Corpus ID: 672106

Mixture Model-based Minimum Bayes Risk Decoding using Multiple Machine Translation Systems

@inproceedings{Duan2010MixtureMM,
  title={Mixture Model-based Minimum Bayes Risk Decoding using Multiple Machine Translation Systems},
  author={Nan Duan and Mu Li and Dongdong Zhang and Ming Zhou},
  booktitle={COLING},
  year={2010}
}
  • Nan Duan, Mu Li, +1 author Ming Zhou
  • Published in COLING 2010
  • Computer Science
  • We present Mixture Model-based Minimum Bayes Risk (MMMBR) decoding, an approach that makes use of multiple SMT systems to improve translation accuracy. Unlike existing MBR decoding methods defined on the basis of single SMT systems, an MMMBR decoder reranks translation outputs in the combined search space of multiple systems using the MBR decision rule and a mixture distribution of component SMT models for translation hypotheses. MMMBR decoding is a general method that is independent of… CONTINUE READING

    Create an AI-powered research feed to stay up to date with new papers like this posted to ArXiv

    Citations

    Publications citing this paper.
    SHOWING 1-10 OF 11 CITATIONS

    Hypothesis Mixture Decoding for Statistical Machine Translation

    VIEW 4 EXCERPTS
    CITES METHODS & BACKGROUND

    Bagging and Boosting statistical machine translation systems

    VIEW 2 EXCERPTS
    CITES METHODS & BACKGROUND

    Query rewriting using statistical machine translation

    VIEW 2 EXCERPTS
    CITES METHODS & BACKGROUND

    Combining Multiple Alignments to Improve Machine Translation

    VIEW 2 EXCERPTS
    CITES BACKGROUND

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 20 REFERENCES

    ForestBased Translation

    • Mi Haitao, Liang Huang, Qun Liu.
    • Proc. of 46 Meeting of the Association for Computational Linguistics, pages 192-199.
    • 2008

    An Empirical Study on Computing Consensus Translations from multiple Machine Translation Systems

    • Macherey Wolfgang, Franz Och.
    • Proc. of Empirical Methods on Natural Language Processing, pages 986-995.
    • 2007