@inproceedings{koehn-etal-2020-findings,
title = "Findings of the {WMT} 2020 Shared Task on Parallel Corpus Filtering and Alignment",
author = "Koehn, Philipp and
Chaudhary, Vishrav and
El-Kishky, Ahmed and
Goyal, Naman and
Chen, Peng-Jen and
Guzm{\'a}n, Francisco",
booktitle = "Proceedings of the Fifth Conference on Machine Translation",
month = nov,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.wmt-1.78",
pages = "726--742",
abstract = "Following two preceding WMT Shared Task on Parallel Corpus Filtering (Koehn et al., 2018, 2019), we posed again the challenge of assigning sentence-level quality scores for very noisy corpora of sentence pairs crawled from the web, with the goal of sub-selecting the highest-quality data to be used to train ma-chine translation systems. This year, the task tackled the low resource condition of Pashto{--}English and Khmer{--}English and also included the challenge of sentence alignment from document pairs.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="koehn-etal-2020-findings">
<titleInfo>
<title>Findings of the WMT 2020 Shared Task on Parallel Corpus Filtering and Alignment</title>
</titleInfo>
<name type="personal">
<namePart type="given">Philipp</namePart>
<namePart type="family">Koehn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vishrav</namePart>
<namePart type="family">Chaudhary</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ahmed</namePart>
<namePart type="family">El-Kishky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Naman</namePart>
<namePart type="family">Goyal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Peng-Jen</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Francisco</namePart>
<namePart type="family">Guzmán</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-nov</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fifth Conference on Machine Translation</title>
</titleInfo>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Following two preceding WMT Shared Task on Parallel Corpus Filtering (Koehn et al., 2018, 2019), we posed again the challenge of assigning sentence-level quality scores for very noisy corpora of sentence pairs crawled from the web, with the goal of sub-selecting the highest-quality data to be used to train ma-chine translation systems. This year, the task tackled the low resource condition of Pashto–English and Khmer–English and also included the challenge of sentence alignment from document pairs.</abstract>
<identifier type="citekey">koehn-etal-2020-findings</identifier>
<location>
<url>https://aclanthology.org/2020.wmt-1.78</url>
</location>
<part>
<date>2020-nov</date>
<extent unit="page">
<start>726</start>
<end>742</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Findings of the WMT 2020 Shared Task on Parallel Corpus Filtering and Alignment
%A Koehn, Philipp
%A Chaudhary, Vishrav
%A El-Kishky, Ahmed
%A Goyal, Naman
%A Chen, Peng-Jen
%A Guzmán, Francisco
%S Proceedings of the Fifth Conference on Machine Translation
%D 2020
%8 nov
%I Association for Computational Linguistics
%C Online
%F koehn-etal-2020-findings
%X Following two preceding WMT Shared Task on Parallel Corpus Filtering (Koehn et al., 2018, 2019), we posed again the challenge of assigning sentence-level quality scores for very noisy corpora of sentence pairs crawled from the web, with the goal of sub-selecting the highest-quality data to be used to train ma-chine translation systems. This year, the task tackled the low resource condition of Pashto–English and Khmer–English and also included the challenge of sentence alignment from document pairs.
%U https://aclanthology.org/2020.wmt-1.78
%P 726-742
Markdown (Informal)
[Findings of the WMT 2020 Shared Task on Parallel Corpus Filtering and Alignment](https://aclanthology.org/2020.wmt-1.78) (Koehn et al., WMT 2020)
ACL