Abstract

This paper describes the University of Edinburgh's submissions to the WMT17 shared news translation and biomedical translation tasks. We participated in 12 translation directions for news, translating between English and Czech, German, Latvian, Russian, Turkish and Chinese. For the biomedical task we submitted systems for English to Czech, German, Polish and Romanian. Our systems are neural machine translation systems trained with Nematus, an attentional encoder-decoder. We follow our setup from last year and build BPE-based models with parallel and back-translated monolingual training data. Novelties this year include the use of deep architectures, layer normalization, and more compact models due to weight tying and improvements in BPE segmentations. We perform extensive ablative experiments, reporting on the effectivenes of layer normalization, deep architectures, and different ensembling techniques.

Citation information

Sennrich, R, Birch-Mayne, A, Currey, A, Germann, U, Haddow, B, Heafield, K, Miceli Barone, A & Williams, P 2017, The University of Edinburgh’s Neural MT Systems for WMT17. in EMNLP 2017: The Second Conference on Machine Translation, Volume 2: Shared Task Papers.. Association for Computational Linguistics (ACL), pp. 389-399, Proceedings of the Second Conference on Machine Translation, Copenhagen, Denmark, 7-8 September. DOI: 10.18653/v1/W17-4739

Turing affiliated authors