SCIENCE@home

Intersecting Multilingual Data for Faster and Better Statistical Translations

Yu Chen,M. Kay,A. Eisele

Published 2009 in North American Chapter of the Association for Computational Linguistics

ABSTRACT

In current phrase-based SMT systems, more training data is generally better than less. However, a larger data set eventually introduces a larger model that enlarges the search space for the translation problem, and consequently requires more time and more resources to translate. We argue redundant information in a SMT system may not only delay the computations but also affect the quality of the outputs. This paper proposes an approach to reduce the model size by filtering out the less probable entries based on compatible data in an intermediate language, a novel use of triangulation, without sacrificing the translation quality. Comprehensive experiments were conducted on standard data sets. We achieved significant quality improvements (up to 2.3 Bleu points) while translating with reduced models. In addition, we demonstrate a straightforward combination method for more progressive filtering. The reduction of the model size can be up to 94% with the translation quality being preserved.

PUBLICATION RECORD

  • Publication year

    2009

  • Venue

    North American Chapter of the Association for Computational Linguistics

  • Publication date

    2009-05-31

  • Fields of study

    Linguistics, Computer Science

  • Identifiers
    DOI 10.3115/1620754.1620773
  • External record

    Open on Semantic Scholar

  • Source metadata

    Semantic Scholar

CITATION MAP

EXTRACTION MAP

CLAIMS

  • No claims are published for this paper.

CONCEPTS

  • No concepts are published for this paper.

REFERENCES

Showing 1-14 of 14 references · Page 1 of 1

CITED BY

Showing 1-14 of 14 citing papers · Page 1 of 1