@inproceedings{roussis-EtAl:2022:LREC1,
title = {Constructing Parallel Corpora from COVID-19 News using MediSys Metadata},
author = {Dimitrios Roussis and Vassilis Papavassiliou and Sokratis Sofianopoulos and Prokopidis Prokopis and Stelios Piperidis},
url = {http://www.lrec-conf.org/proceedings/lrec2022/pdf/2022.lrec-1.115.pdf},
year = {2022},
date = {2022-06-01},
urldate = {2022-06-01},
booktitle = {Proceedings of the Language Resources and Evaluation Conference},
pages = {1068-1072},
publisher = {European Language Resources Association},
address = {Marseille, France},
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.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}