The University of Edinburgh’s Neural MT Systems for WMT17

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

Abstract / Description of output

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.
Original languageEnglish
Title of host publicationProceedings of the Second Conference on Machine Translation
PublisherAssociation for Computational Linguistics (ACL)
Number of pages11
ISBN (Electronic)978-1-945626-96-8
Publication statusPublished - 8 Sept 2017
EventSecond Conference on Machine Translation - Copenhagen, Denmark
Duration: 7 Sept 20178 Sept 2017


ConferenceSecond Conference on Machine Translation
Abbreviated titleWMT17
Internet address


Dive into the research topics of 'The University of Edinburgh’s Neural MT Systems for WMT17'. Together they form a unique fingerprint.

Cite this