Maastricht University’s Large-Scale Multilingual Machine Translation System for WMT 2021

Danni Liu; Jan Niehues

Maastricht University’s Large-Scale Multilingual Machine Translation System for WMT 2021

Danni Liu, Jan Niehues

Research output: Chapter in Book/Report/Conference proceeding › Conference article in proceeding › Academic › peer-review

Abstract

We present our development of the multilingual machine translation system for the large-scale multilingual machine translation task at WMT 2021. Starting form the provided baseline system, we investigated several techniques to improve the translation quality on the target subset of languages. We were able to significantly improve the translation quality by adapting the system towards the target subset of languages and by generating synthetic data using the initial model. Techniques successfully applied in zero-shot multilingual machine translation (e.g. similarity regularizer) only had a minor effect on the final translation performance.

Original language	English
Title of host publication	Proceedings of the Sixth Conference on Machine Translation (WMT)
Publisher	Association for Computational Linguistics (ACL)
Pages	425-430
Number of pages	6
ISBN (Electronic)	9781954085947
Publication status	Published - Nov 2021
Event	2021 Sixth Conference on Machine Translation (WMT21) - Punta Cana (Dominican Republic) and Online, Punta Cana, Dominican Republic Duration: 10 Nov 2021 → 11 Nov 2021 https://www.statmt.org/wmt21/

Conference

Conference	2021 Sixth Conference on Machine Translation (WMT21)
Abbreviated title	WMT21
Country/Territory	Dominican Republic
City	Punta Cana
Period	10/11/21 → 11/11/21
Internet address	https://www.statmt.org/wmt21/

Access to Document

https://aclanthology.org/2021.wmt-1.51.pdf

Cite this

@inproceedings{ebe9ddecf2244a2299b31c827591ddf7,

title = "Maastricht University{\textquoteright}s Large-Scale Multilingual Machine Translation System for WMT 2021",

abstract = "We present our development of the multilingual machine translation system for the large-scale multilingual machine translation task at WMT 2021. Starting form the provided baseline system, we investigated several techniques to improve the translation quality on the target subset of languages. We were able to significantly improve the translation quality by adapting the system towards the target subset of languages and by generating synthetic data using the initial model. Techniques successfully applied in zero-shot multilingual machine translation (e.g. similarity regularizer) only had a minor effect on the final translation performance.",

author = "Danni Liu and Jan Niehues",

year = "2021",

month = nov,

language = "English",

pages = "425--430",

booktitle = "Proceedings of the Sixth Conference on Machine Translation (WMT)",

publisher = "Association for Computational Linguistics (ACL)",

address = "United States",

note = "2021 Sixth Conference on Machine Translation (WMT21), WMT21 ; Conference date: 10-11-2021 Through 11-11-2021",

url = "https://www.statmt.org/wmt21/",

}

Liu, D & Niehues, J 2021, Maastricht University’s Large-Scale Multilingual Machine Translation System for WMT 2021. in Proceedings of the Sixth Conference on Machine Translation (WMT). Association for Computational Linguistics (ACL), pp. 425-430, 2021 Sixth Conference on Machine Translation (WMT21), Punta Cana, Dominican Republic, 10/11/21. <https://aclanthology.org/2021.wmt-1.51.pdf>

Maastricht University’s Large-Scale Multilingual Machine Translation System for WMT 2021. / Liu, Danni; Niehues, Jan.
Proceedings of the Sixth Conference on Machine Translation (WMT). Association for Computational Linguistics (ACL), 2021. p. 425-430.

Research output: Chapter in Book/Report/Conference proceeding › Conference article in proceeding › Academic › peer-review

TY - GEN

T1 - Maastricht University’s Large-Scale Multilingual Machine Translation System for WMT 2021

AU - Liu, Danni

AU - Niehues, Jan

PY - 2021/11

Y1 - 2021/11

N2 - We present our development of the multilingual machine translation system for the large-scale multilingual machine translation task at WMT 2021. Starting form the provided baseline system, we investigated several techniques to improve the translation quality on the target subset of languages. We were able to significantly improve the translation quality by adapting the system towards the target subset of languages and by generating synthetic data using the initial model. Techniques successfully applied in zero-shot multilingual machine translation (e.g. similarity regularizer) only had a minor effect on the final translation performance.

AB - We present our development of the multilingual machine translation system for the large-scale multilingual machine translation task at WMT 2021. Starting form the provided baseline system, we investigated several techniques to improve the translation quality on the target subset of languages. We were able to significantly improve the translation quality by adapting the system towards the target subset of languages and by generating synthetic data using the initial model. Techniques successfully applied in zero-shot multilingual machine translation (e.g. similarity regularizer) only had a minor effect on the final translation performance.

M3 - Conference article in proceeding

SP - 425

EP - 430

BT - Proceedings of the Sixth Conference on Machine Translation (WMT)

PB - Association for Computational Linguistics (ACL)

T2 - 2021 Sixth Conference on Machine Translation (WMT21)

Y2 - 10 November 2021 through 11 November 2021

ER -

Maastricht University’s Large-Scale Multilingual Machine Translation System for WMT 2021

Abstract

Conference

Access to Document

Fingerprint

Cite this