The Helsinki Neural Machine Translation System
Robert \"Ostling, Yves Scherrer, J\"org Tiedemann, Gongbo, Tang, Tommi Nieminen
TL;DR
The paper presents the Helsinki Neural Machine Translation system (HNMT), which achieved top rankings in English-Finnish news translation at WMT 2017, demonstrating NMT's advantages over SMT and extending to other language pairs.
Contribution
Introduction of the HNMT system and its successful application in news translation tasks, highlighting improvements over traditional SMT methods.
Findings
Ranked first in English-Finnish translation at WMT 2017
Demonstrated NMT's advantage over SMT baseline
Extended application to multiple language pairs
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.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsNatural Language Processing Techniques · Topic Modeling · Multimodal Machine Learning Applications