@inproceedings{elnokrashy-etal-2020-score,
title = "Score Combination for Improved Parallel Corpus Filtering for Low Resource Conditions",
author = "ElNokrashy, Muhammad and
Hendy, Amr and
Abdelghaffar, Mohamed and
Afify, Mohamed and
Tawfik, Ahmed and
Hassan Awadalla, Hany",
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-1.106",
pages = "947--951",
abstract = "This paper presents the description of our submission to WMT20 sentence filtering task. We combine scores from custom LASER built for each source language, a classifier built to distinguish positive and negative pairs and the original scores provided with the task. For the mBART setup, provided by the organizers, our method shows 7{\%} and 5{\%} relative improvement, over the baseline, in sacreBLEU score on the test set for Pashto and Khmer respectively.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="elnokrashy-etal-2020-score">
<titleInfo>
<title>Score Combination for Improved Parallel Corpus Filtering for Low Resource Conditions</title>
</titleInfo>
<name type="personal">
<namePart type="given">Muhammad</namePart>
<namePart type="family">ElNokrashy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Amr</namePart>
<namePart type="family">Hendy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohamed</namePart>
<namePart type="family">Abdelghaffar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohamed</namePart>
<namePart type="family">Afify</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ahmed</namePart>
<namePart type="family">Tawfik</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hany</namePart>
<namePart type="family">Hassan Awadalla</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>This paper presents the description of our submission to WMT20 sentence filtering task. We combine scores from custom LASER built for each source language, a classifier built to distinguish positive and negative pairs and the original scores provided with the task. For the mBART setup, provided by the organizers, our method shows 7% and 5% relative improvement, over the baseline, in sacreBLEU score on the test set for Pashto and Khmer respectively.</abstract>
<identifier type="citekey">elnokrashy-etal-2020-score</identifier>
<location>
<url>https://aclanthology.org/2020.wmt-1.106</url>
</location>
<part>
<date>2020-nov</date>
<extent unit="page">
<start>947</start>
<end>951</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Score Combination for Improved Parallel Corpus Filtering for Low Resource Conditions
%A ElNokrashy, Muhammad
%A Hendy, Amr
%A Abdelghaffar, Mohamed
%A Afify, Mohamed
%A Tawfik, Ahmed
%A Hassan Awadalla, Hany
%S Proceedings of the Fifth Conference on Machine Translation
%D 2020
%8 nov
%I Association for Computational Linguistics
%C Online
%F elnokrashy-etal-2020-score
%X This paper presents the description of our submission to WMT20 sentence filtering task. We combine scores from custom LASER built for each source language, a classifier built to distinguish positive and negative pairs and the original scores provided with the task. For the mBART setup, provided by the organizers, our method shows 7% and 5% relative improvement, over the baseline, in sacreBLEU score on the test set for Pashto and Khmer respectively.
%U https://aclanthology.org/2020.wmt-1.106
%P 947-951
Markdown (Informal)
[Score Combination for Improved Parallel Corpus Filtering for Low Resource Conditions](https://aclanthology.org/2020.wmt-1.106) (ElNokrashy et al., WMT 2020)
ACL