The Helsinki Neural Machine Translation System
This work addresses machine translation for news domains, demonstrating the advantage of neural methods over existing approaches, though it is incremental as it applies established NMT techniques to specific language pairs.
The Helsinki Neural Machine Translation system (HNMT) tackled the news translation task at WMT 2017, achieving first place in both human and automatic evaluations for English-Finnish and outperforming a strong statistical machine translation baseline.
We introduce the Helsinki Neural Machine Translation system (HNMT) and how it is applied in the news translation task at WMT 2017, where it ranked first in both the human and automatic evaluations for English--Finnish. We discuss the success of English--Finnish translations and the overall advantage of NMT over a strong SMT baseline. We also discuss our submissions for English--Latvian, English--Chinese and Chinese--English.