Publication at Faculty of Mathematics and Physics |
2016
Abstract
This paper describes the phrase-based systems jointly submitted by CUNI and LMU to English-Czech and English-Romanian News translation tasks of WMT16. In contrast to previous years, we strictly limited our training data to the constraint datasets, to allow for a reliable comparison with other research systems.
We experiment with using several additional models in our system, including a feature-rich discriminative model of phrasal translation.