The University of Edinburgh's Neural MT Systems for WMT17
This is an incremental improvement for machine translation researchers and practitioners, focusing on specific tasks and language pairs.
The paper describes the University of Edinburgh's neural machine translation systems for the WMT17 shared tasks, tackling news and biomedical translation across multiple language pairs, with results including improvements from deep architectures and layer normalization, though no concrete numbers are provided in the 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.