@inproceedings{roussis-etal-2022-constructing,
title = "Constructing Parallel Corpora from {COVID}-19 News using {M}edi{S}ys Metadata",
author = "Roussis, Dimitrios and
Papavassiliou, Vassilis and
Sofianopoulos, Sokratis and
Prokopidis, Prokopis and
Piperidis, Stelios",
editor = "Calzolari, Nicoletta and
B{\'e}chet, Fr{\'e}d{\'e}ric and
Blache, Philippe and
Choukri, Khalid and
Cieri, Christopher and
Declerck, Thierry and
Goggi, Sara and
Isahara, Hitoshi and
Maegaard, Bente and
Mariani, Joseph and
Mazo, H{\'e}l{\`e}ne and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Thirteenth Language Resources and Evaluation Conference",
month = jun,
year = "2022",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2022.lrec-1.115",
pages = "1068--1072",
abstract = "This paper presents a collection of parallel corpora generated by exploiting the COVID-19 related dataset of metadata created with the Europe Media Monitor (EMM) / Medical Information System (MediSys) processing chain of news articles. We describe how we constructed comparable monolingual corpora of news articles related to the current pandemic and used them to mine about 11.2 million segment alignments in 26 EN-X language pairs, covering most official EU languages plus Albanian, Arabic, Icelandic, Macedonian, and Norwegian. Subsets of this collection have been used in shared tasks (e.g. Multilingual Semantic Search, Machine Translation) aimed at accelerating the creation of resources and tools needed to facilitate access to information in the COVID-19 emergency situation.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="roussis-etal-2022-constructing">
<titleInfo>
<title>Constructing Parallel Corpora from COVID-19 News using MediSys Metadata</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dimitrios</namePart>
<namePart type="family">Roussis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vassilis</namePart>
<namePart type="family">Papavassiliou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sokratis</namePart>
<namePart type="family">Sofianopoulos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Prokopis</namePart>
<namePart type="family">Prokopidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Thirteenth Language Resources and Evaluation Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Frédéric</namePart>
<namePart type="family">Béchet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philippe</namePart>
<namePart type="family">Blache</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalid</namePart>
<namePart type="family">Choukri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christopher</namePart>
<namePart type="family">Cieri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thierry</namePart>
<namePart type="family">Declerck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Goggi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hitoshi</namePart>
<namePart type="family">Isahara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bente</namePart>
<namePart type="family">Maegaard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joseph</namePart>
<namePart type="family">Mariani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hélène</namePart>
<namePart type="family">Mazo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Odijk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper presents a collection of parallel corpora generated by exploiting the COVID-19 related dataset of metadata created with the Europe Media Monitor (EMM) / Medical Information System (MediSys) processing chain of news articles. We describe how we constructed comparable monolingual corpora of news articles related to the current pandemic and used them to mine about 11.2 million segment alignments in 26 EN-X language pairs, covering most official EU languages plus Albanian, Arabic, Icelandic, Macedonian, and Norwegian. Subsets of this collection have been used in shared tasks (e.g. Multilingual Semantic Search, Machine Translation) aimed at accelerating the creation of resources and tools needed to facilitate access to information in the COVID-19 emergency situation.</abstract>
<identifier type="citekey">roussis-etal-2022-constructing</identifier>
<location>
<url>https://aclanthology.org/2022.lrec-1.115</url>
</location>
<part>
<date>2022-06</date>
<extent unit="page">
<start>1068</start>
<end>1072</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Constructing Parallel Corpora from COVID-19 News using MediSys Metadata
%A Roussis, Dimitrios
%A Papavassiliou, Vassilis
%A Sofianopoulos, Sokratis
%A Prokopidis, Prokopis
%A Piperidis, Stelios
%Y Calzolari, Nicoletta
%Y Béchet, Frédéric
%Y Blache, Philippe
%Y Choukri, Khalid
%Y Cieri, Christopher
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Isahara, Hitoshi
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Hélène
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Thirteenth Language Resources and Evaluation Conference
%D 2022
%8 June
%I European Language Resources Association
%C Marseille, France
%F roussis-etal-2022-constructing
%X This paper presents a collection of parallel corpora generated by exploiting the COVID-19 related dataset of metadata created with the Europe Media Monitor (EMM) / Medical Information System (MediSys) processing chain of news articles. We describe how we constructed comparable monolingual corpora of news articles related to the current pandemic and used them to mine about 11.2 million segment alignments in 26 EN-X language pairs, covering most official EU languages plus Albanian, Arabic, Icelandic, Macedonian, and Norwegian. Subsets of this collection have been used in shared tasks (e.g. Multilingual Semantic Search, Machine Translation) aimed at accelerating the creation of resources and tools needed to facilitate access to information in the COVID-19 emergency situation.
%U https://aclanthology.org/2022.lrec-1.115
%P 1068-1072
Markdown (Informal)
[Constructing Parallel Corpora from COVID-19 News using MediSys Metadata](https://aclanthology.org/2022.lrec-1.115) (Roussis et al., LREC 2022)
ACL