We describe a method for the fully automatic learning of hierarchical finite state translation models. The input to the method is transcribed speech utterances and their correspon...
Most statistical machine translation systems employ a word-based alignment model. In this paper we demonstrate that word-based alignment is a major cause of translation errors. We...
A word in one language can be translated to zero, one, or several words in other languages. Using word fertility features has been shown to be useful in building word alignment mo...
In this paper we use statistical machine translation and morphology information from two different morphological analyzers to try to improve translation quality by linguistically ...
Tree based translation models are a compelling means of integrating linguistic information into machine translation. Syntax can inform lexical selection and reordering choices and...