@inproceedings{khayrallah-etal-2018-jhu,
title = "The {JHU} Parallel Corpus Filtering Systems for {WMT} 2018",
author = "Khayrallah, Huda and
Xu, Hainan and
Koehn, Philipp",
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/W18-6479",
doi = "10.18653/v1/W18-6479",
pages = "896--899",
abstract = "This work describes our submission to the WMT18 Parallel Corpus Filtering shared task. We use a slightly modified version of the Zipporah Corpus Filtering toolkit (Xu and Koehn, 2017), which computes an adequacy score and a fluency score on a sentence pair, and use a weighted sum of the scores as the selection criteria. This work differs from Zipporah in that we experiment with using the noisy corpus to be filtered to compute the combination weights, and thus avoids generating synthetic data as in standard Zipporah.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="khayrallah-etal-2018-jhu">
<titleInfo>
<title>The JHU Parallel Corpus Filtering Systems for WMT 2018</title>
</titleInfo>
<name type="personal">
<namePart type="given">Huda</namePart>
<namePart type="family">Khayrallah</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hainan</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philipp</namePart>
<namePart type="family">Koehn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2018-oct</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Third Conference on Machine Translation: Shared Task Papers</title>
</titleInfo>
<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 work describes our submission to the WMT18 Parallel Corpus Filtering shared task. We use a slightly modified version of the Zipporah Corpus Filtering toolkit (Xu and Koehn, 2017), which computes an adequacy score and a fluency score on a sentence pair, and use a weighted sum of the scores as the selection criteria. This work differs from Zipporah in that we experiment with using the noisy corpus to be filtered to compute the combination weights, and thus avoids generating synthetic data as in standard Zipporah.</abstract>
<identifier type="citekey">khayrallah-etal-2018-jhu</identifier>
<identifier type="doi">10.18653/v1/W18-6479</identifier>
<location>
<url>https://aclanthology.org/W18-6479</url>
</location>
<part>
<date>2018-oct</date>
<extent unit="page">
<start>896</start>
<end>899</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T The JHU Parallel Corpus Filtering Systems for WMT 2018
%A Khayrallah, Huda
%A Xu, Hainan
%A Koehn, Philipp
%S Proceedings of the Third Conference on Machine Translation: Shared Task Papers
%D 2018
%8 oct
%I Association for Computational Linguistics
%C Belgium, Brussels
%F khayrallah-etal-2018-jhu
%X This work describes our submission to the WMT18 Parallel Corpus Filtering shared task. We use a slightly modified version of the Zipporah Corpus Filtering toolkit (Xu and Koehn, 2017), which computes an adequacy score and a fluency score on a sentence pair, and use a weighted sum of the scores as the selection criteria. This work differs from Zipporah in that we experiment with using the noisy corpus to be filtered to compute the combination weights, and thus avoids generating synthetic data as in standard Zipporah.
%R 10.18653/v1/W18-6479
%U https://aclanthology.org/W18-6479
%U https://doi.org/10.18653/v1/W18-6479
%P 896-899
Markdown (Informal)
[The JHU Parallel Corpus Filtering Systems for WMT 2018](https://aclanthology.org/W18-6479) (Khayrallah et al., 2018)
ACL