@inproceedings{govindarajan-etal-2023-counterfactual,
title = "Counterfactual Probing for the Influence of Affect and Specificity on Intergroup Bias",
author = "Govindarajan, Venkata Subrahmanyan and
Beaver, David and
Mahowald, Kyle and
Li, Junyi Jessy",
editor = "Rogers, Anna and
Boyd-Graber, Jordan and
Okazaki, Naoaki",
booktitle = "Findings of the Association for Computational Linguistics: ACL 2023",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.findings-acl.813/",
doi = "10.18653/v1/2023.findings-acl.813",
pages = "12853--12862",
abstract = "While existing work on studying bias in NLP focues on negative or pejorative language use, Govindarajan et al. (2023) offer a revised framing of bias in terms of intergroup social context, and its effects on language behavior. In this paper, we investigate if two pragmatic features (specificity and affect) systematically vary in different intergroup contexts {---} thus connecting this new framing of bias to language output. Preliminary analysis finds modest correlations between specificity and affect of tweets with supervised intergroup relationship (IGR) labels. Counterfactual probing further reveals that while neural models finetuned for predicting IGR reliably use affect in classification, the model`s usage of specificity is inconclusive."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="govindarajan-etal-2023-counterfactual">
<titleInfo>
<title>Counterfactual Probing for the Influence of Affect and Specificity on Intergroup Bias</title>
</titleInfo>
<name type="personal">
<namePart type="given">Venkata</namePart>
<namePart type="given">Subrahmanyan</namePart>
<namePart type="family">Govindarajan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Beaver</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kyle</namePart>
<namePart type="family">Mahowald</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Junyi</namePart>
<namePart type="given">Jessy</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: ACL 2023</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Rogers</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jordan</namePart>
<namePart type="family">Boyd-Graber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Naoaki</namePart>
<namePart type="family">Okazaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Toronto, Canada</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>While existing work on studying bias in NLP focues on negative or pejorative language use, Govindarajan et al. (2023) offer a revised framing of bias in terms of intergroup social context, and its effects on language behavior. In this paper, we investigate if two pragmatic features (specificity and affect) systematically vary in different intergroup contexts — thus connecting this new framing of bias to language output. Preliminary analysis finds modest correlations between specificity and affect of tweets with supervised intergroup relationship (IGR) labels. Counterfactual probing further reveals that while neural models finetuned for predicting IGR reliably use affect in classification, the model‘s usage of specificity is inconclusive.</abstract>
<identifier type="citekey">govindarajan-etal-2023-counterfactual</identifier>
<identifier type="doi">10.18653/v1/2023.findings-acl.813</identifier>
<location>
<url>https://aclanthology.org/2023.findings-acl.813/</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>12853</start>
<end>12862</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Counterfactual Probing for the Influence of Affect and Specificity on Intergroup Bias
%A Govindarajan, Venkata Subrahmanyan
%A Beaver, David
%A Mahowald, Kyle
%A Li, Junyi Jessy
%Y Rogers, Anna
%Y Boyd-Graber, Jordan
%Y Okazaki, Naoaki
%S Findings of the Association for Computational Linguistics: ACL 2023
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F govindarajan-etal-2023-counterfactual
%X While existing work on studying bias in NLP focues on negative or pejorative language use, Govindarajan et al. (2023) offer a revised framing of bias in terms of intergroup social context, and its effects on language behavior. In this paper, we investigate if two pragmatic features (specificity and affect) systematically vary in different intergroup contexts — thus connecting this new framing of bias to language output. Preliminary analysis finds modest correlations between specificity and affect of tweets with supervised intergroup relationship (IGR) labels. Counterfactual probing further reveals that while neural models finetuned for predicting IGR reliably use affect in classification, the model‘s usage of specificity is inconclusive.
%R 10.18653/v1/2023.findings-acl.813
%U https://aclanthology.org/2023.findings-acl.813/
%U https://doi.org/10.18653/v1/2023.findings-acl.813
%P 12853-12862
Markdown (Informal)
[Counterfactual Probing for the Influence of Affect and Specificity on Intergroup Bias](https://aclanthology.org/2023.findings-acl.813/) (Govindarajan et al., Findings 2023)
ACL