Better Contextual Translation Using Machine Learning

Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 2499)


One of the problems facing translation systems that automatically extract transfer mappings (rules or examples) from bilingual corpora is the trade-off between contextual specificity and general applicability of the mappings, which typically results in conflicting mappings without distinguishing context. We present a machine-learning approach to choosing between such mappings, using classifiers that, in effect, selectively expand the context for these mappings using features available in a linguistic representation of the source language input. We show that using these classifiers in our machine translation system significantly improves the quality of the translated output. Additionally, the set of distinguishing features selected by the classifiers provides insight into the relative importance of the various linguistic features in choosing the correct contextual translation.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Hiroyuki Kaji, Yuuko Kida, and Yasutsugu Morimoto: Learning Translation Templates from Bilingual Text. In Proceedings of COLING (1992)Google Scholar
  2. 2.
    Adam Meyers, Michiko Kosaka and Ralph Grishman: Chart-based transfer rule application in machine translation. In Proceedings of COLING (2000)Google Scholar
  3. 3.
    Hideo Watanabe, Sado Kurohashi, and Eiji Aramaki: Finding Structural Correspondences from Bilingual Parsed Corpus for Corpus-based Translation. In Proceedings of COLING (2000)Google Scholar
  4. 4.
    Benoit Lavoie, Michael White and Tanya Korelsky: Inducing Lexico-Structural Transfer Rules from Parsed Bi-texts. In Proceedings of the Workshop on Data-driven Machine Translation, ACL 2001, Toulouse, France (2001)Google Scholar
  5. 5.
    Stephen D. Richardson, William Dolan, Monica Corston-Oliver, and Ami Menezes, Overcoming the customization bottleneck using example-based MT. In Proceedings of the Workshop on Data-Driven Machine Translation, ACL 2001.Toulouse, France (2001)Google Scholar
  6. 6.
    Adam Meyers, Roman Yangarber, Ralph Grishman, Catherine Macleod, and Antonio Moreno-Sandoval: Deriving transfer rules from dominance-preserving alignments. In Proceedings of COLING (1998)Google Scholar
  7. 7.
    Hideo Watanabe: A method for distinguishing exceptional and general examples in example-based transfer systems. In Proceedings of COLING (1994)Google Scholar
  8. 8.
    Ami Menezes and Stephen D. Richardson: A best-first alignment algorithm for automatic extraction of transfer mappings from bilingual corpora. In Proceedings of the Workshop on Data-Driven Machine Translation, ACL 2001.Toulouse, France (2001)Google Scholar
  9. 9.
    David Maxwell Chickering, David Heckerman, and Christopher Meek: A Bayesian approach to learning Bayesian networks with local structure. In D. Geiger, and P. Pundalik Shenoy (Eds.), Uncertainty in Artificial Intelligence: Proceedings of the Thirteenth Conference. 80–89. (1997)Google Scholar
  10. 10.
    Stanley Chen and Joshua Goodman: An empirical study of smoothing techniques for language modeling, In Proceedings of ACL (1996)Google Scholar
  11. 11.
    Frederick Jelinek and Robert L. Mercer: Interpolated estimation of Markov source parameters from sparse data. In Proceedings of the Workshop on Pattern Recognition in Practice, Amsterdam, The Netherlands (1980)Google Scholar
  12. 12.
    David Heckerman, David Maxwell Chickering, Christopher Meek, Robert Rounthwaite, Carl Kadie: Dependency networks for inference, collaborative filtering and data visualization. In Journal of Machine Learning Research 1:49–75 (2000)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2002

Authors and Affiliations

  1. 1.Microsoft ResearchRedmondUSA

Personalised recommendations