@inproceedings{alshahrani-etal-2022-roadblocks,
title = "Roadblocks in Gender Bias Measurement for Diachronic Corpora",
author = "Alshahrani, Saied and
Wali, Esma and
R Alshamsan, Abdullah and
Chen, Yan and
Matthews, Jeanna",
editor = "Tahmasebi, Nina and
Montariol, Syrielle and
Kutuzov, Andrey and
Hengchen, Simon and
Dubossarsky, Haim and
Borin, Lars",
booktitle = "Proceedings of the 3rd Workshop on Computational Approaches to Historical Language Change",
month = may,
year = "2022",
address = "Dublin, Ireland",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.lchange-1.15",
doi = "10.18653/v1/2022.lchange-1.15",
pages = "140--148",
abstract = "The use of word embeddings is an important NLP technique for extracting meaningful conclusions from corpora of human text. One important question that has been raised about word embeddings is the degree of gender bias learned from corpora. Bolukbasi et al. (2016) proposed an important technique for quantifying gender bias in word embeddings that, at its heart, is lexically based and relies on sets of highly gendered word pairs (e.g., mother/father and madam/sir) and a list of professions words (e.g., doctor and nurse). In this paper, we document problems that arise with this method to quantify gender bias in diachronic corpora. Focusing on Arabic and Chinese corpora, in particular, we document clear changes in profession words used over time and, somewhat surprisingly, even changes in the simpler gendered defining set word pairs. We further document complications in languages such as Arabic, where many words are highly polysemous/homonymous, especially female professions words.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="alshahrani-etal-2022-roadblocks">
<titleInfo>
<title>Roadblocks in Gender Bias Measurement for Diachronic Corpora</title>
</titleInfo>
<name type="personal">
<namePart type="given">Saied</namePart>
<namePart type="family">Alshahrani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Esma</namePart>
<namePart type="family">Wali</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Abdullah</namePart>
<namePart type="family">R Alshamsan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yan</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jeanna</namePart>
<namePart type="family">Matthews</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 3rd Workshop on Computational Approaches to Historical Language Change</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nina</namePart>
<namePart type="family">Tahmasebi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Syrielle</namePart>
<namePart type="family">Montariol</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andrey</namePart>
<namePart type="family">Kutuzov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Simon</namePart>
<namePart type="family">Hengchen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Haim</namePart>
<namePart type="family">Dubossarsky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lars</namePart>
<namePart type="family">Borin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Dublin, Ireland</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The use of word embeddings is an important NLP technique for extracting meaningful conclusions from corpora of human text. One important question that has been raised about word embeddings is the degree of gender bias learned from corpora. Bolukbasi et al. (2016) proposed an important technique for quantifying gender bias in word embeddings that, at its heart, is lexically based and relies on sets of highly gendered word pairs (e.g., mother/father and madam/sir) and a list of professions words (e.g., doctor and nurse). In this paper, we document problems that arise with this method to quantify gender bias in diachronic corpora. Focusing on Arabic and Chinese corpora, in particular, we document clear changes in profession words used over time and, somewhat surprisingly, even changes in the simpler gendered defining set word pairs. We further document complications in languages such as Arabic, where many words are highly polysemous/homonymous, especially female professions words.</abstract>
<identifier type="citekey">alshahrani-etal-2022-roadblocks</identifier>
<identifier type="doi">10.18653/v1/2022.lchange-1.15</identifier>
<location>
<url>https://aclanthology.org/2022.lchange-1.15</url>
</location>
<part>
<date>2022-05</date>
<extent unit="page">
<start>140</start>
<end>148</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Roadblocks in Gender Bias Measurement for Diachronic Corpora
%A Alshahrani, Saied
%A Wali, Esma
%A R Alshamsan, Abdullah
%A Chen, Yan
%A Matthews, Jeanna
%Y Tahmasebi, Nina
%Y Montariol, Syrielle
%Y Kutuzov, Andrey
%Y Hengchen, Simon
%Y Dubossarsky, Haim
%Y Borin, Lars
%S Proceedings of the 3rd Workshop on Computational Approaches to Historical Language Change
%D 2022
%8 May
%I Association for Computational Linguistics
%C Dublin, Ireland
%F alshahrani-etal-2022-roadblocks
%X The use of word embeddings is an important NLP technique for extracting meaningful conclusions from corpora of human text. One important question that has been raised about word embeddings is the degree of gender bias learned from corpora. Bolukbasi et al. (2016) proposed an important technique for quantifying gender bias in word embeddings that, at its heart, is lexically based and relies on sets of highly gendered word pairs (e.g., mother/father and madam/sir) and a list of professions words (e.g., doctor and nurse). In this paper, we document problems that arise with this method to quantify gender bias in diachronic corpora. Focusing on Arabic and Chinese corpora, in particular, we document clear changes in profession words used over time and, somewhat surprisingly, even changes in the simpler gendered defining set word pairs. We further document complications in languages such as Arabic, where many words are highly polysemous/homonymous, especially female professions words.
%R 10.18653/v1/2022.lchange-1.15
%U https://aclanthology.org/2022.lchange-1.15
%U https://doi.org/10.18653/v1/2022.lchange-1.15
%P 140-148
Markdown (Informal)
[Roadblocks in Gender Bias Measurement for Diachronic Corpora](https://aclanthology.org/2022.lchange-1.15) (Alshahrani et al., LChange 2022)
ACL
- Saied Alshahrani, Esma Wali, Abdullah R Alshamsan, Yan Chen, and Jeanna Matthews. 2022. Roadblocks in Gender Bias Measurement for Diachronic Corpora. In Proceedings of the 3rd Workshop on Computational Approaches to Historical Language Change, pages 140–148, Dublin, Ireland. Association for Computational Linguistics.