CUNI English-Czech and English-Polish Systems in WMT20: Robust Document-Level Training

Abstract

We describe our two NMT systems submitted to the WMT 2020 shared task in English<->Czech and English<->Polish news translation. One system is sentence level, translating each sentence independently. The second system is document level, translating multiple sentences, trained on multi-sentence sequences up to 3000 characters long.

Tasks

Reproductions