# The University of Edinburgh's Neural MT Systems for WMT17

arXiv: https://arxiv.org/abs/1708.00726 · HTML: https://mlsanity.com/paper/1708.00726/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 Aug 2017.

## Built on by (most cited first, 16 of 16)

- [Domain Adaptation and Multi-Domain Adaptation for Neural Machine Translation: A Survey](https://mlsanity.com/paper/2104.06951/) (2021)
- [BPE Gets Picky: Efficient Vocabulary Refinement During Tokenizer Training](https://mlsanity.com/paper/2409.04599/) (2024)
- [Low-Rank Softmax Can Have Unargmaxable Classes in Theory but Rarely in Practice](https://mlsanity.com/paper/2203.06462/) (2022)
- [Improving Tree-Structured Decoder Training for Code Generation via Mutual Learning](https://mlsanity.com/paper/2105.14796/) (2021)
- [An Analysis of BPE Vocabulary Trimming in Neural Machine Translation](https://mlsanity.com/paper/2404.00397/) (2024)
- [Crowdsourced Phrase-Based Tokenization for Low-Resourced Neural Machine Translation: The Case of Fon Language](https://mlsanity.com/paper/2103.08052/) (2021)
- [MinGram: A Minimalist Unigram Tokenizer with High Compression and Competitive Morphological Alignment](https://mlsanity.com/paper/2606.27019/) (2026)
- [A Syntax-Guided Grammatical Error Correction Model with Dependency Tree Correction](https://mlsanity.com/paper/2111.03294/) (2021)
- [EdinSaar@WMT21: North-Germanic Low-Resource Multilingual NMT](https://mlsanity.com/paper/2109.14368/) (2021)
- [Beyond Vanilla Fine-Tuning: Leveraging Multistage, Multilingual, and Domain-Specific Methods for Low-Resource Machine Translation](https://mlsanity.com/paper/2503.22582/) (2025)
- [Horizontal and Vertical Attention in Transformers](https://mlsanity.com/paper/2207.04399/) (2022)
- [Spiral Language Modeling](https://mlsanity.com/paper/2112.10543/) (2021)
- [Understanding the effects of word-level linguistic annotations in under-resourced neural machine translation](https://mlsanity.com/paper/2401.16078/) (2024)
- [SEE: Sememe Entanglement Encoding for Transformer-bases Models Compression](https://mlsanity.com/paper/2412.12204/) (2024)
- [Time Is Effort: Estimating Human Post-Editing Time for Grammar Error Correction Tool Evaluation](https://mlsanity.com/paper/2510.04394/) (2025)
- [Data-Efficient Domain Adaptation for LLM-based MT using Contrastive Preference Optimization](https://mlsanity.com/paper/2510.27556/) (2025)

## Abstract (arXiv)

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.