@inproceedings{van-esch-etal-2022-writing,
title = "Writing System and Speaker Metadata for 2,800+ Language Varieties",
author = "van Esch, Daan and
Lucassen, Tamar and
Ruder, Sebastian and
Caswell, Isaac and
Rivera, Clara",
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-1.538/",
pages = "5035--5046",
abstract = "We describe an open-source dataset providing metadata for about 2,800 language varieties used in the world today. Specifically, the dataset provides the attested writing system(s) for each of these 2,800+ varieties, as well as an estimated speaker count for each variety. This dataset was developed through internal research and has been used for analyses around language technologies. This is the largest publicly-available, machine-readable resource with writing system and speaker information for the world`s languages. We analyze the distribution of languages and writing systems in our data and compare it to their representation in current NLP. We hope the availability of this data will catalyze research in under-represented languages."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="van-esch-etal-2022-writing">
<titleInfo>
<title>Writing System and Speaker Metadata for 2,800+ Language Varieties</title>
</titleInfo>
<name type="personal">
<namePart type="given">Daan</namePart>
<namePart type="family">van Esch</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tamar</namePart>
<namePart type="family">Lucassen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sebastian</namePart>
<namePart type="family">Ruder</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Isaac</namePart>
<namePart type="family">Caswell</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Clara</namePart>
<namePart type="family">Rivera</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>We describe an open-source dataset providing metadata for about 2,800 language varieties used in the world today. Specifically, the dataset provides the attested writing system(s) for each of these 2,800+ varieties, as well as an estimated speaker count for each variety. This dataset was developed through internal research and has been used for analyses around language technologies. This is the largest publicly-available, machine-readable resource with writing system and speaker information for the world‘s languages. We analyze the distribution of languages and writing systems in our data and compare it to their representation in current NLP. We hope the availability of this data will catalyze research in under-represented languages.</abstract>
<identifier type="citekey">van-esch-etal-2022-writing</identifier>
<location>
<url>https://aclanthology.org/2022.lrec-1.538/</url>
</location>
<part>
<date>2022-06</date>
<extent unit="page">
<start>5035</start>
<end>5046</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Writing System and Speaker Metadata for 2,800+ Language Varieties
%A van Esch, Daan
%A Lucassen, Tamar
%A Ruder, Sebastian
%A Caswell, Isaac
%A Rivera, Clara
%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 van-esch-etal-2022-writing
%X We describe an open-source dataset providing metadata for about 2,800 language varieties used in the world today. Specifically, the dataset provides the attested writing system(s) for each of these 2,800+ varieties, as well as an estimated speaker count for each variety. This dataset was developed through internal research and has been used for analyses around language technologies. This is the largest publicly-available, machine-readable resource with writing system and speaker information for the world‘s languages. We analyze the distribution of languages and writing systems in our data and compare it to their representation in current NLP. We hope the availability of this data will catalyze research in under-represented languages.
%U https://aclanthology.org/2022.lrec-1.538/
%P 5035-5046
Markdown (Informal)
[Writing System and Speaker Metadata for 2,800+ Language Varieties](https://aclanthology.org/2022.lrec-1.538/) (van Esch et al., LREC 2022)
ACL