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

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

Department of Signal Processing and Acoustics

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Scientific › peer-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 language	English
Title of host publication	Proceedings of the Fifth Conference on Machine Translation
Pages	1129-1138
Number of pages	10
ISBN (Electronic)	978-1-948087-81-0
Publication status	Published - 19 Nov 2020
MoE publication type	A4 Article in a conference publication
Event	Conference on Machine Translation - Virtual, Online Duration: 19 Nov 2020 → 20 Nov 2020

Conference

Conference	Conference on Machine Translation
Abbreviated title	WMT
City	Virtual, Online
Period	19/11/2020 → 20/11/2020

Keywords

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

Access to Document

2020.wmt-1.134Final published version, 352 KBLicence: CC BY

https://www.aclweb.org/anthology/2020.wmt-1.134/Licence: CC BY

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

@inproceedings{5a1c064bf3224d6f8d8a01d1c0cb228c,

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

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.",

keywords = "neural machine translation, Low-resource languages, Subword segmentation, Inuktitut, Upper Sorbian",

author = "Yves Scherrer and Stig-Arne Gr{\"o}nroos and Sami Virpioja",

year = "2020",

month = nov,

day = "19",

language = "English",

pages = "1129--1138",

booktitle = "Proceedings of the Fifth Conference on Machine Translation",

note = "Conference on Machine Translation, WMT ; Conference date: 19-11-2020 Through 20-11-2020",

}

The University of Helsinki and Aalto University submissions to the WMT 2020 news and low-resource translation tasks. / Scherrer, Yves; Grönroos, Stig-Arne; Virpioja, Sami.

Proceedings of the Fifth Conference on Machine Translation. 2020. p. 1129-1138.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Scientific › peer-review

TY - GEN

T1 - The University of Helsinki and Aalto University submissions to the WMT 2020 news and low-resource translation tasks

AU - Scherrer, Yves

AU - Grönroos, Stig-Arne

AU - Virpioja, Sami

PY - 2020/11/19

Y1 - 2020/11/19

N2 - 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.

AB - 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.

KW - neural machine translation

KW - Low-resource languages

KW - Subword segmentation

KW - Inuktitut

KW - Upper Sorbian

M3 - Conference contribution

SP - 1129

EP - 1138

BT - Proceedings of the Fifth Conference on Machine Translation

T2 - Conference on Machine Translation

Y2 - 19 November 2020 through 20 November 2020

ER -