Generating a phrase translation model by iteratively estimating phrase translation probabilities
AssigneeMicrosoft Corporation
InventorRobert C. Moore
Life of this patent
Estimating the term…
Loading patent…
AssigneeMicrosoft Corporation
InventorRobert C. Moore
Estimating the term…
A phrase translation model is trained without assuming a segmentation of training data into non-overlapping phrase pairs. Instead, the training algorithm assumes that any particular phrase instance has only a single phrase instance in another language as its translation in that instance, but that phrases can overlap. The model is trained by computing expected phrase alignment counts, deriving selection probabilities from current estimates of translation probabilities and then re-estimating phrase translation probabilities according to the expected phrase alignment counts computed. The model is trained by iterating over these steps until one or more desired stopping criteria are reached. The trained model can be deployed in a machine translation system.
A method of estimating phrase translation probabilities for use in a machine translation system, comprising:
A phrase translation model training system, comprising:
A method of training a phrase alignment model, comprising:
The method of claim 19 wherein initializing phrase translation probability values comprises:
Dependencies are inferred from the claim text.