@inproceedings{sanchez-cartagena-etal-2018-prompsits,
title = "Prompsit`s submission to {WMT} 2018 Parallel Corpus Filtering shared task",
author = "S{\'a}nchez-Cartagena, V{\'i}ctor M. and
Ba{\~n}{\'o}n, Marta and
Ortiz-Rojas, Sergio and
Ram{\'i}rez, Gema",
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/W18-6488/",
doi = "10.18653/v1/W18-6488",
pages = "955--962",
abstract = "This paper describes Prompsit Language Engineering`s submissions to the WMT 2018 parallel corpus filtering shared task. Our four submissions were based on an automatic classifier for identifying pairs of sentences that are mutual translations. A set of hand-crafted hard rules for discarding sentences with evident flaws were applied before the classifier. We explored different strategies for achieving a training corpus with diverse vocabulary and fluent sentences: language model scoring, an active-learning-inspired data selection algorithm and n-gram saturation. Our submissions were very competitive in comparison with other participants on the 100 million word training corpus."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sanchez-cartagena-etal-2018-prompsits">
<titleInfo>
<title>Prompsit‘s submission to WMT 2018 Parallel Corpus Filtering shared task</title>
</titleInfo>
<name type="personal">
<namePart type="given">Víctor</namePart>
<namePart type="given">M</namePart>
<namePart type="family">Sánchez-Cartagena</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marta</namePart>
<namePart type="family">Bañón</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sergio</namePart>
<namePart type="family">Ortiz-Rojas</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gema</namePart>
<namePart type="family">Ramírez</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>This paper describes Prompsit Language Engineering‘s submissions to the WMT 2018 parallel corpus filtering shared task. Our four submissions were based on an automatic classifier for identifying pairs of sentences that are mutual translations. A set of hand-crafted hard rules for discarding sentences with evident flaws were applied before the classifier. We explored different strategies for achieving a training corpus with diverse vocabulary and fluent sentences: language model scoring, an active-learning-inspired data selection algorithm and n-gram saturation. Our submissions were very competitive in comparison with other participants on the 100 million word training corpus.</abstract>
<identifier type="citekey">sanchez-cartagena-etal-2018-prompsits</identifier>
<identifier type="doi">10.18653/v1/W18-6488</identifier>
<location>
<url>https://aclanthology.org/W18-6488/</url>
</location>
<part>
<date>2018-10</date>
<extent unit="page">
<start>955</start>
<end>962</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Prompsit‘s submission to WMT 2018 Parallel Corpus Filtering shared task
%A Sánchez-Cartagena, Víctor M.
%A Bañón, Marta
%A Ortiz-Rojas, Sergio
%A Ramírez, Gema
%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 sanchez-cartagena-etal-2018-prompsits
%X This paper describes Prompsit Language Engineering‘s submissions to the WMT 2018 parallel corpus filtering shared task. Our four submissions were based on an automatic classifier for identifying pairs of sentences that are mutual translations. A set of hand-crafted hard rules for discarding sentences with evident flaws were applied before the classifier. We explored different strategies for achieving a training corpus with diverse vocabulary and fluent sentences: language model scoring, an active-learning-inspired data selection algorithm and n-gram saturation. Our submissions were very competitive in comparison with other participants on the 100 million word training corpus.
%R 10.18653/v1/W18-6488
%U https://aclanthology.org/W18-6488/
%U https://doi.org/10.18653/v1/W18-6488
%P 955-962
Markdown (Informal)
[Prompsit’s submission to WMT 2018 Parallel Corpus Filtering shared task](https://aclanthology.org/W18-6488/) (Sánchez-Cartagena et al., WMT 2018)
ACL