@inproceedings{ash-etal-2018-speechmatics,
title = "The Speechmatics Parallel Corpus Filtering System for {WMT}18",
author = "Ash, Tom and
Francis, Remi and
Williams, Will",
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/W18-6472",
doi = "10.18653/v1/W18-6472",
pages = "853--859",
abstract = "Our entry to the parallel corpus filtering task uses a two-step strategy. The first step uses a series of pragmatic hard {`}rules{'} to remove the worst example sentences. This first step reduces the effective corpus size down from the initial 1 billion to 160 million tokens. The second step uses four different heuristics weighted to produce a score that is then used for further filtering down to 100 or 10 million tokens. Our final system produces competitive results without requiring excessive fine tuning to the exact task or language pair. The first step in isolation provides a very fast filter that gives most of the gains of the final system.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ash-etal-2018-speechmatics">
<titleInfo>
<title>The Speechmatics Parallel Corpus Filtering System for WMT18</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tom</namePart>
<namePart type="family">Ash</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Remi</namePart>
<namePart type="family">Francis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Will</namePart>
<namePart type="family">Williams</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>Our entry to the parallel corpus filtering task uses a two-step strategy. The first step uses a series of pragmatic hard ‘rules’ to remove the worst example sentences. This first step reduces the effective corpus size down from the initial 1 billion to 160 million tokens. The second step uses four different heuristics weighted to produce a score that is then used for further filtering down to 100 or 10 million tokens. Our final system produces competitive results without requiring excessive fine tuning to the exact task or language pair. The first step in isolation provides a very fast filter that gives most of the gains of the final system.</abstract>
<identifier type="citekey">ash-etal-2018-speechmatics</identifier>
<identifier type="doi">10.18653/v1/W18-6472</identifier>
<location>
<url>https://aclanthology.org/W18-6472</url>
</location>
<part>
<date>2018-oct</date>
<extent unit="page">
<start>853</start>
<end>859</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T The Speechmatics Parallel Corpus Filtering System for WMT18
%A Ash, Tom
%A Francis, Remi
%A Williams, Will
%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 ash-etal-2018-speechmatics
%X Our entry to the parallel corpus filtering task uses a two-step strategy. The first step uses a series of pragmatic hard ‘rules’ to remove the worst example sentences. This first step reduces the effective corpus size down from the initial 1 billion to 160 million tokens. The second step uses four different heuristics weighted to produce a score that is then used for further filtering down to 100 or 10 million tokens. Our final system produces competitive results without requiring excessive fine tuning to the exact task or language pair. The first step in isolation provides a very fast filter that gives most of the gains of the final system.
%R 10.18653/v1/W18-6472
%U https://aclanthology.org/W18-6472
%U https://doi.org/10.18653/v1/W18-6472
%P 853-859
Markdown (Informal)
[The Speechmatics Parallel Corpus Filtering System for WMT18](https://aclanthology.org/W18-6472) (Ash et al., 2018)
ACL