This paper describes LIUM submissions to WMT17 News Translation Task for English-German, English-Turkish, English-Czech and English-Latvian language pairs. We train BPE-based attentive Neural Machine Translation systems with and without factored outputs using the open source nmtpy framework. Competitive scores were obtained by ensembling various systems and exploiting the availability of target monolingual corpora for back-translation. The impact of back-translation quantity and quality is also analyzed for English-Turkish where our post-deadline submission surpassed the best entry by +1.6 BLEU.
@article{arxiv.1707.04499,
title = {LIUM Machine Translation Systems for WMT17 News Translation Task},
author = {Mercedes García-Martínez and Ozan Caglayan and Walid Aransa and Adrien Bardet and Fethi Bougares and Loïc Barrault},
journal= {arXiv preprint arXiv:1707.04499},
year = {2017}
}
Comments
News Translation Task System Description paper for WMT17