@inproceedings{bergman-diab-2022-towards,
title = "Towards Responsible Natural Language Annotation for the Varieties of {A}rabic",
author = "Bergman, A. and
Diab, Mona",
editor = "Muresan, Smaranda and
Nakov, Preslav and
Villavicencio, Aline",
booktitle = "Findings of the Association for Computational Linguistics: ACL 2022",
month = may,
year = "2022",
address = "Dublin, Ireland",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.findings-acl.31",
doi = "10.18653/v1/2022.findings-acl.31",
pages = "364--371",
abstract = "When building NLP models, there is a tendency to aim for broader coverage, often overlooking cultural and (socio)linguistic nuance. In this position paper, we make the case for care and attention to such nuances, particularly in dataset annotation, as well as the inclusion of cultural and linguistic expertise in the process. We present a playbook for responsible dataset creation for polyglossic, multidialectal languages. This work is informed by a study on Arabic annotation of social media content.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bergman-diab-2022-towards">
<titleInfo>
<title>Towards Responsible Natural Language Annotation for the Varieties of Arabic</title>
</titleInfo>
<name type="personal">
<namePart type="given">A</namePart>
<namePart type="family">Bergman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mona</namePart>
<namePart type="family">Diab</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: ACL 2022</title>
</titleInfo>
<name type="personal">
<namePart type="given">Smaranda</namePart>
<namePart type="family">Muresan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Preslav</namePart>
<namePart type="family">Nakov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aline</namePart>
<namePart type="family">Villavicencio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Dublin, Ireland</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>When building NLP models, there is a tendency to aim for broader coverage, often overlooking cultural and (socio)linguistic nuance. In this position paper, we make the case for care and attention to such nuances, particularly in dataset annotation, as well as the inclusion of cultural and linguistic expertise in the process. We present a playbook for responsible dataset creation for polyglossic, multidialectal languages. This work is informed by a study on Arabic annotation of social media content.</abstract>
<identifier type="citekey">bergman-diab-2022-towards</identifier>
<identifier type="doi">10.18653/v1/2022.findings-acl.31</identifier>
<location>
<url>https://aclanthology.org/2022.findings-acl.31</url>
</location>
<part>
<date>2022-05</date>
<extent unit="page">
<start>364</start>
<end>371</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Towards Responsible Natural Language Annotation for the Varieties of Arabic
%A Bergman, A.
%A Diab, Mona
%Y Muresan, Smaranda
%Y Nakov, Preslav
%Y Villavicencio, Aline
%S Findings of the Association for Computational Linguistics: ACL 2022
%D 2022
%8 May
%I Association for Computational Linguistics
%C Dublin, Ireland
%F bergman-diab-2022-towards
%X When building NLP models, there is a tendency to aim for broader coverage, often overlooking cultural and (socio)linguistic nuance. In this position paper, we make the case for care and attention to such nuances, particularly in dataset annotation, as well as the inclusion of cultural and linguistic expertise in the process. We present a playbook for responsible dataset creation for polyglossic, multidialectal languages. This work is informed by a study on Arabic annotation of social media content.
%R 10.18653/v1/2022.findings-acl.31
%U https://aclanthology.org/2022.findings-acl.31
%U https://doi.org/10.18653/v1/2022.findings-acl.31
%P 364-371
Markdown (Informal)
[Towards Responsible Natural Language Annotation for the Varieties of Arabic](https://aclanthology.org/2022.findings-acl.31) (Bergman & Diab, Findings 2022)
ACL