@inproceedings{etchegoyhen-gete-2020-handle,
title = "Handle with Care: A Case Study in Comparable Corpora Exploitation for Neural Machine Translation",
author = "Etchegoyhen, Thierry and
Gete, Harritxu",
editor = "Calzolari, Nicoletta and
B{\'e}chet, Fr{\'e}d{\'e}ric and
Blache, Philippe and
Choukri, Khalid and
Cieri, Christopher and
Declerck, Thierry and
Goggi, Sara and
Isahara, Hitoshi and
Maegaard, Bente and
Mariani, Joseph and
Mazo, H{\'e}l{\`e}ne and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Twelfth Language Resources and Evaluation Conference",
month = may,
year = "2020",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2020.lrec-1.469/",
pages = "3799--3807",
language = "eng",
ISBN = "979-10-95546-34-4",
abstract = "We present the results of a case study in the exploitation of comparable corpora for Neural Machine Translation. A large comparable corpus for Basque-Spanish was prepared, on the basis of independently-produced news by the Basque public broadcaster EiTB, and we discuss the impact of various techniques to exploit the original data in order to determine optimal variants of the corpus. In particular, we show that filtering in terms of alignment thresholds and length-difference outliers has a significant impact on translation quality. The impact of tags identifying comparable data in the training datasets is also evaluated, with results indicating that this technique might be useful to help the models discriminate noisy information, in the form of informational imbalance between aligned sentences. The final corpus was prepared according to the experimental results and is made available to the scientific community for research purposes."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="etchegoyhen-gete-2020-handle">
<titleInfo>
<title>Handle with Care: A Case Study in Comparable Corpora Exploitation for Neural Machine Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Thierry</namePart>
<namePart type="family">Etchegoyhen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Harritxu</namePart>
<namePart type="family">Gete</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<language>
<languageTerm type="text">eng</languageTerm>
</language>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Twelfth Language Resources and Evaluation Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Frédéric</namePart>
<namePart type="family">Béchet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philippe</namePart>
<namePart type="family">Blache</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalid</namePart>
<namePart type="family">Choukri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christopher</namePart>
<namePart type="family">Cieri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thierry</namePart>
<namePart type="family">Declerck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Goggi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hitoshi</namePart>
<namePart type="family">Isahara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bente</namePart>
<namePart type="family">Maegaard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joseph</namePart>
<namePart type="family">Mariani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hélène</namePart>
<namePart type="family">Mazo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Asuncion</namePart>
<namePart type="family">Moreno</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Odijk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</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>
<identifier type="isbn">979-10-95546-34-4</identifier>
</relatedItem>
<abstract>We present the results of a case study in the exploitation of comparable corpora for Neural Machine Translation. A large comparable corpus for Basque-Spanish was prepared, on the basis of independently-produced news by the Basque public broadcaster EiTB, and we discuss the impact of various techniques to exploit the original data in order to determine optimal variants of the corpus. In particular, we show that filtering in terms of alignment thresholds and length-difference outliers has a significant impact on translation quality. The impact of tags identifying comparable data in the training datasets is also evaluated, with results indicating that this technique might be useful to help the models discriminate noisy information, in the form of informational imbalance between aligned sentences. The final corpus was prepared according to the experimental results and is made available to the scientific community for research purposes.</abstract>
<identifier type="citekey">etchegoyhen-gete-2020-handle</identifier>
<location>
<url>https://aclanthology.org/2020.lrec-1.469/</url>
</location>
<part>
<date>2020-05</date>
<extent unit="page">
<start>3799</start>
<end>3807</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Handle with Care: A Case Study in Comparable Corpora Exploitation for Neural Machine Translation
%A Etchegoyhen, Thierry
%A Gete, Harritxu
%Y Calzolari, Nicoletta
%Y Béchet, Frédéric
%Y Blache, Philippe
%Y Choukri, Khalid
%Y Cieri, Christopher
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Isahara, Hitoshi
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Hélène
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Twelfth Language Resources and Evaluation Conference
%D 2020
%8 May
%I European Language Resources Association
%C Marseille, France
%@ 979-10-95546-34-4
%G eng
%F etchegoyhen-gete-2020-handle
%X We present the results of a case study in the exploitation of comparable corpora for Neural Machine Translation. A large comparable corpus for Basque-Spanish was prepared, on the basis of independently-produced news by the Basque public broadcaster EiTB, and we discuss the impact of various techniques to exploit the original data in order to determine optimal variants of the corpus. In particular, we show that filtering in terms of alignment thresholds and length-difference outliers has a significant impact on translation quality. The impact of tags identifying comparable data in the training datasets is also evaluated, with results indicating that this technique might be useful to help the models discriminate noisy information, in the form of informational imbalance between aligned sentences. The final corpus was prepared according to the experimental results and is made available to the scientific community for research purposes.
%U https://aclanthology.org/2020.lrec-1.469/
%P 3799-3807
Markdown (Informal)
[Handle with Care: A Case Study in Comparable Corpora Exploitation for Neural Machine Translation](https://aclanthology.org/2020.lrec-1.469/) (Etchegoyhen & Gete, LREC 2020)
ACL