@inproceedings{das-etal-2023-toward,
title = "Toward Cultural Bias Evaluation Datasets: The Case of {B}engali Gender, Religious, and National Identity",
author = "Das, Dipto and
Guha, Shion and
Semaan, Bryan",
editor = "Dev, Sunipa and
Prabhakaran, Vinodkumar and
Adelani, David and
Hovy, Dirk and
Benotti, Luciana",
booktitle = "Proceedings of the First Workshop on Cross-Cultural Considerations in NLP (C3NLP)",
month = may,
year = "2023",
address = "Dubrovnik, Croatia",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.c3nlp-1.8",
doi = "10.18653/v1/2023.c3nlp-1.8",
pages = "68--83",
abstract = "Critical studies found NLP systems to bias based on gender and racial identities. However, few studies focused on identities defined by cultural factors like religion and nationality. Compared to English, such research efforts are even further limited in major languages like Bengali due to the unavailability of labeled datasets. This paper describes a process for developing a bias evaluation dataset highlighting cultural influences on identity. We also provide a Bengali dataset as an artifact outcome that can contribute to future critical research.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="das-etal-2023-toward">
<titleInfo>
<title>Toward Cultural Bias Evaluation Datasets: The Case of Bengali Gender, Religious, and National Identity</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dipto</namePart>
<namePart type="family">Das</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shion</namePart>
<namePart type="family">Guha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bryan</namePart>
<namePart type="family">Semaan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the First Workshop on Cross-Cultural Considerations in NLP (C3NLP)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sunipa</namePart>
<namePart type="family">Dev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vinodkumar</namePart>
<namePart type="family">Prabhakaran</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Adelani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dirk</namePart>
<namePart type="family">Hovy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Luciana</namePart>
<namePart type="family">Benotti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Dubrovnik, Croatia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Critical studies found NLP systems to bias based on gender and racial identities. However, few studies focused on identities defined by cultural factors like religion and nationality. Compared to English, such research efforts are even further limited in major languages like Bengali due to the unavailability of labeled datasets. This paper describes a process for developing a bias evaluation dataset highlighting cultural influences on identity. We also provide a Bengali dataset as an artifact outcome that can contribute to future critical research.</abstract>
<identifier type="citekey">das-etal-2023-toward</identifier>
<identifier type="doi">10.18653/v1/2023.c3nlp-1.8</identifier>
<location>
<url>https://aclanthology.org/2023.c3nlp-1.8</url>
</location>
<part>
<date>2023-05</date>
<extent unit="page">
<start>68</start>
<end>83</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Toward Cultural Bias Evaluation Datasets: The Case of Bengali Gender, Religious, and National Identity
%A Das, Dipto
%A Guha, Shion
%A Semaan, Bryan
%Y Dev, Sunipa
%Y Prabhakaran, Vinodkumar
%Y Adelani, David
%Y Hovy, Dirk
%Y Benotti, Luciana
%S Proceedings of the First Workshop on Cross-Cultural Considerations in NLP (C3NLP)
%D 2023
%8 May
%I Association for Computational Linguistics
%C Dubrovnik, Croatia
%F das-etal-2023-toward
%X Critical studies found NLP systems to bias based on gender and racial identities. However, few studies focused on identities defined by cultural factors like religion and nationality. Compared to English, such research efforts are even further limited in major languages like Bengali due to the unavailability of labeled datasets. This paper describes a process for developing a bias evaluation dataset highlighting cultural influences on identity. We also provide a Bengali dataset as an artifact outcome that can contribute to future critical research.
%R 10.18653/v1/2023.c3nlp-1.8
%U https://aclanthology.org/2023.c3nlp-1.8
%U https://doi.org/10.18653/v1/2023.c3nlp-1.8
%P 68-83
Markdown (Informal)
[Toward Cultural Bias Evaluation Datasets: The Case of Bengali Gender, Religious, and National Identity](https://aclanthology.org/2023.c3nlp-1.8) (Das et al., C3NLP 2023)
ACL