Distance phrase reordering for moses - user manual and code guide
Yizhao Ni, Mahesan Niranjan, Craig Saunders and Sandor Szedmak
University of Southampton, Southampton, UK.
We describe the implementation of a novel distance phrase reordering (DPR) model for a public domain statistical machine translation (SMT) system - MOSES. The model mainly focuses on the application of machine learning (ML) techniques to a speciﬁc problem in machine translation: learning the grammatical rules and content dependent changes, which are simpliﬁed as phrase reorderings. This document serves two purposes: a user manual for the functions of the DPR model and a code guide for developers.