@inproceedings{moran-etal-2022-teddi,
title = "{T}e{DD}i Sample: Text Data Diversity Sample for Language Comparison and Multilingual {NLP}",
author = "Moran, Steven and
Bentz, Christian and
Gutierrez-Vasques, Ximena and
Pelloni, Olga and
Samardzic, Tanja",
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-1.123/",
pages = "1150--1158",
abstract = "We present the TeDDi sample, a diversity sample of text data for language comparison and multilingual Natural Language Processing. The TeDDi sample currently features 89 languages based on the typological diversity sample in the World Atlas of Language Structures. It consists of more than 20k texts and is accompanied by open-source corpus processing tools. The aim of TeDDi is to facilitate text-based quantitative analysis of linguistic diversity. We describe in detail the TeDDi sample, how it was created, data availability, and its added value through for NLP and linguistic research."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="moran-etal-2022-teddi">
<titleInfo>
<title>TeDDi Sample: Text Data Diversity Sample for Language Comparison and Multilingual NLP</title>
</titleInfo>
<name type="personal">
<namePart type="given">Steven</namePart>
<namePart type="family">Moran</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christian</namePart>
<namePart type="family">Bentz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ximena</namePart>
<namePart type="family">Gutierrez-Vasques</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Olga</namePart>
<namePart type="family">Pelloni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tanja</namePart>
<namePart type="family">Samardzic</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 present the TeDDi sample, a diversity sample of text data for language comparison and multilingual Natural Language Processing. The TeDDi sample currently features 89 languages based on the typological diversity sample in the World Atlas of Language Structures. It consists of more than 20k texts and is accompanied by open-source corpus processing tools. The aim of TeDDi is to facilitate text-based quantitative analysis of linguistic diversity. We describe in detail the TeDDi sample, how it was created, data availability, and its added value through for NLP and linguistic research.</abstract>
<identifier type="citekey">moran-etal-2022-teddi</identifier>
<location>
<url>https://aclanthology.org/2022.lrec-1.123/</url>
</location>
<part>
<date>2022-06</date>
<extent unit="page">
<start>1150</start>
<end>1158</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T TeDDi Sample: Text Data Diversity Sample for Language Comparison and Multilingual NLP
%A Moran, Steven
%A Bentz, Christian
%A Gutierrez-Vasques, Ximena
%A Pelloni, Olga
%A Samardzic, Tanja
%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 moran-etal-2022-teddi
%X We present the TeDDi sample, a diversity sample of text data for language comparison and multilingual Natural Language Processing. The TeDDi sample currently features 89 languages based on the typological diversity sample in the World Atlas of Language Structures. It consists of more than 20k texts and is accompanied by open-source corpus processing tools. The aim of TeDDi is to facilitate text-based quantitative analysis of linguistic diversity. We describe in detail the TeDDi sample, how it was created, data availability, and its added value through for NLP and linguistic research.
%U https://aclanthology.org/2022.lrec-1.123/
%P 1150-1158
Markdown (Informal)
[TeDDi Sample: Text Data Diversity Sample for Language Comparison and Multilingual NLP](https://aclanthology.org/2022.lrec-1.123/) (Moran et al., LREC 2022)
ACL