@inproceedings{khanuja-etal-2023-evaluating,
title = "Evaluating the Diversity, Equity, and Inclusion of {NLP} Technology: A Case Study for {I}ndian Languages",
author = "Khanuja, Simran and
Ruder, Sebastian and
Talukdar, Partha",
editor = "Vlachos, Andreas and
Augenstein, Isabelle",
booktitle = "Findings of the Association for Computational Linguistics: EACL 2023",
month = may,
year = "2023",
address = "Dubrovnik, Croatia",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.findings-eacl.131/",
doi = "10.18653/v1/2023.findings-eacl.131",
pages = "1763--1777",
abstract = "In order for NLP technology to be widely applicable, fair, and useful, it needs to serve a diverse set of speakers across the world`s languages, be equitable, i.e., not unduly biased towards any particular language, and be inclusive of all users, particularly in low-resource settings where compute constraints are common. In this paper, we propose an evaluation paradigm that assesses NLP technologies across all three dimensions. While diversity and inclusion have received attention in recent literature, equity is currently unexplored. We propose to address this gap using the Gini coefficient, a well-established metric used for estimating societal wealth inequality. Using our paradigm, we highlight the distressed state of current technologies for Indian (IN) languages (a linguistically large and diverse set, with a varied speaker population), across all three dimensions. To improve upon these metrics, we demonstrate the importance of region-specific choices in model building and dataset creation, and more importantly, propose a novel, generalisable approach to optimal resource allocation during fine-tuning. Finally, we discuss steps to mitigate these biases and encourage the community to employ multi-faceted evaluation when building linguistically diverse and equitable technologies."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="khanuja-etal-2023-evaluating">
<titleInfo>
<title>Evaluating the Diversity, Equity, and Inclusion of NLP Technology: A Case Study for Indian Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Simran</namePart>
<namePart type="family">Khanuja</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">Partha</namePart>
<namePart type="family">Talukdar</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>Findings of the Association for Computational Linguistics: EACL 2023</title>
</titleInfo>
<name type="personal">
<namePart type="given">Andreas</namePart>
<namePart type="family">Vlachos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Isabelle</namePart>
<namePart type="family">Augenstein</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>In order for NLP technology to be widely applicable, fair, and useful, it needs to serve a diverse set of speakers across the world‘s languages, be equitable, i.e., not unduly biased towards any particular language, and be inclusive of all users, particularly in low-resource settings where compute constraints are common. In this paper, we propose an evaluation paradigm that assesses NLP technologies across all three dimensions. While diversity and inclusion have received attention in recent literature, equity is currently unexplored. We propose to address this gap using the Gini coefficient, a well-established metric used for estimating societal wealth inequality. Using our paradigm, we highlight the distressed state of current technologies for Indian (IN) languages (a linguistically large and diverse set, with a varied speaker population), across all three dimensions. To improve upon these metrics, we demonstrate the importance of region-specific choices in model building and dataset creation, and more importantly, propose a novel, generalisable approach to optimal resource allocation during fine-tuning. Finally, we discuss steps to mitigate these biases and encourage the community to employ multi-faceted evaluation when building linguistically diverse and equitable technologies.</abstract>
<identifier type="citekey">khanuja-etal-2023-evaluating</identifier>
<identifier type="doi">10.18653/v1/2023.findings-eacl.131</identifier>
<location>
<url>https://aclanthology.org/2023.findings-eacl.131/</url>
</location>
<part>
<date>2023-05</date>
<extent unit="page">
<start>1763</start>
<end>1777</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Evaluating the Diversity, Equity, and Inclusion of NLP Technology: A Case Study for Indian Languages
%A Khanuja, Simran
%A Ruder, Sebastian
%A Talukdar, Partha
%Y Vlachos, Andreas
%Y Augenstein, Isabelle
%S Findings of the Association for Computational Linguistics: EACL 2023
%D 2023
%8 May
%I Association for Computational Linguistics
%C Dubrovnik, Croatia
%F khanuja-etal-2023-evaluating
%X In order for NLP technology to be widely applicable, fair, and useful, it needs to serve a diverse set of speakers across the world‘s languages, be equitable, i.e., not unduly biased towards any particular language, and be inclusive of all users, particularly in low-resource settings where compute constraints are common. In this paper, we propose an evaluation paradigm that assesses NLP technologies across all three dimensions. While diversity and inclusion have received attention in recent literature, equity is currently unexplored. We propose to address this gap using the Gini coefficient, a well-established metric used for estimating societal wealth inequality. Using our paradigm, we highlight the distressed state of current technologies for Indian (IN) languages (a linguistically large and diverse set, with a varied speaker population), across all three dimensions. To improve upon these metrics, we demonstrate the importance of region-specific choices in model building and dataset creation, and more importantly, propose a novel, generalisable approach to optimal resource allocation during fine-tuning. Finally, we discuss steps to mitigate these biases and encourage the community to employ multi-faceted evaluation when building linguistically diverse and equitable technologies.
%R 10.18653/v1/2023.findings-eacl.131
%U https://aclanthology.org/2023.findings-eacl.131/
%U https://doi.org/10.18653/v1/2023.findings-eacl.131
%P 1763-1777
Markdown (Informal)
[Evaluating the Diversity, Equity, and Inclusion of NLP Technology: A Case Study for Indian Languages](https://aclanthology.org/2023.findings-eacl.131/) (Khanuja et al., Findings 2023)
ACL