@inproceedings{popovic-poncelas-2020-neural,
title = "Neural Machine Translation between similar {S}outh-{S}lavic languages",
author = "Popovi{\'c}, Maja and
Poncelas, Alberto",
editor = {Barrault, Lo{\"i}c and
Bojar, Ond{\v{r}}ej and
Bougares, Fethi and
Chatterjee, Rajen and
Costa-juss{\`a}, Marta R. and
Federmann, Christian and
Fishel, Mark and
Fraser, Alexander and
Graham, Yvette and
Guzman, Paco and
Haddow, Barry and
Huck, Matthias and
Yepes, Antonio Jimeno and
Koehn, Philipp and
Martins, Andr{\'e} and
Morishita, Makoto and
Monz, Christof and
Nagata, Masaaki and
Nakazawa, Toshiaki and
Negri, Matteo},
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-1.51/",
pages = "430--436",
abstract = "This paper describes the ADAPT-DCU machine translation systems built for the WMT 2020 shared task on Similar Language Translation. We explored several set-ups for NMT for Croatian{--}Slovenian and Serbian{--}Slovenian language pairs in both translation directions. Our experiments focus on different amounts and types of training data: we first apply basic filtering on the OpenSubtitles training corpora, then we perform additional cleaning of remaining misaligned segments based on character n-gram matching. Finally, we make use of additional monolingual data by creating synthetic parallel data through back-translation. Automatic evaluation shows that multilingual systems with joint Serbian and Croatian data are better than bilingual, as well as that character-based cleaning leads to improved scores while using less data. The results also confirm once more that adding back-translated data further improves the performance, especially when the synthetic data is similar to the desired domain of the development and test set. This, however, might come at a price of prolonged training time, especially for multitarget systems."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="popovic-poncelas-2020-neural">
<titleInfo>
<title>Neural Machine Translation between similar South-Slavic languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maja</namePart>
<namePart type="family">Popović</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alberto</namePart>
<namePart type="family">Poncelas</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fifth Conference on Machine Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Loïc</namePart>
<namePart type="family">Barrault</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ondřej</namePart>
<namePart type="family">Bojar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fethi</namePart>
<namePart type="family">Bougares</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rajen</namePart>
<namePart type="family">Chatterjee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marta</namePart>
<namePart type="given">R</namePart>
<namePart type="family">Costa-jussà</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christian</namePart>
<namePart type="family">Federmann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mark</namePart>
<namePart type="family">Fishel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexander</namePart>
<namePart type="family">Fraser</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yvette</namePart>
<namePart type="family">Graham</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Paco</namePart>
<namePart type="family">Guzman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Barry</namePart>
<namePart type="family">Haddow</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Matthias</namePart>
<namePart type="family">Huck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antonio</namePart>
<namePart type="given">Jimeno</namePart>
<namePart type="family">Yepes</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philipp</namePart>
<namePart type="family">Koehn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">André</namePart>
<namePart type="family">Martins</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Makoto</namePart>
<namePart type="family">Morishita</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christof</namePart>
<namePart type="family">Monz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Masaaki</namePart>
<namePart type="family">Nagata</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Toshiaki</namePart>
<namePart type="family">Nakazawa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Matteo</namePart>
<namePart type="family">Negri</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>This paper describes the ADAPT-DCU machine translation systems built for the WMT 2020 shared task on Similar Language Translation. We explored several set-ups for NMT for Croatian–Slovenian and Serbian–Slovenian language pairs in both translation directions. Our experiments focus on different amounts and types of training data: we first apply basic filtering on the OpenSubtitles training corpora, then we perform additional cleaning of remaining misaligned segments based on character n-gram matching. Finally, we make use of additional monolingual data by creating synthetic parallel data through back-translation. Automatic evaluation shows that multilingual systems with joint Serbian and Croatian data are better than bilingual, as well as that character-based cleaning leads to improved scores while using less data. The results also confirm once more that adding back-translated data further improves the performance, especially when the synthetic data is similar to the desired domain of the development and test set. This, however, might come at a price of prolonged training time, especially for multitarget systems.</abstract>
<identifier type="citekey">popovic-poncelas-2020-neural</identifier>
<location>
<url>https://aclanthology.org/2020.wmt-1.51/</url>
</location>
<part>
<date>2020-11</date>
<extent unit="page">
<start>430</start>
<end>436</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Neural Machine Translation between similar South-Slavic languages
%A Popović, Maja
%A Poncelas, Alberto
%Y Barrault, Loïc
%Y Bojar, Ondřej
%Y Bougares, Fethi
%Y Chatterjee, Rajen
%Y Costa-jussà, Marta R.
%Y Federmann, Christian
%Y Fishel, Mark
%Y Fraser, Alexander
%Y Graham, Yvette
%Y Guzman, Paco
%Y Haddow, Barry
%Y Huck, Matthias
%Y Yepes, Antonio Jimeno
%Y Koehn, Philipp
%Y Martins, André
%Y Morishita, Makoto
%Y Monz, Christof
%Y Nagata, Masaaki
%Y Nakazawa, Toshiaki
%Y Negri, Matteo
%S Proceedings of the Fifth Conference on Machine Translation
%D 2020
%8 November
%I Association for Computational Linguistics
%C Online
%F popovic-poncelas-2020-neural
%X This paper describes the ADAPT-DCU machine translation systems built for the WMT 2020 shared task on Similar Language Translation. We explored several set-ups for NMT for Croatian–Slovenian and Serbian–Slovenian language pairs in both translation directions. Our experiments focus on different amounts and types of training data: we first apply basic filtering on the OpenSubtitles training corpora, then we perform additional cleaning of remaining misaligned segments based on character n-gram matching. Finally, we make use of additional monolingual data by creating synthetic parallel data through back-translation. Automatic evaluation shows that multilingual systems with joint Serbian and Croatian data are better than bilingual, as well as that character-based cleaning leads to improved scores while using less data. The results also confirm once more that adding back-translated data further improves the performance, especially when the synthetic data is similar to the desired domain of the development and test set. This, however, might come at a price of prolonged training time, especially for multitarget systems.
%U https://aclanthology.org/2020.wmt-1.51/
%P 430-436
Markdown (Informal)
[Neural Machine Translation between similar South-Slavic languages](https://aclanthology.org/2020.wmt-1.51/) (Popović & Poncelas, WMT 2020)
ACL