Mixtures of IBM Model 2
Jorge Civera, Alfons Juan · 2006
Mixture modelling is a standard pattern classication technique. However, in statistical machine translation, the use of mixture modelling is still un-explored. Two main advantages of the mixture approach are rst, its ex-ibility to nd an appropriate tradeo between model complexity and the amount of training data available and second, its capability to learn specic probability distributions that better t subsets of the training dataset. This latter advantage is even more important in statistical machine translation, since it is well known that most of the current translation models proposed have limited application to restricted semantic domains. In this paper, we describe a mixture extension of the IBM model 2 along with the maximum likelihood estimation of its parameters through the EM algorithm and a dynamic-programming decoding algorithm for this mixture model. Prelim-inary experiments carried out on the Tourist task show that the mixture extension conveys a decrease in word-error rate of up to 15%. 1