The University of Helsinki and Aalto University submissions to the WMT 2020 news and low-resource translation tasks

Yves Scherrer*, Stig-Arne Grönroos, Sami Virpioja

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review

4 Downloads (Pure)

Abstract

This paper describes the joint participation of University of Helsinki and Aalto University to two shared tasks of WMT 2020: the news translation between Inuktitut and English and the low-resource translation between German and Upper Sorbian. For both tasks, our efforts concentrate on efficient use of monolingual and related bilingual corpora with scheduled multi-task learning as well as an optimized subword segmentation with sampling. Our submission obtained the highest score for Upper Sorbian -> German and was ranked second for German -> Upper Sorbian according to BLEU scores. For English–Inuktitut, we reached ranks 8 and 10 out of 11 according to BLEU scores.
Original languageEnglish
Title of host publicationProceedings of the Fifth Conference on Machine Translation
Pages1129-1138
Number of pages10
ISBN (Electronic)978-1-948087-81-0
Publication statusPublished - 19 Nov 2020
MoE publication typeA4 Article in a conference publication
EventConference on Machine Translation - Virtual, Online
Duration: 19 Nov 202020 Nov 2020

Conference

ConferenceConference on Machine Translation
Abbreviated titleWMT
CityVirtual, Online
Period19/11/202020/11/2020

Keywords

  • neural machine translation
  • Low-resource languages
  • Subword segmentation
  • Inuktitut
  • Upper Sorbian

Fingerprint Dive into the research topics of 'The University of Helsinki and Aalto University submissions to the WMT 2020 news and low-resource translation tasks'. Together they form a unique fingerprint.

Cite this