@inproceedings{kvapilikova-bojar-2022-cuni,
title = "{CUNI} Submission to {MT}4{A}ll Shared Task",
author = "Kvapil{\'i}kov{\'a}, Ivana and
Bojar, Ondrej",
editor = "Melero, Maite and
Sakti, Sakriani and
Soria, Claudia",
booktitle = "Proceedings of the 1st Annual Meeting of the ELRA/ISCA Special Interest Group on Under-Resourced Languages",
month = jun,
year = "2022",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2022.sigul-1.10/",
pages = "78--82",
abstract = "This paper describes our submission to the MT4All Shared Task in unsupervised machine translation from English to Ukrainian, Kazakh and Georgian in the legal domain. In addition to the standard pipeline for unsupervised training (pretraining followed by denoising and back-translation), we used supervised training on a pseudo-parallel corpus retrieved from the provided mono-lingual corpora. Our system scored significantly higher than the baseline hybrid unsupervised MT system."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kvapilikova-bojar-2022-cuni">
<titleInfo>
<title>CUNI Submission to MT4All Shared Task</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">Ondrej</namePart>
<namePart type="family">Bojar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 1st Annual Meeting of the ELRA/ISCA Special Interest Group on Under-Resourced Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maite</namePart>
<namePart type="family">Melero</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Claudia</namePart>
<namePart type="family">Soria</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper describes our submission to the MT4All Shared Task in unsupervised machine translation from English to Ukrainian, Kazakh and Georgian in the legal domain. In addition to the standard pipeline for unsupervised training (pretraining followed by denoising and back-translation), we used supervised training on a pseudo-parallel corpus retrieved from the provided mono-lingual corpora. Our system scored significantly higher than the baseline hybrid unsupervised MT system.</abstract>
<identifier type="citekey">kvapilikova-bojar-2022-cuni</identifier>
<location>
<url>https://aclanthology.org/2022.sigul-1.10/</url>
</location>
<part>
<date>2022-06</date>
<extent unit="page">
<start>78</start>
<end>82</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T CUNI Submission to MT4All Shared Task
%A Kvapilíková, Ivana
%A Bojar, Ondrej
%Y Melero, Maite
%Y Sakti, Sakriani
%Y Soria, Claudia
%S Proceedings of the 1st Annual Meeting of the ELRA/ISCA Special Interest Group on Under-Resourced Languages
%D 2022
%8 June
%I European Language Resources Association
%C Marseille, France
%F kvapilikova-bojar-2022-cuni
%X This paper describes our submission to the MT4All Shared Task in unsupervised machine translation from English to Ukrainian, Kazakh and Georgian in the legal domain. In addition to the standard pipeline for unsupervised training (pretraining followed by denoising and back-translation), we used supervised training on a pseudo-parallel corpus retrieved from the provided mono-lingual corpora. Our system scored significantly higher than the baseline hybrid unsupervised MT system.
%U https://aclanthology.org/2022.sigul-1.10/
%P 78-82
Markdown (Informal)
[CUNI Submission to MT4All Shared Task](https://aclanthology.org/2022.sigul-1.10/) (Kvapilíková & Bojar, SIGUL 2022)
ACL
- Ivana Kvapilíková and Ondrej Bojar. 2022. CUNI Submission to MT4All Shared Task. In Proceedings of the 1st Annual Meeting of the ELRA/ISCA Special Interest Group on Under-Resourced Languages, pages 78–82, Marseille, France. European Language Resources Association.