Machine Translation into Low-resource Language Varieties

Sachin Kumar; Antonios Anastasopoulos; Shuly Wintner; Yulia Tsvetkov

doi:10.18653/v1/2021.acl-short.16

Machine Translation into Low-resource Language Varieties

Sachin Kumar, Antonios Anastasopoulos, Shuly Wintner, Yulia Tsvetkov

Department of Computer Science

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

Abstract

State-of-the-art machine translation (MT) systems are typically trained to generate "standard"target language; however, many languages have multiple varieties (regional varieties, dialects, sociolects, non-native varieties) that are different from the standard language. Such varieties are often low-resource, and hence do not benefit from contemporary NLP solutions, MT included. We propose a general framework to rapidly adapt MT systems to generate language varieties that are close to, but different from, the standard target language, using no parallel (source- variety) data. This also includes adaptation of MT systems to low-resource typologicallyrelated target languages.1 We experiment with adapting an English-Russian MT system to generate Ukrainian and Belarusian, an English-Norwegian Bokmål system to generate Nynorsk, and an English-Arabic system to generate four Arabic dialects, obtaining significant improvements over competitive baselines.

Original language	English
Title of host publication	ACL-IJCNLP 2021 - 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, Proceedings of the Conference
Publisher	Association for Computational Linguistics (ACL)
Pages	110-121
Number of pages	12
ISBN (Electronic)	9781954085534
DOIs	https://doi.org/10.18653/v1/2021.acl-short.16
State	Published - 2021
Event	Joint Conference of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, ACL-IJCNLP 2021 - Virtual, Online Duration: 1 Aug 2021 → 6 Aug 2021

Publication series

Name	ACL-IJCNLP 2021 - 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, Proceedings of the Conference
Volume	2

Conference

Conference	Joint Conference of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, ACL-IJCNLP 2021
City	Virtual, Online
Period	1/08/21 → 6/08/21

Bibliographical note

Publisher Copyright:
© 2021 Association for Computational Linguistics.

ASJC Scopus subject areas

Software
Computational Theory and Mathematics
Linguistics and Language
Language and Linguistics

Access to Document

10.18653/v1/2021.acl-short.16

Cite this

Kumar, S., Anastasopoulos, A., Wintner, S., & Tsvetkov, Y. (2021). Machine Translation into Low-resource Language Varieties. In ACL-IJCNLP 2021 - 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, Proceedings of the Conference (pp. 110-121). (ACL-IJCNLP 2021 - 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, Proceedings of the Conference; Vol. 2). Association for Computational Linguistics (ACL). https://doi.org/10.18653/v1/2021.acl-short.16

Kumar, Sachin ; Anastasopoulos, Antonios ; Wintner, Shuly et al. / Machine Translation into Low-resource Language Varieties. ACL-IJCNLP 2021 - 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, Proceedings of the Conference. Association for Computational Linguistics (ACL), 2021. pp. 110-121 (ACL-IJCNLP 2021 - 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, Proceedings of the Conference).

@inproceedings{e7d6eb8ecad0406eb7bb68d861ce8e3e,

title = "Machine Translation into Low-resource Language Varieties",

abstract = "State-of-the-art machine translation (MT) systems are typically trained to generate {"}standard{"}target language; however, many languages have multiple varieties (regional varieties, dialects, sociolects, non-native varieties) that are different from the standard language. Such varieties are often low-resource, and hence do not benefit from contemporary NLP solutions, MT included. We propose a general framework to rapidly adapt MT systems to generate language varieties that are close to, but different from, the standard target language, using no parallel (source- variety) data. This also includes adaptation of MT systems to low-resource typologicallyrelated target languages.1 We experiment with adapting an English-Russian MT system to generate Ukrainian and Belarusian, an English-Norwegian Bokm{\aa}l system to generate Nynorsk, and an English-Arabic system to generate four Arabic dialects, obtaining significant improvements over competitive baselines.",

author = "Sachin Kumar and Antonios Anastasopoulos and Shuly Wintner and Yulia Tsvetkov",

note = "Publisher Copyright: {\textcopyright} 2021 Association for Computational Linguistics.; Joint Conference of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, ACL-IJCNLP 2021 ; Conference date: 01-08-2021 Through 06-08-2021",

year = "2021",

doi = "10.18653/v1/2021.acl-short.16",

language = "English",

series = "ACL-IJCNLP 2021 - 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, Proceedings of the Conference",

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

pages = "110--121",

booktitle = "ACL-IJCNLP 2021 - 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, Proceedings of the Conference",

address = "United States",

}

Kumar, S, Anastasopoulos, A, Wintner, S & Tsvetkov, Y 2021, Machine Translation into Low-resource Language Varieties. in ACL-IJCNLP 2021 - 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, Proceedings of the Conference. ACL-IJCNLP 2021 - 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, Proceedings of the Conference, vol. 2, Association for Computational Linguistics (ACL), pp. 110-121, Joint Conference of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, ACL-IJCNLP 2021, Virtual, Online, 1/08/21. https://doi.org/10.18653/v1/2021.acl-short.16

Machine Translation into Low-resource Language Varieties. / Kumar, Sachin; Anastasopoulos, Antonios; Wintner, Shuly et al.
ACL-IJCNLP 2021 - 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, Proceedings of the Conference. Association for Computational Linguistics (ACL), 2021. p. 110-121 (ACL-IJCNLP 2021 - 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, Proceedings of the Conference; Vol. 2).

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

TY - GEN

T1 - Machine Translation into Low-resource Language Varieties

AU - Kumar, Sachin

AU - Anastasopoulos, Antonios

AU - Wintner, Shuly

AU - Tsvetkov, Yulia

PY - 2021

Y1 - 2021

N2 - State-of-the-art machine translation (MT) systems are typically trained to generate "standard"target language; however, many languages have multiple varieties (regional varieties, dialects, sociolects, non-native varieties) that are different from the standard language. Such varieties are often low-resource, and hence do not benefit from contemporary NLP solutions, MT included. We propose a general framework to rapidly adapt MT systems to generate language varieties that are close to, but different from, the standard target language, using no parallel (source- variety) data. This also includes adaptation of MT systems to low-resource typologicallyrelated target languages.1 We experiment with adapting an English-Russian MT system to generate Ukrainian and Belarusian, an English-Norwegian Bokmål system to generate Nynorsk, and an English-Arabic system to generate four Arabic dialects, obtaining significant improvements over competitive baselines.

AB - State-of-the-art machine translation (MT) systems are typically trained to generate "standard"target language; however, many languages have multiple varieties (regional varieties, dialects, sociolects, non-native varieties) that are different from the standard language. Such varieties are often low-resource, and hence do not benefit from contemporary NLP solutions, MT included. We propose a general framework to rapidly adapt MT systems to generate language varieties that are close to, but different from, the standard target language, using no parallel (source- variety) data. This also includes adaptation of MT systems to low-resource typologicallyrelated target languages.1 We experiment with adapting an English-Russian MT system to generate Ukrainian and Belarusian, an English-Norwegian Bokmål system to generate Nynorsk, and an English-Arabic system to generate four Arabic dialects, obtaining significant improvements over competitive baselines.

UR - https://www.scopus.com/pages/publications/85115711022

U2 - 10.18653/v1/2021.acl-short.16

DO - 10.18653/v1/2021.acl-short.16

M3 - Conference contribution

AN - SCOPUS:85115711022

T3 - ACL-IJCNLP 2021 - 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, Proceedings of the Conference

SP - 110

EP - 121

BT - ACL-IJCNLP 2021 - 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, Proceedings of the Conference

PB - Association for Computational Linguistics (ACL)

T2 - Joint Conference of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, ACL-IJCNLP 2021

Y2 - 1 August 2021 through 6 August 2021

ER -

Kumar S, Anastasopoulos A, Wintner S, Tsvetkov Y. Machine Translation into Low-resource Language Varieties. In ACL-IJCNLP 2021 - 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, Proceedings of the Conference. Association for Computational Linguistics (ACL). 2021. p. 110-121. (ACL-IJCNLP 2021 - 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, Proceedings of the Conference). doi: 10.18653/v1/2021.acl-short.16

Machine Translation into Low-resource Language Varieties

Abstract

Publication series

Conference

Bibliographical note

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this