PROMT Translation Systems for WMT 2016 Translation Tasks

By Alexander P. Molchanov, Fedor Bykov. 2016

This paper provides an overview of the PROMT submissions for the WMT16 Shared Translation Tasks. We participated in seven language pairs with three different system configurations (rule-based, statistical and hybrid). We describe the architecture of the three configurations. We show that fast and accurate customization of the rule-based system can increase the BLEU scores significantly.

Subfields: Machine Translation

Citations in the corpus

• Findings of the 2016 Conference on Machine Translation (2016, neutral): “PROMT PROMT Automated Translation Solutions (Molchanov and Bykov, 2016)”