This can be used for example in the case where the experts are derived from probabilistic models .

Furthermore, these methods typically assume the use of probabilistic models , which is not a requirement in our learning scenario.

Other ensembles of probabilistic models have also been considered in text and speech processing by forming a product of probabilistic models via the intersection of lattices (Mohri et al., 2008), or a straightforward combination of the posteriors from probabilistic grammars trained using EM with different starting points (Petrov, 2010), or some other rather intricate techniques in speech recognition (Fiscus, 1997).

In this paper we use a basic neural network architecture and a lexicalized probability model to create a powerful MT decoding feature.

Formally, the probability model is:

far too sparse for standard probability models such as Kneser-Ney back-off (Kneser and Ney, 1995) or Maximum Entropy (Rosenfeld, 1996).

However, these new methods lack the rich priors associated with probabilistic models .

For example, if we are seeking the MLE of a probabilistic model parameterized by 6, p(:c|6), adding a regularization term 7(6) = 2le 6?

This is the typical evaluation for probabilistic models .