@inproceedings{ousidhoum-etal-2025-building,
title = "Building Better: Avoiding Pitfalls in Developing Language Resources when Data is Scarce",
author = "Ousidhoum, Nedjma and
Beloucif, Meriem and
Mohammad, Saif M.",
editor = "Che, Wanxiang and
Nabende, Joyce and
Shutova, Ekaterina and
Pilehvar, Mohammad Taher",
booktitle = "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = jul,
year = "2025",
address = "Vienna, Austria",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.acl-long.435/",
doi = "10.18653/v1/2025.acl-long.435",
pages = "8881--8894",
ISBN = "979-8-89176-251-0",
abstract = "Language is a form of symbolic capital that affects people{'}s lives in many ways (Bourdieu1977,1991). As a powerful means of communication, it reflects identities, cultures, traditions, and societies more broadly. Therefore, data in a given language should be regarded as more than just a collection of tokens. Rigorous data collection and labeling practices are essential for developing more human-centered and socially aware technologies. Although there has been growing interest in under-resourced languages within the NLP community, work in this area faces unique challenges, such as data scarcity and limited access to qualified annotators.In this paper, we collect feedback from individuals directly involved in and impacted by NLP artefacts for medium- and low-resource languages. We conduct both quantitative and qualitative analyses of their responses and highlight key issues related to: (1) data quality, including linguistic and cultural appropriateness; and (2) the ethics of common annotation practices, such as the misuse of participatory research. Based on these findings, we make several recommendations for creating high-quality language artefacts that reflect the cultural milieu of their speakers, while also respecting the dignity and labor of data workers."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ousidhoum-etal-2025-building">
<titleInfo>
<title>Building Better: Avoiding Pitfalls in Developing Language Resources when Data is Scarce</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nedjma</namePart>
<namePart type="family">Ousidhoum</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Meriem</namePart>
<namePart type="family">Beloucif</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Saif</namePart>
<namePart type="given">M</namePart>
<namePart type="family">Mohammad</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Wanxiang</namePart>
<namePart type="family">Che</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joyce</namePart>
<namePart type="family">Nabende</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Shutova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohammad</namePart>
<namePart type="given">Taher</namePart>
<namePart type="family">Pilehvar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Vienna, Austria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-251-0</identifier>
</relatedItem>
<abstract>Language is a form of symbolic capital that affects people’s lives in many ways (Bourdieu1977,1991). As a powerful means of communication, it reflects identities, cultures, traditions, and societies more broadly. Therefore, data in a given language should be regarded as more than just a collection of tokens. Rigorous data collection and labeling practices are essential for developing more human-centered and socially aware technologies. Although there has been growing interest in under-resourced languages within the NLP community, work in this area faces unique challenges, such as data scarcity and limited access to qualified annotators.In this paper, we collect feedback from individuals directly involved in and impacted by NLP artefacts for medium- and low-resource languages. We conduct both quantitative and qualitative analyses of their responses and highlight key issues related to: (1) data quality, including linguistic and cultural appropriateness; and (2) the ethics of common annotation practices, such as the misuse of participatory research. Based on these findings, we make several recommendations for creating high-quality language artefacts that reflect the cultural milieu of their speakers, while also respecting the dignity and labor of data workers.</abstract>
<identifier type="citekey">ousidhoum-etal-2025-building</identifier>
<identifier type="doi">10.18653/v1/2025.acl-long.435</identifier>
<location>
<url>https://aclanthology.org/2025.acl-long.435/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>8881</start>
<end>8894</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Building Better: Avoiding Pitfalls in Developing Language Resources when Data is Scarce
%A Ousidhoum, Nedjma
%A Beloucif, Meriem
%A Mohammad, Saif M.
%Y Che, Wanxiang
%Y Nabende, Joyce
%Y Shutova, Ekaterina
%Y Pilehvar, Mohammad Taher
%S Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2025
%8 July
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 979-8-89176-251-0
%F ousidhoum-etal-2025-building
%X Language is a form of symbolic capital that affects people’s lives in many ways (Bourdieu1977,1991). As a powerful means of communication, it reflects identities, cultures, traditions, and societies more broadly. Therefore, data in a given language should be regarded as more than just a collection of tokens. Rigorous data collection and labeling practices are essential for developing more human-centered and socially aware technologies. Although there has been growing interest in under-resourced languages within the NLP community, work in this area faces unique challenges, such as data scarcity and limited access to qualified annotators.In this paper, we collect feedback from individuals directly involved in and impacted by NLP artefacts for medium- and low-resource languages. We conduct both quantitative and qualitative analyses of their responses and highlight key issues related to: (1) data quality, including linguistic and cultural appropriateness; and (2) the ethics of common annotation practices, such as the misuse of participatory research. Based on these findings, we make several recommendations for creating high-quality language artefacts that reflect the cultural milieu of their speakers, while also respecting the dignity and labor of data workers.
%R 10.18653/v1/2025.acl-long.435
%U https://aclanthology.org/2025.acl-long.435/
%U https://doi.org/10.18653/v1/2025.acl-long.435
%P 8881-8894
Markdown (Informal)
[Building Better: Avoiding Pitfalls in Developing Language Resources when Data is Scarce](https://aclanthology.org/2025.acl-long.435/) (Ousidhoum et al., ACL 2025)
ACL