@inproceedings{kvapilikova-etal-2020-cuni,
title = "{CUNI} Systems for the Unsupervised and Very Low Resource Translation Task in {WMT}20",
author = "Kvapil{\'\i}kov{\'a}, Ivana and
Kocmi, Tom and
Bojar, Ond{\v{r}}ej",
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-1.133",
pages = "1123--1128",
abstract = "This paper presents a description of CUNI systems submitted to the WMT20 task on unsupervised and very low-resource supervised machine translation between German and Upper Sorbian. We experimented with training on synthetic data and pre-training on a related language pair. In the fully unsupervised scenario, we achieved 25.5 and 23.7 BLEU translating from and into Upper Sorbian, respectively. Our low-resource systems relied on transfer learning from German-Czech parallel data and achieved 57.4 BLEU and 56.1 BLEU, which is an improvement of 10 BLEU points over the baseline trained only on the available small German-Upper Sorbian parallel corpus.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kvapilikova-etal-2020-cuni">
<titleInfo>
<title>CUNI Systems for the Unsupervised and Very Low Resource Translation Task in WMT20</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ivana</namePart>
<namePart type="family">Kvapilíková</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tom</namePart>
<namePart type="family">Kocmi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ondřej</namePart>
<namePart type="family">Bojar</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 presents a description of CUNI systems submitted to the WMT20 task on unsupervised and very low-resource supervised machine translation between German and Upper Sorbian. We experimented with training on synthetic data and pre-training on a related language pair. In the fully unsupervised scenario, we achieved 25.5 and 23.7 BLEU translating from and into Upper Sorbian, respectively. Our low-resource systems relied on transfer learning from German-Czech parallel data and achieved 57.4 BLEU and 56.1 BLEU, which is an improvement of 10 BLEU points over the baseline trained only on the available small German-Upper Sorbian parallel corpus.</abstract>
<identifier type="citekey">kvapilikova-etal-2020-cuni</identifier>
<location>
<url>https://aclanthology.org/2020.wmt-1.133</url>
</location>
<part>
<date>2020-nov</date>
<extent unit="page">
<start>1123</start>
<end>1128</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T CUNI Systems for the Unsupervised and Very Low Resource Translation Task in WMT20
%A Kvapilíková, Ivana
%A Kocmi, Tom
%A Bojar, Ondřej
%S Proceedings of the Fifth Conference on Machine Translation
%D 2020
%8 nov
%I Association for Computational Linguistics
%C Online
%F kvapilikova-etal-2020-cuni
%X This paper presents a description of CUNI systems submitted to the WMT20 task on unsupervised and very low-resource supervised machine translation between German and Upper Sorbian. We experimented with training on synthetic data and pre-training on a related language pair. In the fully unsupervised scenario, we achieved 25.5 and 23.7 BLEU translating from and into Upper Sorbian, respectively. Our low-resource systems relied on transfer learning from German-Czech parallel data and achieved 57.4 BLEU and 56.1 BLEU, which is an improvement of 10 BLEU points over the baseline trained only on the available small German-Upper Sorbian parallel corpus.
%U https://aclanthology.org/2020.wmt-1.133
%P 1123-1128
Markdown (Informal)
[CUNI Systems for the Unsupervised and Very Low Resource Translation Task in WMT20](https://aclanthology.org/2020.wmt-1.133) (Kvapilíková et al., WMT 2020)
ACL