@inproceedings{bawden-etal-2020-university,
title = "The {U}niversity of {E}dinburgh{'}s {E}nglish-{T}amil and {E}nglish-{I}nuktitut Submissions to the {WMT}20 News Translation Task",
author = "Bawden, Rachel and
Birch, Alexandra and
Dobreva, Radina and
Oncevay, Arturo and
Miceli Barone, Antonio Valerio and
Williams, Philip",
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-1.5",
pages = "92--99",
abstract = "We describe the University of Edinburgh{'}s submissions to the WMT20 news translation shared task for the low resource language pair English-Tamil and the mid-resource language pair English-Inuktitut. We use the neural machine translation transformer architecture for all submissions and explore a variety of techniques to improve translation quality to compensate for the lack of parallel training data. For the very low-resource English-Tamil, this involves exploring pretraining, using both language model objectives and translation using an unrelated high-resource language pair (German-English), and iterative backtranslation. For English-Inuktitut, we explore the use of multilingual systems, which, despite not being part of the primary submission, would have achieved the best results on the test set.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bawden-etal-2020-university">
<titleInfo>
<title>The University of Edinburgh’s English-Tamil and English-Inuktitut Submissions to the WMT20 News Translation Task</title>
</titleInfo>
<name type="personal">
<namePart type="given">Rachel</namePart>
<namePart type="family">Bawden</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexandra</namePart>
<namePart type="family">Birch</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Radina</namePart>
<namePart type="family">Dobreva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Arturo</namePart>
<namePart type="family">Oncevay</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antonio</namePart>
<namePart type="given">Valerio</namePart>
<namePart type="family">Miceli Barone</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philip</namePart>
<namePart type="family">Williams</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>We describe the University of Edinburgh’s submissions to the WMT20 news translation shared task for the low resource language pair English-Tamil and the mid-resource language pair English-Inuktitut. We use the neural machine translation transformer architecture for all submissions and explore a variety of techniques to improve translation quality to compensate for the lack of parallel training data. For the very low-resource English-Tamil, this involves exploring pretraining, using both language model objectives and translation using an unrelated high-resource language pair (German-English), and iterative backtranslation. For English-Inuktitut, we explore the use of multilingual systems, which, despite not being part of the primary submission, would have achieved the best results on the test set.</abstract>
<identifier type="citekey">bawden-etal-2020-university</identifier>
<location>
<url>https://aclanthology.org/2020.wmt-1.5</url>
</location>
<part>
<date>2020-nov</date>
<extent unit="page">
<start>92</start>
<end>99</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T The University of Edinburgh’s English-Tamil and English-Inuktitut Submissions to the WMT20 News Translation Task
%A Bawden, Rachel
%A Birch, Alexandra
%A Dobreva, Radina
%A Oncevay, Arturo
%A Miceli Barone, Antonio Valerio
%A Williams, Philip
%S Proceedings of the Fifth Conference on Machine Translation
%D 2020
%8 nov
%I Association for Computational Linguistics
%C Online
%F bawden-etal-2020-university
%X We describe the University of Edinburgh’s submissions to the WMT20 news translation shared task for the low resource language pair English-Tamil and the mid-resource language pair English-Inuktitut. We use the neural machine translation transformer architecture for all submissions and explore a variety of techniques to improve translation quality to compensate for the lack of parallel training data. For the very low-resource English-Tamil, this involves exploring pretraining, using both language model objectives and translation using an unrelated high-resource language pair (German-English), and iterative backtranslation. For English-Inuktitut, we explore the use of multilingual systems, which, despite not being part of the primary submission, would have achieved the best results on the test set.
%U https://aclanthology.org/2020.wmt-1.5
%P 92-99
Markdown (Informal)
[The University of Edinburgh’s English-Tamil and English-Inuktitut Submissions to the WMT20 News Translation Task](https://aclanthology.org/2020.wmt-1.5) (Bawden et al., WMT 2020)
ACL