 Moses statistical machine translation system |
By default, only a distance-based reordering model is included in final configuration. This model gives a cost linear to the reordering distance. For instance, skipping over two words costs twice as much as skipping over one word.
However, additional conditional reordering models may be build. These are conditioned on specified factors (in the source and target language), and learn different reordering probabilities for each phrase pair (or just the foreign phrase). Possible configurations are
msd vs. monotonicity. MSD models consider three different orientation types: monotone, swap, and discontinous. Monotonicity models consider only monotone or non-monotone, in other words swap, and discontinous are lumped together.
f vs. fe. The model may be conditioned on the foreign phrase (f), or on both the foreign phrase and English phrase (fe).
unidirectional vs. bidirectional. For each phrase, the ordering of itself in respect to the previous is considered. For bidirectional models, also the ordering of the next phrase in respect to the currect phrase is modeled.
This gives us the following possible configuations:
msd-bidirectional-fe (default)
msd-bidirectional-e
msd-fe
msd-f
monotonicity-bidirectional-fe
monotonicity-bidirectional-f
monotonicity-fe
monotonicity-f
and of course distance.
Which reordering model is used (and built during the training process, if necessary) can be set with the switch -reordering, e.g.:
-reordering distance -reordering distance,msd-bidirectional-fe
Note that the distance model is always included, so there is no need to specify it.
The number of features that are created with a lexical reordering model depends on the type of the model. A msd model has three features, one each for the probability that the phrase is translated monotone, swapped, or discontinuous. A monotonicity model has only one feature. If a bidrectional model is used, then the number of features doubles - one for each direction.