The University of Helsinki submissions to the WMT19 news translation task

Show full item record



Permalink

http://hdl.handle.net/10138/304494

Citation

Talman , A , Sulubacak , U , Vazquez , R , Scherrer , Y , Virpioja , S , Raganato , A , Hurskainen , A & Tiedemann , J 2019 , The University of Helsinki submissions to the WMT19 news translation task . in Fourth Conference of Conference on Machine Translation (WMT 2019) : Proceedings of the Conference: Volume 2 . The Association for Computational Linguistics , Stroudsburg , pp. 412-423 , Conference on Machine Translation , Florence , Italy , 01/08/2019 . < http://www.statmt.org/wmt19/papers.html >

Title: The University of Helsinki submissions to the WMT19 news translation task
Author: Talman, Aarne; Sulubacak, Umut; Vazquez , Raul; Scherrer, Yves; Virpioja, Sami; Raganato, Alessandro; Hurskainen, Arvi; Tiedemann, Jörg
Contributor organization: Department of Digital Humanities
Language Technology
Department of Languages
Publisher: The Association for Computational Linguistics
Date: 2019-08-01
Language: eng
Number of pages: 12
Belongs to series: Fourth Conference of Conference on Machine Translation (WMT 2019)
ISBN: 978-1-950737-27-7
URI: http://hdl.handle.net/10138/304494
Abstract: In this paper, we present the University of Helsinki submissions to the WMT 2019 shared task on news translation in three language pairs: English-German, English-Finnish and Finnish-English. This year, we focused first on cleaning and filtering the training data using multiple data-filtering approaches, resulting in much smaller and cleaner training sets. For English-German, we trained both sentence-level transformer models and compared different document-level translation approaches. For Finnish-English and English-Finnish we focused on different segmentation approaches, and we also included a rule-based system for English-Finnish.
Subject: 6121 Languages
113 Computer and information sciences
Peer reviewed: Yes
Rights: unspecified
Usage restriction: openAccess
Self-archived version: publishedVersion
Funder: European Commission
SUOMEN AKATEMIA
Grant number: 771113


Files in this item

Total number of downloads: Loading...

Files Size Format View
WMT0047.pdf 361.4Kb PDF View/Open

This item appears in the following Collection(s)

Show full item record