@Article{Pecheux16reordering,
author="P{\'e}cheux, Nicolas
and Allauzen, Alexandre
and Niehues, Jan
and Yvon, Fran{\c{c}}ois",
title="Reordering space design in statistical machine translation",
journal="Language Resources and Evaluation",
year="2016",
volume="50",
number="2",
pages="375--410",
abstract="In Statistical Machine Translation (SMT), the constraints on word reorderings have a great impact on the set of potential translations that is explored during search. Notwithstanding computational issues, the reordering space of a SMT system needs to be designed with great care: if a larger search space is likely to yield better translations, it may also lead to more decoding errors, because of the added ambiguity and the interaction with the pruning strategy. In this paper, we study the reordering search space, using a state-of-the art translation system, where all reorderings are represented in a permutation lattice prior to decoding. This allows us to directly explore and compare different reordering schemes and oracle settings. We also study in detail a rule-based preordering system, varying the length and number of rules, the tagset used, as well as contrasting with purely combinatorial subsets of permutations. We carry out experiments on three language pairs in both directions: English-French, a close language pair; English-German and English-Czech, two much more challenging pairs. We show that even though it might be desirable to design better reordering spaces, model and search errors seem to be the most important issues. Therefore, improvements of the reordering space should come along with improvements of the associated models to be really effective.",
issn="1574-0218",
doi="10.1007/s10579-016-9353-8",
url="http://dx.doi.org/10.1007/s10579-016-9353-8"
}