@inproceedings{agarwal-etal-2019-word,
title = "Word Embeddings (Also) Encode Human Personality Stereotypes",
author = "Agarwal, Oshin and
Durup{\i}nar, Funda and
Badler, Norman I. and
Nenkova, Ani",
editor = "Mihalcea, Rada and
Shutova, Ekaterina and
Ku, Lun-Wei and
Evang, Kilian and
Poria, Soujanya",
booktitle = "Proceedings of the Eighth Joint Conference on Lexical and Computational Semantics (*{SEM} 2019)",
month = jun,
year = "2019",
address = "Minneapolis, Minnesota",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/S19-1023",
doi = "10.18653/v1/S19-1023",
pages = "205--211",
abstract = "Word representations trained on text reproduce human implicit bias related to gender, race and age. Methods have been developed to remove such bias. Here, we present results that show that human stereotypes exist even for much more nuanced judgments such as personality, for a variety of person identities beyond the typically legally protected attributes and that these are similarly captured in word representations. Specifically, we collected human judgments about a person{'}s Big Five personality traits formed solely from information about the occupation, nationality or a common noun description of a hypothetical person. Analysis of the data reveals a large number of statistically significant stereotypes in people. We then demonstrate the bias captured in lexical representations is statistically significantly correlated with the documented human bias. Our results, showing bias for a large set of person descriptors for such nuanced traits put in doubt the feasibility of broadly and fairly applying debiasing methods and call for the development of new methods for auditing language technology systems and resources.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="agarwal-etal-2019-word">
<titleInfo>
<title>Word Embeddings (Also) Encode Human Personality Stereotypes</title>
</titleInfo>
<name type="personal">
<namePart type="given">Oshin</namePart>
<namePart type="family">Agarwal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Funda</namePart>
<namePart type="family">Durupınar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Norman</namePart>
<namePart type="given">I</namePart>
<namePart type="family">Badler</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ani</namePart>
<namePart type="family">Nenkova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Eighth Joint Conference on Lexical and Computational Semantics (*SEM 2019)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Rada</namePart>
<namePart type="family">Mihalcea</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">Lun-Wei</namePart>
<namePart type="family">Ku</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kilian</namePart>
<namePart type="family">Evang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Soujanya</namePart>
<namePart type="family">Poria</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Minneapolis, Minnesota</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Word representations trained on text reproduce human implicit bias related to gender, race and age. Methods have been developed to remove such bias. Here, we present results that show that human stereotypes exist even for much more nuanced judgments such as personality, for a variety of person identities beyond the typically legally protected attributes and that these are similarly captured in word representations. Specifically, we collected human judgments about a person’s Big Five personality traits formed solely from information about the occupation, nationality or a common noun description of a hypothetical person. Analysis of the data reveals a large number of statistically significant stereotypes in people. We then demonstrate the bias captured in lexical representations is statistically significantly correlated with the documented human bias. Our results, showing bias for a large set of person descriptors for such nuanced traits put in doubt the feasibility of broadly and fairly applying debiasing methods and call for the development of new methods for auditing language technology systems and resources.</abstract>
<identifier type="citekey">agarwal-etal-2019-word</identifier>
<identifier type="doi">10.18653/v1/S19-1023</identifier>
<location>
<url>https://aclanthology.org/S19-1023</url>
</location>
<part>
<date>2019-06</date>
<extent unit="page">
<start>205</start>
<end>211</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Word Embeddings (Also) Encode Human Personality Stereotypes
%A Agarwal, Oshin
%A Durupınar, Funda
%A Badler, Norman I.
%A Nenkova, Ani
%Y Mihalcea, Rada
%Y Shutova, Ekaterina
%Y Ku, Lun-Wei
%Y Evang, Kilian
%Y Poria, Soujanya
%S Proceedings of the Eighth Joint Conference on Lexical and Computational Semantics (*SEM 2019)
%D 2019
%8 June
%I Association for Computational Linguistics
%C Minneapolis, Minnesota
%F agarwal-etal-2019-word
%X Word representations trained on text reproduce human implicit bias related to gender, race and age. Methods have been developed to remove such bias. Here, we present results that show that human stereotypes exist even for much more nuanced judgments such as personality, for a variety of person identities beyond the typically legally protected attributes and that these are similarly captured in word representations. Specifically, we collected human judgments about a person’s Big Five personality traits formed solely from information about the occupation, nationality or a common noun description of a hypothetical person. Analysis of the data reveals a large number of statistically significant stereotypes in people. We then demonstrate the bias captured in lexical representations is statistically significantly correlated with the documented human bias. Our results, showing bias for a large set of person descriptors for such nuanced traits put in doubt the feasibility of broadly and fairly applying debiasing methods and call for the development of new methods for auditing language technology systems and resources.
%R 10.18653/v1/S19-1023
%U https://aclanthology.org/S19-1023
%U https://doi.org/10.18653/v1/S19-1023
%P 205-211
Markdown (Informal)
[Word Embeddings (Also) Encode Human Personality Stereotypes](https://aclanthology.org/S19-1023) (Agarwal et al., *SEM 2019)
ACL
- Oshin Agarwal, Funda Durupınar, Norman I. Badler, and Ani Nenkova. 2019. Word Embeddings (Also) Encode Human Personality Stereotypes. In Proceedings of the Eighth Joint Conference on Lexical and Computational Semantics (*SEM 2019), pages 205–211, Minneapolis, Minnesota. Association for Computational Linguistics.