@inproceedings{fort-etal-2022-use,
title = "Use of a Citizen Science Platform for the Creation of a Language Resource to Study Bias in Language Models for {F}rench: A Case Study",
author = {Fort, Kar{\"e}n and
N{\'e}v{\'e}ol, Aur{\'e}lie and
Dupont, Yoann and
Bezan{\c{c}}on, Julien},
editor = "Callison-Burch, Chris and
Cieri, Christopher and
Fiumara, James and
Liberman, Mark",
booktitle = "Proceedings of the 2nd Workshop on Novel Incentives in Data Collection from People: models, implementations, challenges and results within LREC 2022",
month = jun,
year = "2022",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2022.nidcp-1.2/",
pages = "8--13",
abstract = "There is a growing interest in the evaluation of bias, fairness and social impact of Natural Language Processing models and tools. However, little resources are available for this task in languages other than English. Translation of resources originally developed for English is a promising research direction. However, there is also a need for complementing translated resources by newly sourced resources in the original languages and social contexts studied. In order to collect a language resource for the study of biases in Language Models for French, we decided to resort to citizen science. We created three tasks on the LanguageARC citizen science platform to assist with the translation of an existing resource from English into French as well as the collection of complementary resources in native French. We successfully collected data for all three tasks from a total of 102 volunteer participants. Participants from different parts of the world contributed and we noted that although calls sent to mailing lists had a positive impact on participation, some participants pointed barriers to contributions due to the collection platform."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="fort-etal-2022-use">
<titleInfo>
<title>Use of a Citizen Science Platform for the Creation of a Language Resource to Study Bias in Language Models for French: A Case Study</title>
</titleInfo>
<name type="personal">
<namePart type="given">Karën</namePart>
<namePart type="family">Fort</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aurélie</namePart>
<namePart type="family">Névéol</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yoann</namePart>
<namePart type="family">Dupont</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Julien</namePart>
<namePart type="family">Bezançon</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 2nd Workshop on Novel Incentives in Data Collection from People: models, implementations, challenges and results within LREC 2022</title>
</titleInfo>
<name type="personal">
<namePart type="given">Chris</namePart>
<namePart type="family">Callison-Burch</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">James</namePart>
<namePart type="family">Fiumara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mark</namePart>
<namePart type="family">Liberman</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>There is a growing interest in the evaluation of bias, fairness and social impact of Natural Language Processing models and tools. However, little resources are available for this task in languages other than English. Translation of resources originally developed for English is a promising research direction. However, there is also a need for complementing translated resources by newly sourced resources in the original languages and social contexts studied. In order to collect a language resource for the study of biases in Language Models for French, we decided to resort to citizen science. We created three tasks on the LanguageARC citizen science platform to assist with the translation of an existing resource from English into French as well as the collection of complementary resources in native French. We successfully collected data for all three tasks from a total of 102 volunteer participants. Participants from different parts of the world contributed and we noted that although calls sent to mailing lists had a positive impact on participation, some participants pointed barriers to contributions due to the collection platform.</abstract>
<identifier type="citekey">fort-etal-2022-use</identifier>
<location>
<url>https://aclanthology.org/2022.nidcp-1.2/</url>
</location>
<part>
<date>2022-06</date>
<extent unit="page">
<start>8</start>
<end>13</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Use of a Citizen Science Platform for the Creation of a Language Resource to Study Bias in Language Models for French: A Case Study
%A Fort, Karën
%A Névéol, Aurélie
%A Dupont, Yoann
%A Bezançon, Julien
%Y Callison-Burch, Chris
%Y Cieri, Christopher
%Y Fiumara, James
%Y Liberman, Mark
%S Proceedings of the 2nd Workshop on Novel Incentives in Data Collection from People: models, implementations, challenges and results within LREC 2022
%D 2022
%8 June
%I European Language Resources Association
%C Marseille, France
%F fort-etal-2022-use
%X There is a growing interest in the evaluation of bias, fairness and social impact of Natural Language Processing models and tools. However, little resources are available for this task in languages other than English. Translation of resources originally developed for English is a promising research direction. However, there is also a need for complementing translated resources by newly sourced resources in the original languages and social contexts studied. In order to collect a language resource for the study of biases in Language Models for French, we decided to resort to citizen science. We created three tasks on the LanguageARC citizen science platform to assist with the translation of an existing resource from English into French as well as the collection of complementary resources in native French. We successfully collected data for all three tasks from a total of 102 volunteer participants. Participants from different parts of the world contributed and we noted that although calls sent to mailing lists had a positive impact on participation, some participants pointed barriers to contributions due to the collection platform.
%U https://aclanthology.org/2022.nidcp-1.2/
%P 8-13
Markdown (Informal)
[Use of a Citizen Science Platform for the Creation of a Language Resource to Study Bias in Language Models for French: A Case Study](https://aclanthology.org/2022.nidcp-1.2/) (Fort et al., NIDCP 2022)
ACL