@inproceedings{escolano-etal-2021-talp,
title = "The {TALP}-{UPC} Participation in {WMT}21 News Translation Task: an m{BART}-based {NMT} Approach",
author = "Escolano, Carlos and
Tsiamas, Ioannis and
Basta, Christine and
Ferrando, Javier and
Costa-jussa, Marta R. and
Fonollosa, Jos{\'e} A. R.",
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-1.6",
pages = "117--122",
abstract = "This paper describes the submission to the WMT 2021 news translation shared task by the UPC Machine Translation group. The goal of the task is to translate German to French (De-Fr) and French to German (Fr-De). Our submission focuses on fine-tuning a pre-trained model to take advantage of monolingual data. We fine-tune mBART50 using the filtered data, and additionally, we train a Transformer model on the same data from scratch. In the experiments, we show that fine-tuning mBART50 results in 31.69 BLEU for De-Fr and 23.63 BLEU for Fr-De, which increases 2.71 and 1.90 BLEU accordingly, as compared to the model we train from scratch. Our final submission is an ensemble of these two models, further increasing 0.3 BLEU for Fr-De.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="escolano-etal-2021-talp">
<titleInfo>
<title>The TALP-UPC Participation in WMT21 News Translation Task: an mBART-based NMT Approach</title>
</titleInfo>
<name type="personal">
<namePart type="given">Carlos</namePart>
<namePart type="family">Escolano</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ioannis</namePart>
<namePart type="family">Tsiamas</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christine</namePart>
<namePart type="family">Basta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Javier</namePart>
<namePart type="family">Ferrando</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</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">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">José</namePart>
<namePart type="given">A</namePart>
<namePart type="given">R</namePart>
<namePart type="family">Fonollosa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-nov</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Sixth 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 describes the submission to the WMT 2021 news translation shared task by the UPC Machine Translation group. The goal of the task is to translate German to French (De-Fr) and French to German (Fr-De). Our submission focuses on fine-tuning a pre-trained model to take advantage of monolingual data. We fine-tune mBART50 using the filtered data, and additionally, we train a Transformer model on the same data from scratch. In the experiments, we show that fine-tuning mBART50 results in 31.69 BLEU for De-Fr and 23.63 BLEU for Fr-De, which increases 2.71 and 1.90 BLEU accordingly, as compared to the model we train from scratch. Our final submission is an ensemble of these two models, further increasing 0.3 BLEU for Fr-De.</abstract>
<identifier type="citekey">escolano-etal-2021-talp</identifier>
<location>
<url>https://aclanthology.org/2021.wmt-1.6</url>
</location>
<part>
<date>2021-nov</date>
<extent unit="page">
<start>117</start>
<end>122</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T The TALP-UPC Participation in WMT21 News Translation Task: an mBART-based NMT Approach
%A Escolano, Carlos
%A Tsiamas, Ioannis
%A Basta, Christine
%A Ferrando, Javier
%A Costa-jussa, Marta R.
%A Fonollosa, José A. R.
%S Proceedings of the Sixth Conference on Machine Translation
%D 2021
%8 nov
%I Association for Computational Linguistics
%C Online
%F escolano-etal-2021-talp
%X This paper describes the submission to the WMT 2021 news translation shared task by the UPC Machine Translation group. The goal of the task is to translate German to French (De-Fr) and French to German (Fr-De). Our submission focuses on fine-tuning a pre-trained model to take advantage of monolingual data. We fine-tune mBART50 using the filtered data, and additionally, we train a Transformer model on the same data from scratch. In the experiments, we show that fine-tuning mBART50 results in 31.69 BLEU for De-Fr and 23.63 BLEU for Fr-De, which increases 2.71 and 1.90 BLEU accordingly, as compared to the model we train from scratch. Our final submission is an ensemble of these two models, further increasing 0.3 BLEU for Fr-De.
%U https://aclanthology.org/2021.wmt-1.6
%P 117-122
Markdown (Informal)
[The TALP-UPC Participation in WMT21 News Translation Task: an mBART-based NMT Approach](https://aclanthology.org/2021.wmt-1.6) (Escolano et al., WMT 2021)
ACL