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}
}
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
Highly Cited
This paper has 17 citations. REVIEW CITATIONS