@inproceedings{azpeitia-etal-2018-stacc,
title = "{STACC}, {OOV} Density and N-gram Saturation: Vicomtech{'}s Participation in the {WMT} 2018 Shared Task on Parallel Corpus Filtering",
author = "Azpeitia, Andoni and
Etchegoyhen, Thierry and
Mart{\'\i}nez Garcia, Eva",
editor = "Bojar, Ond{\v{r}}ej and
Chatterjee, Rajen and
Federmann, Christian and
Fishel, Mark and
Graham, Yvette and
Haddow, Barry and
Huck, Matthias and
Yepes, Antonio Jimeno and
Koehn, Philipp and
Monz, Christof and
Negri, Matteo and
N{\'e}v{\'e}ol, Aur{\'e}lie and
Neves, Mariana and
Post, Matt and
Specia, Lucia and
Turchi, Marco and
Verspoor, Karin",
booktitle = "Proceedings of the Third Conference on Machine Translation: Shared Task Papers",
month = oct,
year = "2018",
address = "Belgium, Brussels",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/W18-6473",
doi = "10.18653/v1/W18-6473",
pages = "860--866",
abstract = "We describe Vicomtech{'}s participation in the WMT 2018 Shared Task on parallel corpus filtering. We aimed to evaluate a simple approach to the task, which can efficiently process large volumes of data and can be easily deployed for new datasets in different language pairs and domains. We based our approach on STACC, an efficient and portable method for parallel sentence identification in comparable corpora. To address the specifics of the corpus filtering task, which features significant volumes of noisy data, the core method was expanded with a penalty based on the amount of unknown words in sentence pairs. Additionally, we experimented with a complementary data saturation method based on source sentence n-grams, with the goal of demoting parallel sentence pairs that do not contribute significant amounts of yet unobserved n-grams. Our approach requires no prior training and is highly efficient on the type of large datasets featured in the corpus filtering task. We achieved competitive results with this simple and portable method, ranking in the top half among competing systems overall.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="azpeitia-etal-2018-stacc">
<titleInfo>
<title>STACC, OOV Density and N-gram Saturation: Vicomtech’s Participation in the WMT 2018 Shared Task on Parallel Corpus Filtering</title>
</titleInfo>
<name type="personal">
<namePart type="given">Andoni</namePart>
<namePart type="family">Azpeitia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<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">Eva</namePart>
<namePart type="family">Martínez Garcia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2018-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Third Conference on Machine Translation: Shared Task Papers</title>
</titleInfo>
<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">Rajen</namePart>
<namePart type="family">Chatterjee</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">Yvette</namePart>
<namePart type="family">Graham</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">Christof</namePart>
<namePart type="family">Monz</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>
<name type="personal">
<namePart type="given">Aurélie</namePart>
<namePart type="family">Névéol</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mariana</namePart>
<namePart type="family">Neves</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Matt</namePart>
<namePart type="family">Post</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lucia</namePart>
<namePart type="family">Specia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marco</namePart>
<namePart type="family">Turchi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Karin</namePart>
<namePart type="family">Verspoor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Belgium, Brussels</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We describe Vicomtech’s participation in the WMT 2018 Shared Task on parallel corpus filtering. We aimed to evaluate a simple approach to the task, which can efficiently process large volumes of data and can be easily deployed for new datasets in different language pairs and domains. We based our approach on STACC, an efficient and portable method for parallel sentence identification in comparable corpora. To address the specifics of the corpus filtering task, which features significant volumes of noisy data, the core method was expanded with a penalty based on the amount of unknown words in sentence pairs. Additionally, we experimented with a complementary data saturation method based on source sentence n-grams, with the goal of demoting parallel sentence pairs that do not contribute significant amounts of yet unobserved n-grams. Our approach requires no prior training and is highly efficient on the type of large datasets featured in the corpus filtering task. We achieved competitive results with this simple and portable method, ranking in the top half among competing systems overall.</abstract>
<identifier type="citekey">azpeitia-etal-2018-stacc</identifier>
<identifier type="doi">10.18653/v1/W18-6473</identifier>
<location>
<url>https://aclanthology.org/W18-6473</url>
</location>
<part>
<date>2018-10</date>
<extent unit="page">
<start>860</start>
<end>866</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T STACC, OOV Density and N-gram Saturation: Vicomtech’s Participation in the WMT 2018 Shared Task on Parallel Corpus Filtering
%A Azpeitia, Andoni
%A Etchegoyhen, Thierry
%A Martínez Garcia, Eva
%Y Bojar, Ondřej
%Y Chatterjee, Rajen
%Y Federmann, Christian
%Y Fishel, Mark
%Y Graham, Yvette
%Y Haddow, Barry
%Y Huck, Matthias
%Y Yepes, Antonio Jimeno
%Y Koehn, Philipp
%Y Monz, Christof
%Y Negri, Matteo
%Y Névéol, Aurélie
%Y Neves, Mariana
%Y Post, Matt
%Y Specia, Lucia
%Y Turchi, Marco
%Y Verspoor, Karin
%S Proceedings of the Third Conference on Machine Translation: Shared Task Papers
%D 2018
%8 October
%I Association for Computational Linguistics
%C Belgium, Brussels
%F azpeitia-etal-2018-stacc
%X We describe Vicomtech’s participation in the WMT 2018 Shared Task on parallel corpus filtering. We aimed to evaluate a simple approach to the task, which can efficiently process large volumes of data and can be easily deployed for new datasets in different language pairs and domains. We based our approach on STACC, an efficient and portable method for parallel sentence identification in comparable corpora. To address the specifics of the corpus filtering task, which features significant volumes of noisy data, the core method was expanded with a penalty based on the amount of unknown words in sentence pairs. Additionally, we experimented with a complementary data saturation method based on source sentence n-grams, with the goal of demoting parallel sentence pairs that do not contribute significant amounts of yet unobserved n-grams. Our approach requires no prior training and is highly efficient on the type of large datasets featured in the corpus filtering task. We achieved competitive results with this simple and portable method, ranking in the top half among competing systems overall.
%R 10.18653/v1/W18-6473
%U https://aclanthology.org/W18-6473
%U https://doi.org/10.18653/v1/W18-6473
%P 860-866
Markdown (Informal)
[STACC, OOV Density and N-gram Saturation: Vicomtech’s Participation in the WMT 2018 Shared Task on Parallel Corpus Filtering](https://aclanthology.org/W18-6473) (Azpeitia et al., WMT 2018)
ACL