Abstract
In this paper, we describe our submission to the English-German APE shared task at WMT 2019. We utilize and adapt an NMT architecture originally developed for exploiting context information to APE, implement this in our own transformer model and explore joint training of the APE task with a de-noising encoder.
Cite
CITATION STYLE
APA
Xu, H., Liu, Q., & van Genabith, J. (2019). UdS submission for the WMT 19 automatic post-editing task. In WMT 2019 - 4th Conference on Machine Translation, Proceedings of the Conference (Vol. 3, pp. 145–150). Association for Computational Linguistics (ACL). https://doi.org/10.18653/v1/w19-5417
Register to see more suggestions
Mendeley helps you to discover research relevant for your work.
Already have an account? Sign in
Sign up for free