Abstract
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.
Cite
CITATION STYLE
García-Martínez, M., Caglayan, O., Aransa, W., Bardet, A., Bougares, F., & Barrault, L. (2017). LIUM machine translation systems for WMT17 news translation task. In WMT 2017 - 2nd Conference on Machine Translation, Proceedings (pp. 288–295). Association for Computational Linguistics (ACL). https://doi.org/10.18653/v1/w17-4726
Register to see more suggestions
Mendeley helps you to discover research relevant for your work.
