@inproceedings{ul-haq-etal-2020-document,
title = "Document Level {NMT} of Low-Resource Languages with Backtranslation",
author = "Ul Haq, Sami and
Abdul Rauf, Sadaf and
Shaukat, Arsalan and
Saeed, Abdullah",
booktitle = "Proceedings of the Fifth Conference on Machine Translation",
month = nov,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.wmt-1.53",
pages = "442--446",
abstract = "This paper describes our system submission to WMT20 shared task on similar language translation. We examined the use of documentlevel neural machine translation (NMT) systems for low-resource, similar language pair Marathi−Hindi. Our system is an extension of state-of-the-art Transformer architecture with hierarchical attention networks to incorporate contextual information. Since, NMT requires large amount of parallel data which is not available for this task, our approach is focused on utilizing monolingual data with back translation to train our models. Our experiments reveal that document-level NMT can be a reasonable alternative to sentence-level NMT for improving translation quality of low resourced languages even when used with synthetic data.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ul-haq-etal-2020-document">
<titleInfo>
<title>Document Level NMT of Low-Resource Languages with Backtranslation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sami</namePart>
<namePart type="family">Ul Haq</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sadaf</namePart>
<namePart type="family">Abdul Rauf</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Arsalan</namePart>
<namePart type="family">Shaukat</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Abdullah</namePart>
<namePart type="family">Saeed</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-nov</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fifth Conference on Machine Translation</title>
</titleInfo>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper describes our system submission to WMT20 shared task on similar language translation. We examined the use of documentlevel neural machine translation (NMT) systems for low-resource, similar language pair Marathi−Hindi. Our system is an extension of state-of-the-art Transformer architecture with hierarchical attention networks to incorporate contextual information. Since, NMT requires large amount of parallel data which is not available for this task, our approach is focused on utilizing monolingual data with back translation to train our models. Our experiments reveal that document-level NMT can be a reasonable alternative to sentence-level NMT for improving translation quality of low resourced languages even when used with synthetic data.</abstract>
<identifier type="citekey">ul-haq-etal-2020-document</identifier>
<location>
<url>https://aclanthology.org/2020.wmt-1.53</url>
</location>
<part>
<date>2020-nov</date>
<extent unit="page">
<start>442</start>
<end>446</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Document Level NMT of Low-Resource Languages with Backtranslation
%A Ul Haq, Sami
%A Abdul Rauf, Sadaf
%A Shaukat, Arsalan
%A Saeed, Abdullah
%S Proceedings of the Fifth Conference on Machine Translation
%D 2020
%8 nov
%I Association for Computational Linguistics
%C Online
%F ul-haq-etal-2020-document
%X This paper describes our system submission to WMT20 shared task on similar language translation. We examined the use of documentlevel neural machine translation (NMT) systems for low-resource, similar language pair Marathi−Hindi. Our system is an extension of state-of-the-art Transformer architecture with hierarchical attention networks to incorporate contextual information. Since, NMT requires large amount of parallel data which is not available for this task, our approach is focused on utilizing monolingual data with back translation to train our models. Our experiments reveal that document-level NMT can be a reasonable alternative to sentence-level NMT for improving translation quality of low resourced languages even when used with synthetic data.
%U https://aclanthology.org/2020.wmt-1.53
%P 442-446
Markdown (Informal)
[Document Level NMT of Low-Resource Languages with Backtranslation](https://aclanthology.org/2020.wmt-1.53) (Ul Haq et al., WMT 2020)
ACL