@inproceedings{jain-etal-2022-leveraging,
title = "Leveraging Pre-trained Language Models for Gender Debiasing",
author = "Jain, Nishtha and
Groves, Declan and
Specia, Lucia and
Popovi{\'c}, Maja",
editor = "Calzolari, Nicoletta and
B{\'e}chet, Fr{\'e}d{\'e}ric and
Blache, Philippe and
Choukri, Khalid and
Cieri, Christopher and
Declerck, Thierry and
Goggi, Sara and
Isahara, Hitoshi and
Maegaard, Bente and
Mariani, Joseph and
Mazo, H{\'e}l{\`e}ne and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Thirteenth Language Resources and Evaluation Conference",
month = jun,
year = "2022",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2022.lrec-1.235/",
pages = "2188--2195",
abstract = "Studying and mitigating gender and other biases in natural language have become important areas of research from both algorithmic and data perspectives. This paper explores the idea of reducing gender bias in a language generation context by generating gender variants of sentences. Previous work in this field has either been rule-based or required large amounts of gender balanced training data. These approaches are however not scalable across multiple languages, as creating data or rules for each language is costly and time-consuming. This work explores a light-weight method to generate gender variants for a given text using pre-trained language models as the resource, without any task-specific labelled data. The approach is designed to work on multiple languages with minimal changes in the form of heuristics. To showcase that, we have tested it on a high-resourced language, namely Spanish, and a low-resourced language from a different family, namely Serbian. The approach proved to work very well on Spanish, and while the results were less positive for Serbian, it showed potential even for languages where pre-trained models are less effective."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="jain-etal-2022-leveraging">
<titleInfo>
<title>Leveraging Pre-trained Language Models for Gender Debiasing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nishtha</namePart>
<namePart type="family">Jain</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Declan</namePart>
<namePart type="family">Groves</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lucia</namePart>
<namePart type="family">Specia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maja</namePart>
<namePart type="family">Popović</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Thirteenth Language Resources and Evaluation Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Frédéric</namePart>
<namePart type="family">Béchet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philippe</namePart>
<namePart type="family">Blache</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalid</namePart>
<namePart type="family">Choukri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christopher</namePart>
<namePart type="family">Cieri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thierry</namePart>
<namePart type="family">Declerck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Goggi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hitoshi</namePart>
<namePart type="family">Isahara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bente</namePart>
<namePart type="family">Maegaard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joseph</namePart>
<namePart type="family">Mariani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hélène</namePart>
<namePart type="family">Mazo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Odijk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Studying and mitigating gender and other biases in natural language have become important areas of research from both algorithmic and data perspectives. This paper explores the idea of reducing gender bias in a language generation context by generating gender variants of sentences. Previous work in this field has either been rule-based or required large amounts of gender balanced training data. These approaches are however not scalable across multiple languages, as creating data or rules for each language is costly and time-consuming. This work explores a light-weight method to generate gender variants for a given text using pre-trained language models as the resource, without any task-specific labelled data. The approach is designed to work on multiple languages with minimal changes in the form of heuristics. To showcase that, we have tested it on a high-resourced language, namely Spanish, and a low-resourced language from a different family, namely Serbian. The approach proved to work very well on Spanish, and while the results were less positive for Serbian, it showed potential even for languages where pre-trained models are less effective.</abstract>
<identifier type="citekey">jain-etal-2022-leveraging</identifier>
<location>
<url>https://aclanthology.org/2022.lrec-1.235/</url>
</location>
<part>
<date>2022-06</date>
<extent unit="page">
<start>2188</start>
<end>2195</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Leveraging Pre-trained Language Models for Gender Debiasing
%A Jain, Nishtha
%A Groves, Declan
%A Specia, Lucia
%A Popović, Maja
%Y Calzolari, Nicoletta
%Y Béchet, Frédéric
%Y Blache, Philippe
%Y Choukri, Khalid
%Y Cieri, Christopher
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Isahara, Hitoshi
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Hélène
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Thirteenth Language Resources and Evaluation Conference
%D 2022
%8 June
%I European Language Resources Association
%C Marseille, France
%F jain-etal-2022-leveraging
%X Studying and mitigating gender and other biases in natural language have become important areas of research from both algorithmic and data perspectives. This paper explores the idea of reducing gender bias in a language generation context by generating gender variants of sentences. Previous work in this field has either been rule-based or required large amounts of gender balanced training data. These approaches are however not scalable across multiple languages, as creating data or rules for each language is costly and time-consuming. This work explores a light-weight method to generate gender variants for a given text using pre-trained language models as the resource, without any task-specific labelled data. The approach is designed to work on multiple languages with minimal changes in the form of heuristics. To showcase that, we have tested it on a high-resourced language, namely Spanish, and a low-resourced language from a different family, namely Serbian. The approach proved to work very well on Spanish, and while the results were less positive for Serbian, it showed potential even for languages where pre-trained models are less effective.
%U https://aclanthology.org/2022.lrec-1.235/
%P 2188-2195
Markdown (Informal)
[Leveraging Pre-trained Language Models for Gender Debiasing](https://aclanthology.org/2022.lrec-1.235/) (Jain et al., LREC 2022)
ACL