@inproceedings{poncelas-etal-2018-adapt,
title = "The {ADAPT} System Description for the {IWSLT} 2018 {B}asque to {E}nglish Translation Task",
author = "Poncelas, Alberto and
Way, Andy and
Sarasola, Kepa",
booktitle = "Proceedings of the 15th International Conference on Spoken Language Translation",
month = oct # " 29-30",
year = "2018",
address = "Brussels",
publisher = "International Conference on Spoken Language Translation",
url = "https://aclanthology.org/2018.iwslt-1.11",
pages = "76--82",
abstract = "In this paper we present the ADAPT system built for the Basque to English Low Resource MT Evaluation Campaign. Basque is a low-resourced, morphologically-rich language. This poses a challenge for Neural Machine Translation models which usually achieve better performance when trained with large sets of data. Accordingly, we used synthetic data to improve the translation quality produced by a model built using only authentic data. Our proposal uses back-translated data to: (a) create new sentences, so the system can be trained with more data; and (b) translate sentences that are close to the test set, so the model can be fine-tuned to the document to be translated.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="poncelas-etal-2018-adapt">
<titleInfo>
<title>The ADAPT System Description for the IWSLT 2018 Basque to English Translation Task</title>
</titleInfo>
<name type="personal">
<namePart type="given">Alberto</namePart>
<namePart type="family">Poncelas</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andy</namePart>
<namePart type="family">Way</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kepa</namePart>
<namePart type="family">Sarasola</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2018-oct" 29-30"</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 15th International Conference on Spoken Language Translation</title>
</titleInfo>
<originInfo>
<publisher>International Conference on Spoken Language Translation</publisher>
<place>
<placeTerm type="text">Brussels</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In this paper we present the ADAPT system built for the Basque to English Low Resource MT Evaluation Campaign. Basque is a low-resourced, morphologically-rich language. This poses a challenge for Neural Machine Translation models which usually achieve better performance when trained with large sets of data. Accordingly, we used synthetic data to improve the translation quality produced by a model built using only authentic data. Our proposal uses back-translated data to: (a) create new sentences, so the system can be trained with more data; and (b) translate sentences that are close to the test set, so the model can be fine-tuned to the document to be translated.</abstract>
<identifier type="citekey">poncelas-etal-2018-adapt</identifier>
<location>
<url>https://aclanthology.org/2018.iwslt-1.11</url>
</location>
<part>
<date>2018-oct" 29-30"</date>
<extent unit="page">
<start>76</start>
<end>82</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T The ADAPT System Description for the IWSLT 2018 Basque to English Translation Task
%A Poncelas, Alberto
%A Way, Andy
%A Sarasola, Kepa
%S Proceedings of the 15th International Conference on Spoken Language Translation
%D 2018
%8 oct" 29 30"
%I International Conference on Spoken Language Translation
%C Brussels
%F poncelas-etal-2018-adapt
%X In this paper we present the ADAPT system built for the Basque to English Low Resource MT Evaluation Campaign. Basque is a low-resourced, morphologically-rich language. This poses a challenge for Neural Machine Translation models which usually achieve better performance when trained with large sets of data. Accordingly, we used synthetic data to improve the translation quality produced by a model built using only authentic data. Our proposal uses back-translated data to: (a) create new sentences, so the system can be trained with more data; and (b) translate sentences that are close to the test set, so the model can be fine-tuned to the document to be translated.
%U https://aclanthology.org/2018.iwslt-1.11
%P 76-82
Markdown (Informal)
[The ADAPT System Description for the IWSLT 2018 Basque to English Translation Task](https://aclanthology.org/2018.iwslt-1.11) (Poncelas et al., IWSLT 2018)
ACL