# The University of Edinburgh's Submissions to the WMT19 News Translation Task

arXiv: https://arxiv.org/abs/1907.05854 · HTML: https://mlsanity.com/paper/1907.05854/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 Jul 2019.

## Built on by (most cited first, 11 of 11)

- [Survey of Low-Resource Machine Translation](https://mlsanity.com/paper/2109.00486/) (2021)
- [To Diverge or Not to Diverge: A Morphosyntactic Perspective on Machine Translation vs Human Translation](https://mlsanity.com/paper/2401.01419/) (2024)
- [Few-shot learning through contextual data augmentation](https://mlsanity.com/paper/2103.16911/) (2021)
- [Online Learning Meets Machine Translation Evaluation: Finding the Best Systems with the Least Human Effort](https://mlsanity.com/paper/2105.13385/) (2021)
- [Improving Multilingual Neural Machine Translation System for Indic Languages](https://mlsanity.com/paper/2209.13279/) (2022)
- [Onception: Active Learning with Expert Advice for Real World Machine Translation](https://mlsanity.com/paper/2203.04507/) (2022)
- [HintedBT: Augmenting Back-Translation with Quality and Transliteration Hints](https://mlsanity.com/paper/2109.04443/) (2021)
- [Automatic Discrimination of Human and Neural Machine Translation in Multilingual Scenarios](https://mlsanity.com/paper/2305.19757/) (2023)
- [BrailleLLM: Braille Instruction Tuning with Large Language Models for Braille Domain Tasks](https://mlsanity.com/paper/2510.18288/) (2025)
- [Character-level Chinese Backpack Language Models](https://mlsanity.com/paper/2310.12751/) (2023)
- [FFN: a Fine-grained Chinese-English Financial Domain Parallel Corpus](https://mlsanity.com/paper/2406.18856/) (2024)

## Abstract (arXiv)

The University of Edinburgh participated in the WMT19 Shared Task on News Translation in six language directions: English-to-Gujarati, Gujarati-to-English, English-to-Chinese, Chinese-to-English, German-to-English, and English-to-Czech. For all translation directions, we created or used back-translations of monolingual data in the target language as additional synthetic training data. For English-Gujarati, we also explored semi-supervised MT with cross-lingual language model pre-training, and translation pivoting through Hindi. For translation to and from Chinese, we investigated character-based tokenisation vs. sub-word segmentation of Chinese text. For German-to-English, we studied the impact of vast amounts of back-translated training data on translation quality, gaining a few additional insights over Edunov et al. (2018). For English-to-Czech, we compared different pre-processing and tokenisation regimes.