Stone Soup and the French Room

  • Yorick Wilks
Part of the Linguistica Computazionale book series (LICO, volume 9)


The paper argues that the IBM statistical approach to machine translation ha; done rather better after a few years than many sceptics believed it could. However, it is neither as novel as its proponents suggest nor is it making claims as clear and simple as they would have us believe. The performance of the purely statistical system (and we discuss what that phrase could mean) has not equaled the performance of SYSTRAN. More importantly, the system is now being shifted to a hybrid that incorporates much of the linguistic information that it was initially claimed by IBM would not be needed for MT. Hence, one might infer that its own proponents do not believe “pure” statistics sufficient for MT of a usable quality. In addition to real limits on the statistical method, there are also strong economic limits imposed by their methodology of data gathering. However, the paper concludes that the IBM: group have done the field a great service in pushing these methods far further than. before, and by reminding everyone of the virtues of empiricism in the field and the need for large scale gathering of data.


Machine Translation Computational Linguistics Parallel Corpus Symbolic Structure Preference Semantic 
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]
    Bar-Hillel, Y., “The present status of automatic translation of languages”, in J. Alt (ed.), Advances in Computers 1, Academic Press, New York, 1960.Google Scholar
  2. [2]
    Brown, P.F., J. Cocke, S. Della Pietra, V. Della Pietra, F. Jelinek, J. Lafferty, R. Mercer, P. Roossin, “A statistical approach to machine translation”, in Computational Linguistics, 16, 1990, 79–85.Google Scholar
  3. [3]
    Brown, P.F., J. Lai, R. Mercer, “Aligning sentences in parallel corpora”, in Proceedings 29th Annual Meeting of the Association for Computational Linguistics, Berkeley, CA, 1991, 169–176.CrossRefGoogle Scholar
  4. [4]
    Chomsky, N., Syntactic Structures, Mouton and Co., The Hague, 1957.Google Scholar
  5. [5]
    Dennett, D., Consciousness Explained, Bradford Books, Cambridge MA, 1991.Google Scholar
  6. Gale, W., K. Church, “Poor estimates of context are worse than none”, in Proc. 1990 DARPA Speech and Language Meeting,Hidden Valley, PA, 1990.Google Scholar
  7. [7]
    King, G. “Stochastic methods of mechanical translation”, in Mechanical Translation, 3, 1956.Google Scholar
  8. [8]
    Jelinek, E, R. Mercer, “Interpolated estimation of Markov source parameters from sparse data”, in Proceedings of the Workshop on Pattern Recognition in Practice, North Holland, Amsterdam, The Netherlands, 1980.Google Scholar
  9. [9]
    Lehnert, W., B. Sundheim, “A performance evaluation of text analysis technologies”, Al magazine, 12, 1991.Google Scholar
  10. [10]
    McCord, M., “A new version of the machine translation system LMT”, Literary & Linguistic Computing, 4, 1989.Google Scholar
  11. [l1]
    Wilks, Y., “A preferential pattern-matching semantics for natural language understanding”, Artificial Intelligence, 11, 1975.Google Scholar

Copyright information

© Springer Science+Business Media Dordrecht 1994

Authors and Affiliations

  • Yorick Wilks
    • 1
  1. 1.Department of Computer ScienceUniversity of SheffieldUSA

Personalised recommendations