@inproceedings{lund-etal-2023-gender,
title = "Gender-Inclusive Grammatical Error Correction through Augmentation",
author = "Lund, Gunnar and
Omelianchuk, Kostiantyn and
Samokhin, Igor",
editor = {Kochmar, Ekaterina and
Burstein, Jill and
Horbach, Andrea and
Laarmann-Quante, Ronja and
Madnani, Nitin and
Tack, Ana{\"i}s and
Yaneva, Victoria and
Yuan, Zheng and
Zesch, Torsten},
booktitle = "Proceedings of the 18th Workshop on Innovative Use of NLP for Building Educational Applications (BEA 2023)",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.bea-1.13/",
doi = "10.18653/v1/2023.bea-1.13",
pages = "148--162",
abstract = "In this paper we show that GEC systems display gender bias related to the use of masculine and feminine terms and the gender-neutral singular {\textquotedblleft}they{\textquotedblright}. We develop parallel datasets of texts with masculine and feminine terms, and singular {\textquotedblleft}they{\textquotedblright}, and use them to quantify gender bias in three competitive GEC systems. We contribute a novel data augmentation technique for singular {\textquotedblleft}they{\textquotedblright} leveraging linguistic insights about its distribution relative to plural {\textquotedblleft}they{\textquotedblright}. We demonstrate that both this data augmentation technique and a refinement of a similar augmentation technique for masculine and feminine terms can generate training data that reduces bias in GEC systems, especially with respect to singular {\textquotedblleft}they{\textquotedblright} while maintaining the same level of quality."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lund-etal-2023-gender">
<titleInfo>
<title>Gender-Inclusive Grammatical Error Correction through Augmentation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Gunnar</namePart>
<namePart type="family">Lund</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kostiantyn</namePart>
<namePart type="family">Omelianchuk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Igor</namePart>
<namePart type="family">Samokhin</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>Proceedings of the 18th Workshop on Innovative Use of NLP for Building Educational Applications (BEA 2023)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Kochmar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jill</namePart>
<namePart type="family">Burstein</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andrea</namePart>
<namePart type="family">Horbach</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ronja</namePart>
<namePart type="family">Laarmann-Quante</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nitin</namePart>
<namePart type="family">Madnani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anaïs</namePart>
<namePart type="family">Tack</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Victoria</namePart>
<namePart type="family">Yaneva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zheng</namePart>
<namePart type="family">Yuan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Torsten</namePart>
<namePart type="family">Zesch</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>In this paper we show that GEC systems display gender bias related to the use of masculine and feminine terms and the gender-neutral singular “they”. We develop parallel datasets of texts with masculine and feminine terms, and singular “they”, and use them to quantify gender bias in three competitive GEC systems. We contribute a novel data augmentation technique for singular “they” leveraging linguistic insights about its distribution relative to plural “they”. We demonstrate that both this data augmentation technique and a refinement of a similar augmentation technique for masculine and feminine terms can generate training data that reduces bias in GEC systems, especially with respect to singular “they” while maintaining the same level of quality.</abstract>
<identifier type="citekey">lund-etal-2023-gender</identifier>
<identifier type="doi">10.18653/v1/2023.bea-1.13</identifier>
<location>
<url>https://aclanthology.org/2023.bea-1.13/</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>148</start>
<end>162</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Gender-Inclusive Grammatical Error Correction through Augmentation
%A Lund, Gunnar
%A Omelianchuk, Kostiantyn
%A Samokhin, Igor
%Y Kochmar, Ekaterina
%Y Burstein, Jill
%Y Horbach, Andrea
%Y Laarmann-Quante, Ronja
%Y Madnani, Nitin
%Y Tack, Anaïs
%Y Yaneva, Victoria
%Y Yuan, Zheng
%Y Zesch, Torsten
%S Proceedings of the 18th Workshop on Innovative Use of NLP for Building Educational Applications (BEA 2023)
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F lund-etal-2023-gender
%X In this paper we show that GEC systems display gender bias related to the use of masculine and feminine terms and the gender-neutral singular “they”. We develop parallel datasets of texts with masculine and feminine terms, and singular “they”, and use them to quantify gender bias in three competitive GEC systems. We contribute a novel data augmentation technique for singular “they” leveraging linguistic insights about its distribution relative to plural “they”. We demonstrate that both this data augmentation technique and a refinement of a similar augmentation technique for masculine and feminine terms can generate training data that reduces bias in GEC systems, especially with respect to singular “they” while maintaining the same level of quality.
%R 10.18653/v1/2023.bea-1.13
%U https://aclanthology.org/2023.bea-1.13/
%U https://doi.org/10.18653/v1/2023.bea-1.13
%P 148-162
Markdown (Informal)
[Gender-Inclusive Grammatical Error Correction through Augmentation](https://aclanthology.org/2023.bea-1.13/) (Lund et al., BEA 2023)
ACL