English

The Helsinki Neural Machine Translation System

Computation and Language 2017-08-22 v1

Abstract

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.

Keywords

Cite

@article{arxiv.1708.05942,
  title  = {The Helsinki Neural Machine Translation System},
  author = {Robert Östling and Yves Scherrer and Jörg Tiedemann and Gongbo Tang and Tommi Nieminen},
  journal= {arXiv preprint arXiv:1708.05942},
  year   = {2017}
}

Comments

Proceedings of the Second Conference on Machine Translation (WMT 2017) at EMNLP 2017, Copenhagen/Danmark

R2 v1 2026-06-22T21:18:48.553Z