Jorge Civera and  Alfons Juan.  Mixtures of IBM Model  2.  In Proc. of
the 11th Annual  Conf. of the European Assoc.  for Machine Translation
(EAMT 2006), pages 159-167, Oslo (Norway), jun 2006.

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 the  limited application to restricted  semantic domains of
most of  the current  translation models proposed.  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
dinamic-programming   decoding  algorithm   for  this   mixture  model
Preliminary experiments carried out on  the Tourist task show that the
mixture extension conveys  a decreasement in word-error rate  of up to
15\%.