Correct Metadata for
Abstract
This paper describes the SEBAMAT contribution to the 2021 WMT Similar Language Translation shared task. Using the Marian neural machine translation toolkit, translation systems based on Google’s transformer architecture were built in both directions of Catalan–Spanish and Portuguese–Spanish. The systems were trained in two contrastive parameter settings (different vocabulary sizes for byte pair encoding) using only the parallel but not the comparable corpora provided by the shared task organizers. According to their official evaluation results, the SEBAMAT system turned out to be competitive with rankings among the top teams and BLEU scores between 38 and 47 for the language pairs involving Portuguese and between 76 and 80 for the language pairs involving Catalan.- Anthology ID:
- 2021.wmt-1.31
- Volume:
- Proceedings of the Sixth Conference on Machine Translation
- Month:
- November
- Year:
- 2021
- Address:
- Online
- Editors:
- Loic Barrault, Ondrej Bojar, Fethi Bougares, Rajen Chatterjee, Marta R. Costa-jussa, Christian Federmann, Mark Fishel, Alexander Fraser, Markus Freitag, Yvette Graham, Roman Grundkiewicz, Paco Guzman, Barry Haddow, Matthias Huck, Antonio Jimeno Yepes, Philipp Koehn, Tom Kocmi, Andre Martins, Makoto Morishita, Christof Monz
- Venue:
- WMT
- SIG:
- SIGMT
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 292–298
- Language:
- URL:
- https://aclanthology.org/2021.wmt-1.31/
- DOI:
- Bibkey:
- Cite (ACL):
- Reinhard Rapp. 2021. Similar Language Translation for Catalan, Portuguese and Spanish Using Marian NMT. In Proceedings of the Sixth Conference on Machine Translation, pages 292–298, Online. Association for Computational Linguistics.
- Cite (Informal):
- Similar Language Translation for Catalan, Portuguese and Spanish Using Marian NMT (Rapp, WMT 2021)
- Copy Citation:
- PDF:
- https://aclanthology.org/2021.wmt-1.31.pdf
Export citation
@inproceedings{rapp-2021-similar,
title = "Similar Language Translation for {C}atalan, {P}ortuguese and {S}panish Using {M}arian {NMT}",
author = "Rapp, Reinhard",
editor = "Barrault, Loic and
Bojar, Ondrej and
Bougares, Fethi and
Chatterjee, Rajen and
Costa-jussa, Marta R. and
Federmann, Christian and
Fishel, Mark and
Fraser, Alexander and
Freitag, Markus and
Graham, Yvette and
Grundkiewicz, Roman and
Guzman, Paco and
Haddow, Barry and
Huck, Matthias and
Yepes, Antonio Jimeno and
Koehn, Philipp and
Kocmi, Tom and
Martins, Andre and
Morishita, Makoto and
Monz, Christof",
booktitle = "Proceedings of the Sixth Conference on Machine Translation",
month = nov,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.wmt-1.31/",
pages = "292--298",
abstract = "This paper describes the SEBAMAT contribution to the 2021 WMT Similar Language Translation shared task. Using the Marian neural machine translation toolkit, translation systems based on Google{'}s transformer architecture were built in both directions of Catalan{--}Spanish and Portuguese{--}Spanish. The systems were trained in two contrastive parameter settings (different vocabulary sizes for byte pair encoding) using only the parallel but not the comparable corpora provided by the shared task organizers. According to their official evaluation results, the SEBAMAT system turned out to be competitive with rankings among the top teams and BLEU scores between 38 and 47 for the language pairs involving Portuguese and between 76 and 80 for the language pairs involving Catalan."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="rapp-2021-similar">
<titleInfo>
<title>Similar Language Translation for Catalan, Portuguese and Spanish Using Marian NMT</title>
</titleInfo>
<name type="personal">
<namePart type="given">Reinhard</namePart>
<namePart type="family">Rapp</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Sixth Conference on Machine Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Loic</namePart>
<namePart type="family">Barrault</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ondrej</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-jussa</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">Markus</namePart>
<namePart type="family">Freitag</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">Roman</namePart>
<namePart type="family">Grundkiewicz</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">Tom</namePart>
<namePart type="family">Kocmi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andre</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>
<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 SEBAMAT contribution to the 2021 WMT Similar Language Translation shared task. Using the Marian neural machine translation toolkit, translation systems based on Google’s transformer architecture were built in both directions of Catalan–Spanish and Portuguese–Spanish. The systems were trained in two contrastive parameter settings (different vocabulary sizes for byte pair encoding) using only the parallel but not the comparable corpora provided by the shared task organizers. According to their official evaluation results, the SEBAMAT system turned out to be competitive with rankings among the top teams and BLEU scores between 38 and 47 for the language pairs involving Portuguese and between 76 and 80 for the language pairs involving Catalan.</abstract>
<identifier type="citekey">rapp-2021-similar</identifier>
<location>
<url>https://aclanthology.org/2021.wmt-1.31/</url>
</location>
<part>
<date>2021-11</date>
<extent unit="page">
<start>292</start>
<end>298</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings %T Similar Language Translation for Catalan, Portuguese and Spanish Using Marian NMT %A Rapp, Reinhard %Y Barrault, Loic %Y Bojar, Ondrej %Y Bougares, Fethi %Y Chatterjee, Rajen %Y Costa-jussa, Marta R. %Y Federmann, Christian %Y Fishel, Mark %Y Fraser, Alexander %Y Freitag, Markus %Y Graham, Yvette %Y Grundkiewicz, Roman %Y Guzman, Paco %Y Haddow, Barry %Y Huck, Matthias %Y Yepes, Antonio Jimeno %Y Koehn, Philipp %Y Kocmi, Tom %Y Martins, Andre %Y Morishita, Makoto %Y Monz, Christof %S Proceedings of the Sixth Conference on Machine Translation %D 2021 %8 November %I Association for Computational Linguistics %C Online %F rapp-2021-similar %X This paper describes the SEBAMAT contribution to the 2021 WMT Similar Language Translation shared task. Using the Marian neural machine translation toolkit, translation systems based on Google’s transformer architecture were built in both directions of Catalan–Spanish and Portuguese–Spanish. The systems were trained in two contrastive parameter settings (different vocabulary sizes for byte pair encoding) using only the parallel but not the comparable corpora provided by the shared task organizers. According to their official evaluation results, the SEBAMAT system turned out to be competitive with rankings among the top teams and BLEU scores between 38 and 47 for the language pairs involving Portuguese and between 76 and 80 for the language pairs involving Catalan. %U https://aclanthology.org/2021.wmt-1.31/ %P 292-298
Markdown (Informal)
[Similar Language Translation for Catalan, Portuguese and Spanish Using Marian NMT](https://aclanthology.org/2021.wmt-1.31/) (Rapp, WMT 2021)
ACL
- Reinhard Rapp. 2021. Similar Language Translation for Catalan, Portuguese and Spanish Using Marian NMT. In Proceedings of the Sixth Conference on Machine Translation, pages 292–298, Online. Association for Computational Linguistics.