Combining Local and Document-Level Context: The LMU Munich Neural Machine Translation System at WMT19

Dario Stojanovski, Alexander Fraser
2019 Proceedings of the Fourth Conference on Machine Translation (Volume 2: Shared Task Papers, Day 1)  
We describe LMU Munich's machine translation system for English→German translation which was used to participate in the WMT19 shared task on supervised news translation. We specifically participated in the documentlevel MT track. The system used as a primary submission is a context-aware Transformer capable of both rich modeling of limited contextual information and integration of large-scale document-level context with a less rich representation. We train this model by fine-tuning a big
more » ... rmer baseline. Our experimental results show that document-level context provides for large improvements in translation quality, and adding a rich representation of the previous sentence provides a small additional gain.
doi:10.18653/v1/w19-5345 dblp:conf/wmt/StojanovskiF19 fatcat:ssuliypx4nf3pemceivc6ggr3q