@inproceedings{pinnis-2018-tildes,
title = "Tilde{'}s Parallel Corpus Filtering Methods for {WMT} 2018",
author = "Pinnis, M{\=a}rcis",
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/W18-6486",
doi = "10.18653/v1/W18-6486",
pages = "939--945",
abstract = "The paper describes parallel corpus filtering methods that allow reducing noise of noisy {``}parallel{''} corpora from a level where the corpora are not usable for neural machine translation training (i.e., the resulting systems fail to achieve reasonable translation quality; well below 10 BLEU points) up to a level where the trained systems show decent (over 20 BLEU points on a 10 million word dataset and up to 30 BLEU points on a 100 million word dataset). The paper also documents Tilde{'}s submissions to the WMT 2018 shared task on parallel corpus filtering.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="pinnis-2018-tildes">
<titleInfo>
<title>Tilde’s Parallel Corpus Filtering Methods for WMT 2018</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mārcis</namePart>
<namePart type="family">Pinnis</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>The paper describes parallel corpus filtering methods that allow reducing noise of noisy “parallel” corpora from a level where the corpora are not usable for neural machine translation training (i.e., the resulting systems fail to achieve reasonable translation quality; well below 10 BLEU points) up to a level where the trained systems show decent (over 20 BLEU points on a 10 million word dataset and up to 30 BLEU points on a 100 million word dataset). The paper also documents Tilde’s submissions to the WMT 2018 shared task on parallel corpus filtering.</abstract>
<identifier type="citekey">pinnis-2018-tildes</identifier>
<identifier type="doi">10.18653/v1/W18-6486</identifier>
<location>
<url>https://aclanthology.org/W18-6486</url>
</location>
<part>
<date>2018-oct</date>
<extent unit="page">
<start>939</start>
<end>945</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Tilde’s Parallel Corpus Filtering Methods for WMT 2018
%A Pinnis, Mārcis
%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 pinnis-2018-tildes
%X The paper describes parallel corpus filtering methods that allow reducing noise of noisy “parallel” corpora from a level where the corpora are not usable for neural machine translation training (i.e., the resulting systems fail to achieve reasonable translation quality; well below 10 BLEU points) up to a level where the trained systems show decent (over 20 BLEU points on a 10 million word dataset and up to 30 BLEU points on a 100 million word dataset). The paper also documents Tilde’s submissions to the WMT 2018 shared task on parallel corpus filtering.
%R 10.18653/v1/W18-6486
%U https://aclanthology.org/W18-6486
%U https://doi.org/10.18653/v1/W18-6486
%P 939-945
Markdown (Informal)
[Tilde’s Parallel Corpus Filtering Methods for WMT 2018](https://aclanthology.org/W18-6486) (Pinnis, 2018)
ACL