SCIENCE@home

Variational Decoding for Statistical Machine Translation

Zhifei Li,Jason Eisner,S. Khudanpur

Published 2009 in Annual Meeting of the Association for Computational Linguistics

ABSTRACT

Statistical models in machine translation exhibit spurious ambiguity. That is, the probability of an output string is split among many distinct derivations (e.g., trees or segmentations). In principle, the goodness of a string is measured by the total probability of its many derivations. However, finding the best string (e.g., during decoding) is then computationally intractable. Therefore, most systems use a simple Viterbi approximation that measures the goodness of a string using only its most probable derivation. Instead, we develop a variational approximation, which considers all the derivations but still allows tractable decoding. Our particular variational distributions are parameterized as n-gram models. We also analytically show that interpolating these n-gram models for different n is similar to minimum-risk decoding for BLEU (Tromble et al., 2008). Experiments show that our approach improves the state of the art.

PUBLICATION RECORD

  • Publication year

    2009

  • Venue

    Annual Meeting of the Association for Computational Linguistics

  • Publication date

    2009-08-02

  • Fields of study

    Linguistics, Computer Science

  • Identifiers
    DOI 10.3115/1690219.1690229
  • 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 1-32 of 32 references · Page 1 of 1

CITED BY

Showing 1-85 of 85 citing papers · Page 1 of 1