@inproceedings{dunn-adams-2020-geographically,
title = "Geographically-Balanced {G}igaword Corpora for 50 Language Varieties",
author = "Dunn, Jonathan and
Adams, Ben",
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
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Twelfth Language Resources and Evaluation Conference",
month = may,
year = "2020",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2020.lrec-1.308",
pages = "2528--2536",
abstract = "While text corpora have been steadily increasing in overall size, even very large corpora are not designed to represent global population demographics. For example, recent work has shown that existing English gigaword corpora over-represent inner-circle varieties from the US and the UK. To correct implicit geographic and demographic biases, this paper uses country-level population demographics to guide the construction of gigaword web corpora. The resulting corpora explicitly match the ground-truth geographic distribution of each language, thus equally representing language users from around the world. This is important because it ensures that speakers of under-resourced language varieties (i.e., Indian English or Algerian French) are represented, both in the corpora themselves but also in derivative resources like word embeddings.",
language = "English",
ISBN = "979-10-95546-34-4",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="dunn-adams-2020-geographically">
<titleInfo>
<title>Geographically-Balanced Gigaword Corpora for 50 Language Varieties</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jonathan</namePart>
<namePart type="family">Dunn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ben</namePart>
<namePart type="family">Adams</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<language>
<languageTerm type="text">English</languageTerm>
<languageTerm type="code" authority="iso639-2b">eng</languageTerm>
</language>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Twelfth 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">Asuncion</namePart>
<namePart type="family">Moreno</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>
<identifier type="isbn">979-10-95546-34-4</identifier>
</relatedItem>
<abstract>While text corpora have been steadily increasing in overall size, even very large corpora are not designed to represent global population demographics. For example, recent work has shown that existing English gigaword corpora over-represent inner-circle varieties from the US and the UK. To correct implicit geographic and demographic biases, this paper uses country-level population demographics to guide the construction of gigaword web corpora. The resulting corpora explicitly match the ground-truth geographic distribution of each language, thus equally representing language users from around the world. This is important because it ensures that speakers of under-resourced language varieties (i.e., Indian English or Algerian French) are represented, both in the corpora themselves but also in derivative resources like word embeddings.</abstract>
<identifier type="citekey">dunn-adams-2020-geographically</identifier>
<location>
<url>https://aclanthology.org/2020.lrec-1.308</url>
</location>
<part>
<date>2020-05</date>
<extent unit="page">
<start>2528</start>
<end>2536</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Geographically-Balanced Gigaword Corpora for 50 Language Varieties
%A Dunn, Jonathan
%A Adams, Ben
%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 Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Twelfth Language Resources and Evaluation Conference
%D 2020
%8 May
%I European Language Resources Association
%C Marseille, France
%@ 979-10-95546-34-4
%G English
%F dunn-adams-2020-geographically
%X While text corpora have been steadily increasing in overall size, even very large corpora are not designed to represent global population demographics. For example, recent work has shown that existing English gigaword corpora over-represent inner-circle varieties from the US and the UK. To correct implicit geographic and demographic biases, this paper uses country-level population demographics to guide the construction of gigaword web corpora. The resulting corpora explicitly match the ground-truth geographic distribution of each language, thus equally representing language users from around the world. This is important because it ensures that speakers of under-resourced language varieties (i.e., Indian English or Algerian French) are represented, both in the corpora themselves but also in derivative resources like word embeddings.
%U https://aclanthology.org/2020.lrec-1.308
%P 2528-2536
Markdown (Informal)
[Geographically-Balanced Gigaword Corpora for 50 Language Varieties](https://aclanthology.org/2020.lrec-1.308) (Dunn & Adams, LREC 2020)
ACL