0 Acoustic model score: p(O|W) o Haptic model score : p(H|£)

o PLI model score : P(£|W)

0 Language model score : P(W)

The agreement model scores sequences of morpho-syntactic word classes, which express grammatical features relevant to agreement.

However, in MT, we seek a measure of sentence quality (1(6) that is comparable across different hypotheses on the beam (much like the n-gram language model score ).

Discriminative model scores have been used as MT features (Galley and Manning, 2009), but we obtained better results by scoring the l-best class sequences with a generative model.

The agreement model score is one decoder feature function.

Our model scores hypotheses during decoding.

where 6} denotes the mixture operation between two or more model scores .

o Weighted Max (wmax): where the ensemble score is the weighted max of all model scores .

Since in log-linear models, the model scores are not normalized to form probability distributions, the scores that different models assign to each phrase-pair may not be in the same scale.

An interesting observation based on the results in Table 3 is that uniform weights are doing reasonably well given that the component weights are not optimized and therefore model scores may not be in the same scope (refer to discussion in §3.2).