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

Language Technology

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

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
Editors	Loïc Barrault [et al.]
Number of pages	10
Place of Publication	Stroudsburg
Publisher	The Association for Computational Linguistics
Publication date	1 Nov 2020
Pages	1129-1138
ISBN (Print)	978-1-948087-81-0
Publication status	Published - 1 Nov 2020
MoE publication type	A4 Article in conference proceedings
Event	Conference on Machine Translation - [Online conference] Duration: 19 Nov 2020 → 20 Nov 2020 Conference number: 5 http://www.statmt.org/wmt20/

Fields of Science

6121 Languages

Access to Document

2020.wmt-1.134Final published version, 305 KBLicence: CC BY

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

FoTran: Found in Translation - Natural Language Understanding with Cross-Lingual Grounding
Tiedemann, J. (Project manager), Attieh, J. (Participant), Aulamo, M. (Participant), Celikkanat, H. (Participant), De Gibert Bonet, O. (Participant), Grönroos, S.-A. (Participant), Mickus, T. (Participant), Raganato, A. (Participant), Scherrer, Y. (Participant), Silfverberg, M. (Participant), Sjöblom, E. I. (Participant), Talman, A. (Participant), Vazquez , R. (Participant), Virpioja, S. P. (Participant), Yli-Jyrä, A. (Participant), Zosa, E. (Participant), Celikkanat, H. (Participant), Raganato, A. (Participant), Silfverberg, M. (Participant), Sulubacak, U. (Participant) & Vazquez , R. (Participant)
01/09/2018 → 31/03/2024
Project: EU Horizon 2020: European Research Council: Consolidator Grant (H2020-ERC-COG)

Cite this

Scherrer, Y., Grönroos, S.-A., & Virpioja, S. (2020). The University of Helsinki and Aalto University submissions to the WMT 2020 news and low-resource translation tasks. In L. Barrault [et al.] (Ed.), Proceedings of the Fifth Conference on Machine Translation (pp. 1129-1138). The Association for Computational Linguistics. https://www.aclweb.org/anthology/2020.wmt-1.134

@inproceedings{6a12e131c2334cdcb6d716204f6a96bf,

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 = "6121 Languages",

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

year = "2020",

month = nov,

day = "1",

language = "English",

isbn = "978-1-948087-81-0",

pages = "1129--1138",

editor = "{ Barrault [et al.]}, Lo{\"i}c",

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

publisher = "The Association for Computational Linguistics",

address = "United States",

note = "Conference on Machine Translation, WMT20 ; Conference date: 19-11-2020 Through 20-11-2020",

url = "http://www.statmt.org/wmt20/",

}

Scherrer, Y , Grönroos, S-A & Virpioja, S 2020, The University of Helsinki and Aalto University submissions to the WMT 2020 news and low-resource translation tasks. in L Barrault [et al.] (ed.), Proceedings of the Fifth Conference on Machine Translation. The Association for Computational Linguistics, Stroudsburg, pp. 1129-1138, Conference on Machine Translation, 19/11/2020. <https://www.aclweb.org/anthology/2020.wmt-1.134>

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. ed. / Loïc Barrault [et al.]. Stroudsburg: The Association for Computational Linguistics, 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

N1 - Conference code: 5

PY - 2020/11/1

Y1 - 2020/11/1

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 - 6121 Languages

M3 - Conference contribution

SN - 978-1-948087-81-0

SP - 1129

EP - 1138

BT - Proceedings of the Fifth Conference on Machine Translation

A2 - Barrault [et al.], Loïc

PB - The Association for Computational Linguistics

CY - Stroudsburg

T2 - Conference on Machine Translation

Y2 - 19 November 2020 through 20 November 2020

ER -

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

Abstract

Fields of Science

Access to Document

Projects

FoTran: Found in Translation - Natural Language Understanding with Cross-Lingual Grounding

Cite this