@inproceedings{antoniak-mimno-2021-bad,
title = "Bad Seeds: Evaluating Lexical Methods for Bias Measurement",
author = "Antoniak, Maria and
Mimno, David",
editor = "Zong, Chengqing and
Xia, Fei and
Li, Wenjie and
Navigli, Roberto",
booktitle = "Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)",
month = aug,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.acl-long.148",
doi = "10.18653/v1/2021.acl-long.148",
pages = "1889--1904",
abstract = "A common factor in bias measurement methods is the use of hand-curated seed lexicons, but there remains little guidance for their selection. We gather seeds used in prior work, documenting their common sources and rationales, and in case studies of three English-language corpora, we enumerate the different types of social biases and linguistic features that, once encoded in the seeds, can affect subsequent bias measurements. Seeds developed in one context are often re-used in other contexts, but documentation and evaluation remain necessary precursors to relying on seeds for sensitive measurements.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="antoniak-mimno-2021-bad">
<titleInfo>
<title>Bad Seeds: Evaluating Lexical Methods for Bias Measurement</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="family">Antoniak</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Mimno</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Chengqing</namePart>
<namePart type="family">Zong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fei</namePart>
<namePart type="family">Xia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wenjie</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Roberto</namePart>
<namePart type="family">Navigli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>A common factor in bias measurement methods is the use of hand-curated seed lexicons, but there remains little guidance for their selection. We gather seeds used in prior work, documenting their common sources and rationales, and in case studies of three English-language corpora, we enumerate the different types of social biases and linguistic features that, once encoded in the seeds, can affect subsequent bias measurements. Seeds developed in one context are often re-used in other contexts, but documentation and evaluation remain necessary precursors to relying on seeds for sensitive measurements.</abstract>
<identifier type="citekey">antoniak-mimno-2021-bad</identifier>
<identifier type="doi">10.18653/v1/2021.acl-long.148</identifier>
<location>
<url>https://aclanthology.org/2021.acl-long.148</url>
</location>
<part>
<date>2021-08</date>
<extent unit="page">
<start>1889</start>
<end>1904</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Bad Seeds: Evaluating Lexical Methods for Bias Measurement
%A Antoniak, Maria
%A Mimno, David
%Y Zong, Chengqing
%Y Xia, Fei
%Y Li, Wenjie
%Y Navigli, Roberto
%S Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)
%D 2021
%8 August
%I Association for Computational Linguistics
%C Online
%F antoniak-mimno-2021-bad
%X A common factor in bias measurement methods is the use of hand-curated seed lexicons, but there remains little guidance for their selection. We gather seeds used in prior work, documenting their common sources and rationales, and in case studies of three English-language corpora, we enumerate the different types of social biases and linguistic features that, once encoded in the seeds, can affect subsequent bias measurements. Seeds developed in one context are often re-used in other contexts, but documentation and evaluation remain necessary precursors to relying on seeds for sensitive measurements.
%R 10.18653/v1/2021.acl-long.148
%U https://aclanthology.org/2021.acl-long.148
%U https://doi.org/10.18653/v1/2021.acl-long.148
%P 1889-1904
Markdown (Informal)
[Bad Seeds: Evaluating Lexical Methods for Bias Measurement](https://aclanthology.org/2021.acl-long.148) (Antoniak & Mimno, ACL-IJCNLP 2021)
ACL
- Maria Antoniak and David Mimno. 2021. Bad Seeds: Evaluating Lexical Methods for Bias Measurement. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pages 1889–1904, Online. Association for Computational Linguistics.