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: University of Helsinki, Department of Digital Humanities
University of Helsinki, Language Technology
University of Helsinki, Language Technology
University of Helsinki, Department of Digital Humanities
University of Helsinki, Language Technology
University of Helsinki, Language Technology
University of Helsinki, Department of Languages
University of Helsinki, Department of Digital Humanities
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) Proceedings of the Conference: Volume 2
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
Rights:


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