Edinburgh Research Explorer

The University of Edinburgh’s Neural MT Systems for WMT17

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Original languageEnglish
Title of host publicationEMNLP 2017: The Second Conference on Machine Translation, Volume 2: Shared Task Papers.
PublisherAssociation for Computational Linguistics (ACL)
Number of pages11
Publication statusPublished - 8 Sep 2017
EventProceedings of the Second Conference on Machine Translation - Copenhagen, Denmark
Duration: 7 Sep 20178 Sep 2017


ConferenceProceedings of the Second Conference on Machine Translation
Abbreviated titleWMT17
Internet address


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 backtranslated 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 effectiveness of layer normalization, deep architectures, and different ensembling techniques.


Proceedings of the Second Conference on Machine Translation


Copenhagen, Denmark

Event: Conference

Download statistics

No data available

ID: 38925375