A finite-state approach to phrase-based statistical machine translation
Jorge González · 2013
This paper presents a finite-state approach to phrase-based statistical machine translation where a log-linear modelling framework is implemented by means of an on-the-fly composition of weighted finite-state transducers. Moses, a well-known state-of-the-art system, is used as a machine translation reference in order to validate our results by comparison. Experiments on the TED corpus achieve a similar performance to that yielded by Moses. 1