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

ACL ID C10-1036
Title Mixture Model-based Minimum Bayes Risk Decoding using Multiple Machine Translation Systems
Venue International Conference on Computational Linguistics
Session Main Conference
Year 2010
Authors

We present Mixture Model-based Mini- mum Bayes Risk (MMMBR) decoding, an approach that makes use of multiple SMT systems to improve translation ac- curacy. Unlike existing MBR decoding methods defined on the basis of single SMT systems, an MMMBR decoder re- ranks translation outputs in the combined search space of multiple systems using the MBR decision rule and a mixture dis- tribution of component SMT models for translation hypotheses. MMMBR decod- ing is a general method that is indepen- dent of specific SMT models and can be applied to various commonly used search spaces. Experimental results on the NIST Chinese-to-English MT evaluation tasks show that our approach brings significant improvements to single system-based MBR decoding and outperforms a state- of-the-art syst...