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

Rachel Bawden, Nikolay Bogoychev, Ulrich Germann, Roman Grundkiewicz, Faheem Kirefu, Antonio Miceli Barone, Alexandra Birch-Mayne

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


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.
Original languageEnglish
Title of host publicationProceedings of the Fourth Conference on Machine Translation
Subtitle of host publicationVolume 2: Shared Task Papers
Place of PublicationFlorence, Italy
PublisherAssociation for Computational Linguistics
Number of pages13
Publication statusPublished - Aug 2019
EventACL 2019 Fourth Conference on Machine Translation - Florence, Italy
Duration: 1 Aug 20192 Aug 2019


ConferenceACL 2019 Fourth Conference on Machine Translation
Abbreviated titleWMT19
Internet address


  • Machine translation
  • Shared task


Dive into the research topics of 'The University of Edinburgh’s Submissions to the WMT19 News Translation Task'. Together they form a unique fingerprint.

Cite this