    • 1
  1. 1.Department of Computer Engineering and Information Sciences Bilkent UniversityAnkaraTurkey

Personalised recommendations