FBK's participation to the English-to-German news translation task of WMT 2017

Abstract

In this paper we report on FBK's participation to the English-to-German news translation task of the Second Conference on Machine Translation (WMT'17). The submitted system is based on Neural Machine Translation using byte-pair encoding segmentation on both source and target languages for open-vocabulary translations. Back-translations of news monolingual data are used for improving the translations fluency on the in-domain data. With respect to last year's evaluation, our baseline outperforms the 2016 best system's baseline on the test sets 2015 and 2016. However, in our set-up back-translations produced a smaller improvement than expected. The final submission is given by the combination of 7 systems, including a system trained only on true parallel data and two right-to-left systems, which improves over our single best system by 1.5 BLEU points.