@inproceedings{ashida-etal-2022-covid,
title = "{COVID}-19 Mythbusters in World Languages",
author = "Ashida, Mana and
Kim, Jin-Dong and
Lee, Seunghun",
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-1.326",
pages = "3048--3055",
abstract = "This paper introduces a multi-lingual database containing translated texts of COVID-19 mythbusters. The database has translations into 115 languages as well as the original English texts, of which the original texts are published by World Health Organization (WHO). This paper then presents preliminary analyses on latin-alphabet-based texts to see the potential of the database as a resource for multilingual linguistic analyses. The analyses on latin-alphabet-based texts gave interesting insights into the resource. While the amount of translated texts in each language was small, character bi-grams with normalization (lowercasing and removal of diacritics) was turned out to be an effective proxy for measuring the similarity of the languages, and the affinity ranking of language pairs could be obtained. Additionally, the hierarchical clustering analysis is performed using the character bigram overlap ratio of every possible pair of languages. The result shows the cluster of Germanic languages, Romance languages, and Southern Bantu languages. In sum, the multilingual database not only offers fixed set of materials in numerous languages, but also serves as a preliminary tool to identify the language family using text-based similarity measure of bigram overlap ratio.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ashida-etal-2022-covid">
<titleInfo>
<title>COVID-19 Mythbusters in World Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mana</namePart>
<namePart type="family">Ashida</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jin-Dong</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Seunghun</namePart>
<namePart type="family">Lee</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 introduces a multi-lingual database containing translated texts of COVID-19 mythbusters. The database has translations into 115 languages as well as the original English texts, of which the original texts are published by World Health Organization (WHO). This paper then presents preliminary analyses on latin-alphabet-based texts to see the potential of the database as a resource for multilingual linguistic analyses. The analyses on latin-alphabet-based texts gave interesting insights into the resource. While the amount of translated texts in each language was small, character bi-grams with normalization (lowercasing and removal of diacritics) was turned out to be an effective proxy for measuring the similarity of the languages, and the affinity ranking of language pairs could be obtained. Additionally, the hierarchical clustering analysis is performed using the character bigram overlap ratio of every possible pair of languages. The result shows the cluster of Germanic languages, Romance languages, and Southern Bantu languages. In sum, the multilingual database not only offers fixed set of materials in numerous languages, but also serves as a preliminary tool to identify the language family using text-based similarity measure of bigram overlap ratio.</abstract>
<identifier type="citekey">ashida-etal-2022-covid</identifier>
<location>
<url>https://aclanthology.org/2022.lrec-1.326</url>
</location>
<part>
<date>2022-06</date>
<extent unit="page">
<start>3048</start>
<end>3055</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T COVID-19 Mythbusters in World Languages
%A Ashida, Mana
%A Kim, Jin-Dong
%A Lee, Seunghun
%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 ashida-etal-2022-covid
%X This paper introduces a multi-lingual database containing translated texts of COVID-19 mythbusters. The database has translations into 115 languages as well as the original English texts, of which the original texts are published by World Health Organization (WHO). This paper then presents preliminary analyses on latin-alphabet-based texts to see the potential of the database as a resource for multilingual linguistic analyses. The analyses on latin-alphabet-based texts gave interesting insights into the resource. While the amount of translated texts in each language was small, character bi-grams with normalization (lowercasing and removal of diacritics) was turned out to be an effective proxy for measuring the similarity of the languages, and the affinity ranking of language pairs could be obtained. Additionally, the hierarchical clustering analysis is performed using the character bigram overlap ratio of every possible pair of languages. The result shows the cluster of Germanic languages, Romance languages, and Southern Bantu languages. In sum, the multilingual database not only offers fixed set of materials in numerous languages, but also serves as a preliminary tool to identify the language family using text-based similarity measure of bigram overlap ratio.
%U https://aclanthology.org/2022.lrec-1.326
%P 3048-3055
Markdown (Informal)
[COVID-19 Mythbusters in World Languages](https://aclanthology.org/2022.lrec-1.326) (Ashida et al., LREC 2022)
ACL
- Mana Ashida, Jin-Dong Kim, and Seunghun Lee. 2022. COVID-19 Mythbusters in World Languages. In Proceedings of the Thirteenth Language Resources and Evaluation Conference, pages 3048–3055, Marseille, France. European Language Resources Association.