Neural Translation for the European Union Short Name: NTEU Name: Neural Translation for the European Union Coordinator: Manuel Herranz, Pangeanic Consortium: Pangeanic, Tilde, KantanMT and SEDIA Project Runtime: September 2019 – August 2021 Funded by: European Commission https://nteu.eu The NTEU project aims to build a neural engine farm with all the 24 European official language combinations for eTranslation, without the necessity to use a high-resourced language as a pivot (around 550 translation engines in total). NTEU will provide a capacity service to eTranslation by building a near-human-professional-quality neural engine farm which includes all EU language combinations. Lower-resourced languages will be a challenge, and more effort will be required to obtain well-performing engines for them. We will experiment with techniques to supplement the original data, such as generating synthetic data by doing back-translation and transfer learning. In addition, the NTEU consortium will gather and clean data from all language combinations so that the engines can be retrained with other technologies in the future. The results of the MT will be manually evaluated following industry and WMT practices in an open-source platform created by the consortium.