The University of Helsinki Submissions to the WMT19 Similar Language Translation Task

Show full item record



Permalink

http://hdl.handle.net/10138/305093

Citation

Scherrer , Y , Vázquez , R & Virpioja , S 2019 , The University of Helsinki Submissions to the WMT19 Similar Language Translation Task . in O Bojar , R Chatterjee , C Federmann & E A (eds) , Fourth Conference on Machine Translation: Proceedings of the Conference : Volume 3 (Shared Task Papers, Day 2) . The Association for Computational Linguistics , Stroudsburg , pp. 236-244 , Conference on Machine Translation , Florence , Italy , 01/08/2019 . < https://www.aclweb.org/anthology/W19-5432 >

Title: The University of Helsinki Submissions to the WMT19 Similar Language Translation Task
Author: Scherrer, Yves; Vázquez, Raúl; Virpioja, Sami
Editor: Bojar, Ondřej; Chatterjee, Rajen; Federmann, Christian; et al.
Contributor: University of Helsinki, Department of Digital Humanities
University of Helsinki, Department of Digital Humanities
University of Helsinki, Language Technology
Publisher: The Association for Computational Linguistics
Date: 2019-08-01
Language: eng
Number of pages: 9
Belongs to series: Fourth Conference on Machine Translation: Proceedings of the Conference Volume 3 (Shared Task Papers, Day 2)
ISBN: 978-1-950737-27-7
URI: http://hdl.handle.net/10138/305093
Abstract: This paper describes the University of Helsinki Language Technology group's participation in the WMT 2019 similar language translation task. We trained neural machine translation models for the language pairs Czech textless-textgreater Polish and Spanish textless-textgreater Portuguese. Our experiments focused on different subword segmentation methods, and in particular on the comparison of a cognate-aware segmentation method, Cognate Morfessor, with character segmentation and unsupervised segmentation methods for which the data from different languages were simply concatenated. We did not observe major benefits from cognate-aware segmentation methods, but further research may be needed to explore larger parts of the parameter space. Character-level models proved to be competitive for translation between Spanish and Portuguese, but they are slower in training and decoding.
Subject: 113 Computer and information sciences
6121 Languages
Rights:


Files in this item

Total number of downloads: Loading...

Files Size Format View
W19_5432.pdf 322.1Kb PDF View/Open

This item appears in the following Collection(s)

Show full item record