@inproceedings{gonzalez-alvarez-2023-filtering,
title = "Filtering and rescoring the {CCM}atrix corpus for Neural Machine Translation training",
author = "Gonz{\'a}lez, Antoni Oliver and
{\'A}lvarez, Sergi",
editor = "Nurminen, Mary and
Brenner, Judith and
Koponen, Maarit and
Latomaa, Sirkku and
Mikhailov, Mikhail and
Schierl, Frederike and
Ranasinghe, Tharindu and
Vanmassenhove, Eva and
Vidal, Sergi Alvarez and
Aranberri, Nora and
Nunziatini, Mara and
Escart{\'\i}n, Carla Parra and
Forcada, Mikel and
Popovic, Maja and
Scarton, Carolina and
Moniz, Helena",
booktitle = "Proceedings of the 24th Annual Conference of the European Association for Machine Translation",
month = jun,
year = "2023",
address = "Tampere, Finland",
publisher = "European Association for Machine Translation",
url = "https://aclanthology.org/2023.eamt-1.5",
pages = "39--45",
abstract = "There are several parallel corpora available for many language pairs, such as CCMatrix, built from mass downloads of web content and automatic detection of segments in one language and the translation equivalent in another. These techniques can produce large parallel corpora, but of questionable quality. In many cases, the segments are not in the required languages, or if they are, they are not translation equivalents. In this article, we present an algorithm for filtering out the segments in languages other than the required ones and re-scoring the segments using SBERT. A use case on the Spanish-Asturian and Spanish-Catalan CCMatrix corpus is presented.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="gonzalez-alvarez-2023-filtering">
<titleInfo>
<title>Filtering and rescoring the CCMatrix corpus for Neural Machine Translation training</title>
</titleInfo>
<name type="personal">
<namePart type="given">Antoni</namePart>
<namePart type="given">Oliver</namePart>
<namePart type="family">González</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sergi</namePart>
<namePart type="family">Álvarez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 24th Annual Conference of the European Association for Machine Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mary</namePart>
<namePart type="family">Nurminen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Judith</namePart>
<namePart type="family">Brenner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maarit</namePart>
<namePart type="family">Koponen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sirkku</namePart>
<namePart type="family">Latomaa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mikhail</namePart>
<namePart type="family">Mikhailov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Frederike</namePart>
<namePart type="family">Schierl</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tharindu</namePart>
<namePart type="family">Ranasinghe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eva</namePart>
<namePart type="family">Vanmassenhove</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sergi</namePart>
<namePart type="given">Alvarez</namePart>
<namePart type="family">Vidal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nora</namePart>
<namePart type="family">Aranberri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mara</namePart>
<namePart type="family">Nunziatini</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Carla</namePart>
<namePart type="given">Parra</namePart>
<namePart type="family">Escartín</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mikel</namePart>
<namePart type="family">Forcada</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maja</namePart>
<namePart type="family">Popovic</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Carolina</namePart>
<namePart type="family">Scarton</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Helena</namePart>
<namePart type="family">Moniz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Association for Machine Translation</publisher>
<place>
<placeTerm type="text">Tampere, Finland</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>There are several parallel corpora available for many language pairs, such as CCMatrix, built from mass downloads of web content and automatic detection of segments in one language and the translation equivalent in another. These techniques can produce large parallel corpora, but of questionable quality. In many cases, the segments are not in the required languages, or if they are, they are not translation equivalents. In this article, we present an algorithm for filtering out the segments in languages other than the required ones and re-scoring the segments using SBERT. A use case on the Spanish-Asturian and Spanish-Catalan CCMatrix corpus is presented.</abstract>
<identifier type="citekey">gonzalez-alvarez-2023-filtering</identifier>
<location>
<url>https://aclanthology.org/2023.eamt-1.5</url>
</location>
<part>
<date>2023-06</date>
<extent unit="page">
<start>39</start>
<end>45</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Filtering and rescoring the CCMatrix corpus for Neural Machine Translation training
%A González, Antoni Oliver
%A Álvarez, Sergi
%Y Nurminen, Mary
%Y Brenner, Judith
%Y Koponen, Maarit
%Y Latomaa, Sirkku
%Y Mikhailov, Mikhail
%Y Schierl, Frederike
%Y Ranasinghe, Tharindu
%Y Vanmassenhove, Eva
%Y Vidal, Sergi Alvarez
%Y Aranberri, Nora
%Y Nunziatini, Mara
%Y Escartín, Carla Parra
%Y Forcada, Mikel
%Y Popovic, Maja
%Y Scarton, Carolina
%Y Moniz, Helena
%S Proceedings of the 24th Annual Conference of the European Association for Machine Translation
%D 2023
%8 June
%I European Association for Machine Translation
%C Tampere, Finland
%F gonzalez-alvarez-2023-filtering
%X There are several parallel corpora available for many language pairs, such as CCMatrix, built from mass downloads of web content and automatic detection of segments in one language and the translation equivalent in another. These techniques can produce large parallel corpora, but of questionable quality. In many cases, the segments are not in the required languages, or if they are, they are not translation equivalents. In this article, we present an algorithm for filtering out the segments in languages other than the required ones and re-scoring the segments using SBERT. A use case on the Spanish-Asturian and Spanish-Catalan CCMatrix corpus is presented.
%U https://aclanthology.org/2023.eamt-1.5
%P 39-45
Markdown (Informal)
[Filtering and rescoring the CCMatrix corpus for Neural Machine Translation training](https://aclanthology.org/2023.eamt-1.5) (González & Álvarez, EAMT 2023)
ACL