@inproceedings{madanagopal-caverlee-2023-bias,
title = "Bias Neutralization in Non-Parallel Texts: A Cyclic Approach with Auxiliary Guidance",
author = "Madanagopal, Karthic and
Caverlee, James",
editor = "Bouamor, Houda and
Pino, Juan and
Bali, Kalika",
booktitle = "Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing",
month = dec,
year = "2023",
address = "Singapore",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.emnlp-main.882",
doi = "10.18653/v1/2023.emnlp-main.882",
pages = "14265--14278",
abstract = "Objectivity is a goal for Wikipedia and many news sites, as well as a guiding principle of many large language models. Indeed, several methods have recently been developed for automatic subjective bias neutralization. These methods, however, typically rely on parallel text for training (i.e. a biased sentence coupled with a non-biased sentence), demonstrate poor transfer to new domains, and can lose important bias-independent context. Toward expanding the reach of bias neutralization, we propose in this paper a new approach called FairBalance. Three of its unique features are: i) a cycle consistent adversarial network enables bias neutralization without the need for parallel text; ii) the model design preserves bias-independent content; and iii) through auxiliary guidance, the model highlights sequences of bias-inducing words, yielding strong results in terms of bias neutralization quality. Extensive experiments demonstrate how FairBalance significantly improves subjective bias neutralization compared to other methods.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="madanagopal-caverlee-2023-bias">
<titleInfo>
<title>Bias Neutralization in Non-Parallel Texts: A Cyclic Approach with Auxiliary Guidance</title>
</titleInfo>
<name type="personal">
<namePart type="given">Karthic</namePart>
<namePart type="family">Madanagopal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">James</namePart>
<namePart type="family">Caverlee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Houda</namePart>
<namePart type="family">Bouamor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Juan</namePart>
<namePart type="family">Pino</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kalika</namePart>
<namePart type="family">Bali</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Singapore</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Objectivity is a goal for Wikipedia and many news sites, as well as a guiding principle of many large language models. Indeed, several methods have recently been developed for automatic subjective bias neutralization. These methods, however, typically rely on parallel text for training (i.e. a biased sentence coupled with a non-biased sentence), demonstrate poor transfer to new domains, and can lose important bias-independent context. Toward expanding the reach of bias neutralization, we propose in this paper a new approach called FairBalance. Three of its unique features are: i) a cycle consistent adversarial network enables bias neutralization without the need for parallel text; ii) the model design preserves bias-independent content; and iii) through auxiliary guidance, the model highlights sequences of bias-inducing words, yielding strong results in terms of bias neutralization quality. Extensive experiments demonstrate how FairBalance significantly improves subjective bias neutralization compared to other methods.</abstract>
<identifier type="citekey">madanagopal-caverlee-2023-bias</identifier>
<identifier type="doi">10.18653/v1/2023.emnlp-main.882</identifier>
<location>
<url>https://aclanthology.org/2023.emnlp-main.882</url>
</location>
<part>
<date>2023-12</date>
<extent unit="page">
<start>14265</start>
<end>14278</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Bias Neutralization in Non-Parallel Texts: A Cyclic Approach with Auxiliary Guidance
%A Madanagopal, Karthic
%A Caverlee, James
%Y Bouamor, Houda
%Y Pino, Juan
%Y Bali, Kalika
%S Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing
%D 2023
%8 December
%I Association for Computational Linguistics
%C Singapore
%F madanagopal-caverlee-2023-bias
%X Objectivity is a goal for Wikipedia and many news sites, as well as a guiding principle of many large language models. Indeed, several methods have recently been developed for automatic subjective bias neutralization. These methods, however, typically rely on parallel text for training (i.e. a biased sentence coupled with a non-biased sentence), demonstrate poor transfer to new domains, and can lose important bias-independent context. Toward expanding the reach of bias neutralization, we propose in this paper a new approach called FairBalance. Three of its unique features are: i) a cycle consistent adversarial network enables bias neutralization without the need for parallel text; ii) the model design preserves bias-independent content; and iii) through auxiliary guidance, the model highlights sequences of bias-inducing words, yielding strong results in terms of bias neutralization quality. Extensive experiments demonstrate how FairBalance significantly improves subjective bias neutralization compared to other methods.
%R 10.18653/v1/2023.emnlp-main.882
%U https://aclanthology.org/2023.emnlp-main.882
%U https://doi.org/10.18653/v1/2023.emnlp-main.882
%P 14265-14278
Markdown (Informal)
[Bias Neutralization in Non-Parallel Texts: A Cyclic Approach with Auxiliary Guidance](https://aclanthology.org/2023.emnlp-main.882) (Madanagopal & Caverlee, EMNLP 2023)
ACL