@inproceedings{koerner-koehn-2020-dual,
title = "Dual Conditional Cross Entropy Scores and {LASER} Similarity Scores for the {WMT}20 Parallel Corpus Filtering Shared Task",
author = "Koerner, Felicia and
Koehn, Philipp",
editor = {Barrault, Lo{\"\i}c and
Bojar, Ond{\v{r}}ej and
Bougares, Fethi and
Chatterjee, Rajen and
Costa-juss{\`a}, Marta R. and
Federmann, Christian and
Fishel, Mark and
Fraser, Alexander and
Graham, Yvette and
Guzman, Paco and
Haddow, Barry and
Huck, Matthias and
Yepes, Antonio Jimeno and
Koehn, Philipp and
Martins, Andr{\'e} and
Morishita, Makoto and
Monz, Christof and
Nagata, Masaaki and
Nakazawa, Toshiaki and
Negri, Matteo},
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-1.109",
pages = "966--971",
abstract = "This paper describes our submission to the WMT20 Parallel Corpus Filtering and Alignment for Low-Resource Conditions Shared Task. This year{'}s corpora are noisy Khmer-English and Pashto-English, with 58.3 million and 11.6 million words respectively (English token count). Our submission focuses on filtering Pashto-English, building on previously successful methods to produce two sets of scores: LASER{\_}LM, a combination of the LASER similarity scores provided in the shared task and perplexity scores from language models, and DCCEF{\_}DUP, dual conditional cross entropy scores combined with a duplication penalty. We improve slightly on the LASER similarity score and find that the provided clean data can successfully be supplemented with a subsampled set of the noisy data, effectively increasing the training data for the models used for dual conditional cross entropy scoring.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="koerner-koehn-2020-dual">
<titleInfo>
<title>Dual Conditional Cross Entropy Scores and LASER Similarity Scores for the WMT20 Parallel Corpus Filtering Shared Task</title>
</titleInfo>
<name type="personal">
<namePart type="given">Felicia</namePart>
<namePart type="family">Koerner</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>2020-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fifth Conference on Machine Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Loïc</namePart>
<namePart type="family">Barrault</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<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">Fethi</namePart>
<namePart type="family">Bougares</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">Marta</namePart>
<namePart type="given">R</namePart>
<namePart type="family">Costa-jussà</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">Alexander</namePart>
<namePart type="family">Fraser</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">Paco</namePart>
<namePart type="family">Guzman</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">André</namePart>
<namePart type="family">Martins</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Makoto</namePart>
<namePart type="family">Morishita</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">Masaaki</namePart>
<namePart type="family">Nagata</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Toshiaki</namePart>
<namePart type="family">Nakazawa</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>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper describes our submission to the WMT20 Parallel Corpus Filtering and Alignment for Low-Resource Conditions Shared Task. This year’s corpora are noisy Khmer-English and Pashto-English, with 58.3 million and 11.6 million words respectively (English token count). Our submission focuses on filtering Pashto-English, building on previously successful methods to produce two sets of scores: LASER_LM, a combination of the LASER similarity scores provided in the shared task and perplexity scores from language models, and DCCEF_DUP, dual conditional cross entropy scores combined with a duplication penalty. We improve slightly on the LASER similarity score and find that the provided clean data can successfully be supplemented with a subsampled set of the noisy data, effectively increasing the training data for the models used for dual conditional cross entropy scoring.</abstract>
<identifier type="citekey">koerner-koehn-2020-dual</identifier>
<location>
<url>https://aclanthology.org/2020.wmt-1.109</url>
</location>
<part>
<date>2020-11</date>
<extent unit="page">
<start>966</start>
<end>971</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Dual Conditional Cross Entropy Scores and LASER Similarity Scores for the WMT20 Parallel Corpus Filtering Shared Task
%A Koerner, Felicia
%A Koehn, Philipp
%Y Barrault, Loïc
%Y Bojar, Ondřej
%Y Bougares, Fethi
%Y Chatterjee, Rajen
%Y Costa-jussà, Marta R.
%Y Federmann, Christian
%Y Fishel, Mark
%Y Fraser, Alexander
%Y Graham, Yvette
%Y Guzman, Paco
%Y Haddow, Barry
%Y Huck, Matthias
%Y Yepes, Antonio Jimeno
%Y Koehn, Philipp
%Y Martins, André
%Y Morishita, Makoto
%Y Monz, Christof
%Y Nagata, Masaaki
%Y Nakazawa, Toshiaki
%Y Negri, Matteo
%S Proceedings of the Fifth Conference on Machine Translation
%D 2020
%8 November
%I Association for Computational Linguistics
%C Online
%F koerner-koehn-2020-dual
%X This paper describes our submission to the WMT20 Parallel Corpus Filtering and Alignment for Low-Resource Conditions Shared Task. This year’s corpora are noisy Khmer-English and Pashto-English, with 58.3 million and 11.6 million words respectively (English token count). Our submission focuses on filtering Pashto-English, building on previously successful methods to produce two sets of scores: LASER_LM, a combination of the LASER similarity scores provided in the shared task and perplexity scores from language models, and DCCEF_DUP, dual conditional cross entropy scores combined with a duplication penalty. We improve slightly on the LASER similarity score and find that the provided clean data can successfully be supplemented with a subsampled set of the noisy data, effectively increasing the training data for the models used for dual conditional cross entropy scoring.
%U https://aclanthology.org/2020.wmt-1.109
%P 966-971
Markdown (Informal)
[Dual Conditional Cross Entropy Scores and LASER Similarity Scores for the WMT20 Parallel Corpus Filtering Shared Task](https://aclanthology.org/2020.wmt-1.109) (Koerner & Koehn, WMT 2020)
ACL