Mixtures of IBM Model 2 ∗

Mixture modelling is a standard pattern classification technique. However, in statistical machine translation, the use of mixture modelling is still unexplored. Two main advantages of the mixture approach are first, its flexibility to find an appropriate tradeoff between model complexity and the amount of training data available and second, its capability to learn specific probability distributions that better fit 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. Preliminary experiments carried out on the Tourist task show that the mixture extension conveys a decrease in word-error rate of up to 15%.