@inproceedings{chavez-mulsa-spanakis-2020-evaluating,
title = "Evaluating Bias In {D}utch Word Embeddings",
author = "Ch{\'a}vez Mulsa, Rodrigo Alejandro and
Spanakis, Gerasimos",
editor = "Costa-juss{\`a}, Marta R. and
Hardmeier, Christian and
Radford, Will and
Webster, Kellie",
booktitle = "Proceedings of the Second Workshop on Gender Bias in Natural Language Processing",
month = dec,
year = "2020",
address = "Barcelona, Spain (Online)",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.gebnlp-1.6",
pages = "56--71",
abstract = "Recent research in Natural Language Processing has revealed that word embeddings can encode social biases present in the training data which can affect minorities in real world applications. This paper explores the gender bias implicit in Dutch embeddings while investigating whether English language based approaches can also be used in Dutch. We implement the Word Embeddings Association Test (WEAT), Clustering and Sentence Embeddings Association Test (SEAT) methods to quantify the gender bias in Dutch word embeddings, then we proceed to reduce the bias with Hard-Debias and Sent-Debias mitigation methods and finally we evaluate the performance of the debiased embeddings in downstream tasks. The results suggest that, among others, gender bias is present in traditional and contextualized Dutch word embeddings. We highlight how techniques used to measure and reduce bias created for English can be used in Dutch embeddings by adequately translating the data and taking into account the unique characteristics of the language. Furthermore, we analyze the effect of the debiasing techniques on downstream tasks which show a negligible impact on traditional embeddings and a 2{\%} decrease in performance in contextualized embeddings. Finally, we release the translated Dutch datasets to the public along with the traditional embeddings with mitigated bias.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chavez-mulsa-spanakis-2020-evaluating">
<titleInfo>
<title>Evaluating Bias In Dutch Word Embeddings</title>
</titleInfo>
<name type="personal">
<namePart type="given">Rodrigo</namePart>
<namePart type="given">Alejandro</namePart>
<namePart type="family">Chávez Mulsa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gerasimos</namePart>
<namePart type="family">Spanakis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Second Workshop on Gender Bias in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marta</namePart>
<namePart type="given">R</namePart>
<namePart type="family">Costa-jussà</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christian</namePart>
<namePart type="family">Hardmeier</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Will</namePart>
<namePart type="family">Radford</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kellie</namePart>
<namePart type="family">Webster</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Barcelona, Spain (Online)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Recent research in Natural Language Processing has revealed that word embeddings can encode social biases present in the training data which can affect minorities in real world applications. This paper explores the gender bias implicit in Dutch embeddings while investigating whether English language based approaches can also be used in Dutch. We implement the Word Embeddings Association Test (WEAT), Clustering and Sentence Embeddings Association Test (SEAT) methods to quantify the gender bias in Dutch word embeddings, then we proceed to reduce the bias with Hard-Debias and Sent-Debias mitigation methods and finally we evaluate the performance of the debiased embeddings in downstream tasks. The results suggest that, among others, gender bias is present in traditional and contextualized Dutch word embeddings. We highlight how techniques used to measure and reduce bias created for English can be used in Dutch embeddings by adequately translating the data and taking into account the unique characteristics of the language. Furthermore, we analyze the effect of the debiasing techniques on downstream tasks which show a negligible impact on traditional embeddings and a 2% decrease in performance in contextualized embeddings. Finally, we release the translated Dutch datasets to the public along with the traditional embeddings with mitigated bias.</abstract>
<identifier type="citekey">chavez-mulsa-spanakis-2020-evaluating</identifier>
<location>
<url>https://aclanthology.org/2020.gebnlp-1.6</url>
</location>
<part>
<date>2020-12</date>
<extent unit="page">
<start>56</start>
<end>71</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Evaluating Bias In Dutch Word Embeddings
%A Chávez Mulsa, Rodrigo Alejandro
%A Spanakis, Gerasimos
%Y Costa-jussà, Marta R.
%Y Hardmeier, Christian
%Y Radford, Will
%Y Webster, Kellie
%S Proceedings of the Second Workshop on Gender Bias in Natural Language Processing
%D 2020
%8 December
%I Association for Computational Linguistics
%C Barcelona, Spain (Online)
%F chavez-mulsa-spanakis-2020-evaluating
%X Recent research in Natural Language Processing has revealed that word embeddings can encode social biases present in the training data which can affect minorities in real world applications. This paper explores the gender bias implicit in Dutch embeddings while investigating whether English language based approaches can also be used in Dutch. We implement the Word Embeddings Association Test (WEAT), Clustering and Sentence Embeddings Association Test (SEAT) methods to quantify the gender bias in Dutch word embeddings, then we proceed to reduce the bias with Hard-Debias and Sent-Debias mitigation methods and finally we evaluate the performance of the debiased embeddings in downstream tasks. The results suggest that, among others, gender bias is present in traditional and contextualized Dutch word embeddings. We highlight how techniques used to measure and reduce bias created for English can be used in Dutch embeddings by adequately translating the data and taking into account the unique characteristics of the language. Furthermore, we analyze the effect of the debiasing techniques on downstream tasks which show a negligible impact on traditional embeddings and a 2% decrease in performance in contextualized embeddings. Finally, we release the translated Dutch datasets to the public along with the traditional embeddings with mitigated bias.
%U https://aclanthology.org/2020.gebnlp-1.6
%P 56-71
Markdown (Informal)
[Evaluating Bias In Dutch Word Embeddings](https://aclanthology.org/2020.gebnlp-1.6) (Chávez Mulsa & Spanakis, GeBNLP 2020)
ACL
- Rodrigo Alejandro Chávez Mulsa and Gerasimos Spanakis. 2020. Evaluating Bias In Dutch Word Embeddings. In Proceedings of the Second Workshop on Gender Bias in Natural Language Processing, pages 56–71, Barcelona, Spain (Online). Association for Computational Linguistics.