@inproceedings{havens-etal-2022-uncertainty,
title = "Uncertainty and Inclusivity in Gender Bias Annotation: An Annotation Taxonomy and Annotated Datasets of {B}ritish {E}nglish Text",
author = "Havens, Lucy and
Terras, Melissa and
Bach, Benjamin and
Alex, Beatrice",
editor = "Hardmeier, Christian and
Basta, Christine and
Costa-juss{\`a}, Marta R. and
Stanovsky, Gabriel and
Gonen, Hila",
booktitle = "Proceedings of the 4th Workshop on Gender Bias in Natural Language Processing (GeBNLP)",
month = jul,
year = "2022",
address = "Seattle, Washington",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.gebnlp-1.4",
doi = "10.18653/v1/2022.gebnlp-1.4",
pages = "30--57",
abstract = "Mitigating harms from gender biased language in Natural Language Processing (NLP) systems remains a challenge, and the situated nature of language means bias is inescapable in NLP data. Though efforts to mitigate gender bias in NLP are numerous, they often vaguely define gender and bias, only consider two genders, and do not incorporate uncertainty into models. To address these limitations, in this paper we present a taxonomy of gender biased language and apply it to create annotated datasets. We created the taxonomy and annotated data with the aim of making gender bias in language transparent. If biases are communicated clearly, varieties of biased language can be better identified and measured. Our taxonomy contains eleven types of gender biases inclusive of people whose gender expressions do not fit into the binary conceptions of woman and man, and whose gender differs from that they were assigned at birth, while also allowing annotators to document unknown gender information. The taxonomy and annotated data will, in future work, underpin analysis and more equitable language model development.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="havens-etal-2022-uncertainty">
<titleInfo>
<title>Uncertainty and Inclusivity in Gender Bias Annotation: An Annotation Taxonomy and Annotated Datasets of British English Text</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lucy</namePart>
<namePart type="family">Havens</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Melissa</namePart>
<namePart type="family">Terras</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Benjamin</namePart>
<namePart type="family">Bach</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Beatrice</namePart>
<namePart type="family">Alex</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 4th Workshop on Gender Bias in Natural Language Processing (GeBNLP)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Christian</namePart>
<namePart type="family">Hardmeier</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christine</namePart>
<namePart type="family">Basta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marta</namePart>
<namePart type="given">R</namePart>
<namePart type="family">Costa-jussà</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gabriel</namePart>
<namePart type="family">Stanovsky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hila</namePart>
<namePart type="family">Gonen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Seattle, Washington</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Mitigating harms from gender biased language in Natural Language Processing (NLP) systems remains a challenge, and the situated nature of language means bias is inescapable in NLP data. Though efforts to mitigate gender bias in NLP are numerous, they often vaguely define gender and bias, only consider two genders, and do not incorporate uncertainty into models. To address these limitations, in this paper we present a taxonomy of gender biased language and apply it to create annotated datasets. We created the taxonomy and annotated data with the aim of making gender bias in language transparent. If biases are communicated clearly, varieties of biased language can be better identified and measured. Our taxonomy contains eleven types of gender biases inclusive of people whose gender expressions do not fit into the binary conceptions of woman and man, and whose gender differs from that they were assigned at birth, while also allowing annotators to document unknown gender information. The taxonomy and annotated data will, in future work, underpin analysis and more equitable language model development.</abstract>
<identifier type="citekey">havens-etal-2022-uncertainty</identifier>
<identifier type="doi">10.18653/v1/2022.gebnlp-1.4</identifier>
<location>
<url>https://aclanthology.org/2022.gebnlp-1.4</url>
</location>
<part>
<date>2022-07</date>
<extent unit="page">
<start>30</start>
<end>57</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Uncertainty and Inclusivity in Gender Bias Annotation: An Annotation Taxonomy and Annotated Datasets of British English Text
%A Havens, Lucy
%A Terras, Melissa
%A Bach, Benjamin
%A Alex, Beatrice
%Y Hardmeier, Christian
%Y Basta, Christine
%Y Costa-jussà, Marta R.
%Y Stanovsky, Gabriel
%Y Gonen, Hila
%S Proceedings of the 4th Workshop on Gender Bias in Natural Language Processing (GeBNLP)
%D 2022
%8 July
%I Association for Computational Linguistics
%C Seattle, Washington
%F havens-etal-2022-uncertainty
%X Mitigating harms from gender biased language in Natural Language Processing (NLP) systems remains a challenge, and the situated nature of language means bias is inescapable in NLP data. Though efforts to mitigate gender bias in NLP are numerous, they often vaguely define gender and bias, only consider two genders, and do not incorporate uncertainty into models. To address these limitations, in this paper we present a taxonomy of gender biased language and apply it to create annotated datasets. We created the taxonomy and annotated data with the aim of making gender bias in language transparent. If biases are communicated clearly, varieties of biased language can be better identified and measured. Our taxonomy contains eleven types of gender biases inclusive of people whose gender expressions do not fit into the binary conceptions of woman and man, and whose gender differs from that they were assigned at birth, while also allowing annotators to document unknown gender information. The taxonomy and annotated data will, in future work, underpin analysis and more equitable language model development.
%R 10.18653/v1/2022.gebnlp-1.4
%U https://aclanthology.org/2022.gebnlp-1.4
%U https://doi.org/10.18653/v1/2022.gebnlp-1.4
%P 30-57
Markdown (Informal)
[Uncertainty and Inclusivity in Gender Bias Annotation: An Annotation Taxonomy and Annotated Datasets of British English Text](https://aclanthology.org/2022.gebnlp-1.4) (Havens et al., GeBNLP 2022)
ACL