Log-linear Combinations of Monolingual and Bilingual Neural Machine Translation Models for Automatic Post-Editing
Proceedings of the First Conference on Machine Translation: Volume 2,#N# Shared Task Papers, pp. 751-758, 2016.
This paper describes the submission of the AMU (Adam Mickiewicz University) team to the Automatic Post-Editing (APE) task of WMT 2016. We explore the application of neural translation models to the APE problem and achieve good results by treating different models as components in a log-linear model, allowing for multiple inputs (the MT-ou...More
PPT (Upload PPT)