@inproceedings{kumar-etal-2021-machine,
title = "Machine Translation into Low-resource Language Varieties",
author = "Kumar, Sachin and
Anastasopoulos, Antonios and
Wintner, Shuly and
Tsvetkov, Yulia",
editor = "Zong, Chengqing and
Xia, Fei and
Li, Wenjie and
Navigli, Roberto",
booktitle = "Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 2: Short Papers)",
month = aug,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.acl-short.16",
doi = "10.18653/v1/2021.acl-short.16",
pages = "110--121",
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 typologically-related target languages. 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.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kumar-etal-2021-machine">
<titleInfo>
<title>Machine Translation into Low-resource Language Varieties</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sachin</namePart>
<namePart type="family">Kumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antonios</namePart>
<namePart type="family">Anastasopoulos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shuly</namePart>
<namePart type="family">Wintner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yulia</namePart>
<namePart type="family">Tsvetkov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 2: Short Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Chengqing</namePart>
<namePart type="family">Zong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fei</namePart>
<namePart type="family">Xia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wenjie</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Roberto</namePart>
<namePart type="family">Navigli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<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 typologically-related target languages. 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.</abstract>
<identifier type="citekey">kumar-etal-2021-machine</identifier>
<identifier type="doi">10.18653/v1/2021.acl-short.16</identifier>
<location>
<url>https://aclanthology.org/2021.acl-short.16</url>
</location>
<part>
<date>2021-08</date>
<extent unit="page">
<start>110</start>
<end>121</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Machine Translation into Low-resource Language Varieties
%A Kumar, Sachin
%A Anastasopoulos, Antonios
%A Wintner, Shuly
%A Tsvetkov, Yulia
%Y Zong, Chengqing
%Y Xia, Fei
%Y Li, Wenjie
%Y Navigli, Roberto
%S Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 2: Short Papers)
%D 2021
%8 August
%I Association for Computational Linguistics
%C Online
%F kumar-etal-2021-machine
%X 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 typologically-related target languages. 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.
%R 10.18653/v1/2021.acl-short.16
%U https://aclanthology.org/2021.acl-short.16
%U https://doi.org/10.18653/v1/2021.acl-short.16
%P 110-121
Markdown (Informal)
[Machine Translation into Low-resource Language Varieties](https://aclanthology.org/2021.acl-short.16) (Kumar et al., ACL-IJCNLP 2021)
ACL
- Sachin Kumar, Antonios Anastasopoulos, Shuly Wintner, and Yulia Tsvetkov. 2021. Machine Translation into Low-resource Language Varieties. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 2: Short Papers), pages 110–121, Online. Association for Computational Linguistics.