Integration of a Multilingual Preordering Component into a Commercial SMT Platform

Anita Ramm, Riccardo Superbo, Dimitar Shterionov, Tony O'Dowd, Alexander Fraser

We present a multilingual preordering component tailored for a
commercial Statistical Machine translation platform. In commercial
settings, issues such as processing speed as well as the ability to
adapt models to the customers' needs play a significant role and have
a big impact on the choice of approaches that are added to the custom
pipeline to deal with specific problems such as long-range
reorderings.  We developed a fast and customisable preordering
component, also available as an opensource tool, which comes along
with a generic implementation that is restricted neither to the
translation platform nor to the Machine Translation paradigm. We test
preordering on three language pairs: English to 
Japanese/German/Chinese for both Statistical Machine Translation (SMT)
and Neural Machine Translation (NMT). Our experiments confirm
previously reported improvements in the SMT output when the models are
trained on preordered data, but they also show that preordering does
not improve NMT.