@inproceedings{silva-etal-2021-towards,
title = "Towards a Comprehensive Understanding and Accurate Evaluation of Societal Biases in Pre-Trained Transformers",
author = "Silva, Andrew and
Tambwekar, Pradyumna and
Gombolay, Matthew",
editor = "Toutanova, Kristina and
Rumshisky, Anna and
Zettlemoyer, Luke and
Hakkani-Tur, Dilek and
Beltagy, Iz and
Bethard, Steven and
Cotterell, Ryan and
Chakraborty, Tanmoy and
Zhou, Yichao",
booktitle = "Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies",
month = jun,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.naacl-main.189",
doi = "10.18653/v1/2021.naacl-main.189",
pages = "2383--2389",
abstract = "The ease of access to pre-trained transformers has enabled developers to leverage large-scale language models to build exciting applications for their users. While such pre-trained models offer convenient starting points for researchers and developers, there is little consideration for the societal biases captured within these model risking perpetuation of racial, gender, and other harmful biases when these models are deployed at scale. In this paper, we investigate gender and racial bias across ubiquitous pre-trained language models, including GPT-2, XLNet, BERT, RoBERTa, ALBERT and DistilBERT. We evaluate bias within pre-trained transformers using three metrics: WEAT, sequence likelihood, and pronoun ranking. We conclude with an experiment demonstrating the ineffectiveness of word-embedding techniques, such as WEAT, signaling the need for more robust bias testing in transformers.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="silva-etal-2021-towards">
<titleInfo>
<title>Towards a Comprehensive Understanding and Accurate Evaluation of Societal Biases in Pre-Trained Transformers</title>
</titleInfo>
<name type="personal">
<namePart type="given">Andrew</namePart>
<namePart type="family">Silva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pradyumna</namePart>
<namePart type="family">Tambwekar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Matthew</namePart>
<namePart type="family">Gombolay</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kristina</namePart>
<namePart type="family">Toutanova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Rumshisky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Luke</namePart>
<namePart type="family">Zettlemoyer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dilek</namePart>
<namePart type="family">Hakkani-Tur</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Iz</namePart>
<namePart type="family">Beltagy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steven</namePart>
<namePart type="family">Bethard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ryan</namePart>
<namePart type="family">Cotterell</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tanmoy</namePart>
<namePart type="family">Chakraborty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yichao</namePart>
<namePart type="family">Zhou</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>The ease of access to pre-trained transformers has enabled developers to leverage large-scale language models to build exciting applications for their users. While such pre-trained models offer convenient starting points for researchers and developers, there is little consideration for the societal biases captured within these model risking perpetuation of racial, gender, and other harmful biases when these models are deployed at scale. In this paper, we investigate gender and racial bias across ubiquitous pre-trained language models, including GPT-2, XLNet, BERT, RoBERTa, ALBERT and DistilBERT. We evaluate bias within pre-trained transformers using three metrics: WEAT, sequence likelihood, and pronoun ranking. We conclude with an experiment demonstrating the ineffectiveness of word-embedding techniques, such as WEAT, signaling the need for more robust bias testing in transformers.</abstract>
<identifier type="citekey">silva-etal-2021-towards</identifier>
<identifier type="doi">10.18653/v1/2021.naacl-main.189</identifier>
<location>
<url>https://aclanthology.org/2021.naacl-main.189</url>
</location>
<part>
<date>2021-06</date>
<extent unit="page">
<start>2383</start>
<end>2389</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Towards a Comprehensive Understanding and Accurate Evaluation of Societal Biases in Pre-Trained Transformers
%A Silva, Andrew
%A Tambwekar, Pradyumna
%A Gombolay, Matthew
%Y Toutanova, Kristina
%Y Rumshisky, Anna
%Y Zettlemoyer, Luke
%Y Hakkani-Tur, Dilek
%Y Beltagy, Iz
%Y Bethard, Steven
%Y Cotterell, Ryan
%Y Chakraborty, Tanmoy
%Y Zhou, Yichao
%S Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
%D 2021
%8 June
%I Association for Computational Linguistics
%C Online
%F silva-etal-2021-towards
%X The ease of access to pre-trained transformers has enabled developers to leverage large-scale language models to build exciting applications for their users. While such pre-trained models offer convenient starting points for researchers and developers, there is little consideration for the societal biases captured within these model risking perpetuation of racial, gender, and other harmful biases when these models are deployed at scale. In this paper, we investigate gender and racial bias across ubiquitous pre-trained language models, including GPT-2, XLNet, BERT, RoBERTa, ALBERT and DistilBERT. We evaluate bias within pre-trained transformers using three metrics: WEAT, sequence likelihood, and pronoun ranking. We conclude with an experiment demonstrating the ineffectiveness of word-embedding techniques, such as WEAT, signaling the need for more robust bias testing in transformers.
%R 10.18653/v1/2021.naacl-main.189
%U https://aclanthology.org/2021.naacl-main.189
%U https://doi.org/10.18653/v1/2021.naacl-main.189
%P 2383-2389
Markdown (Informal)
[Towards a Comprehensive Understanding and Accurate Evaluation of Societal Biases in Pre-Trained Transformers](https://aclanthology.org/2021.naacl-main.189) (Silva et al., NAACL 2021)
ACL