@inproceedings{mash-etal-2024-unmasking,
title = "Unmasking Biases: Exploring Gender Bias in {E}nglish-{C}atalan Machine Translation through Tokenization Analysis and Novel Dataset",
author = "Mash, Audrey and
Escolano, Carlos and
Sant, Aleix and
Melero, Maite and
de Luca Fornaciari, Francesca",
editor = "Calzolari, Nicoletta and
Kan, Min-Yen and
Hoste, Veronique and
Lenci, Alessandro and
Sakti, Sakriani and
Xue, Nianwen",
booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.lrec-main.1489/",
pages = "17144--17153",
abstract = "This paper presents a comprehensive evaluation of gender bias in English-Catalan machine translation, encompassing the creation of a novel language resource and an analysis of translation quality across four different tokenization models. The study introduces a new dataset derived from the MuST-SHE corpus, focusing on gender-neutral terms that necessitate gendered translations in Catalan. The results reveal noteworthy gender bias across all translation models, with a consistent preference for masculine forms. Notably, the study finds that when context is available, BPE and Sentencepiece Unigram tokenization methods outperform others, achieving higher accuracy in gender translation. However, when no context is provided, Morfessor outputs more feminine forms than other tokenization methods, albeit still a small percentage. The study also reflects that stereotypes present in the data are amplified in the translation output. Ultimately, this work serves as a valuable resource for addressing and mitigating gender bias in machine translation, emphasizing the need for improved awareness and sensitivity to gender issues in natural language processing applications."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mash-etal-2024-unmasking">
<titleInfo>
<title>Unmasking Biases: Exploring Gender Bias in English-Catalan Machine Translation through Tokenization Analysis and Novel Dataset</title>
</titleInfo>
<name type="personal">
<namePart type="given">Audrey</namePart>
<namePart type="family">Mash</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Carlos</namePart>
<namePart type="family">Escolano</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aleix</namePart>
<namePart type="family">Sant</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maite</namePart>
<namePart type="family">Melero</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Francesca</namePart>
<namePart type="family">de Luca Fornaciari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)</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">Min-Yen</namePart>
<namePart type="family">Kan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronique</namePart>
<namePart type="family">Hoste</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Lenci</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA and ICCL</publisher>
<place>
<placeTerm type="text">Torino, Italia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper presents a comprehensive evaluation of gender bias in English-Catalan machine translation, encompassing the creation of a novel language resource and an analysis of translation quality across four different tokenization models. The study introduces a new dataset derived from the MuST-SHE corpus, focusing on gender-neutral terms that necessitate gendered translations in Catalan. The results reveal noteworthy gender bias across all translation models, with a consistent preference for masculine forms. Notably, the study finds that when context is available, BPE and Sentencepiece Unigram tokenization methods outperform others, achieving higher accuracy in gender translation. However, when no context is provided, Morfessor outputs more feminine forms than other tokenization methods, albeit still a small percentage. The study also reflects that stereotypes present in the data are amplified in the translation output. Ultimately, this work serves as a valuable resource for addressing and mitigating gender bias in machine translation, emphasizing the need for improved awareness and sensitivity to gender issues in natural language processing applications.</abstract>
<identifier type="citekey">mash-etal-2024-unmasking</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.1489/</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>17144</start>
<end>17153</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Unmasking Biases: Exploring Gender Bias in English-Catalan Machine Translation through Tokenization Analysis and Novel Dataset
%A Mash, Audrey
%A Escolano, Carlos
%A Sant, Aleix
%A Melero, Maite
%A de Luca Fornaciari, Francesca
%Y Calzolari, Nicoletta
%Y Kan, Min-Yen
%Y Hoste, Veronique
%Y Lenci, Alessandro
%Y Sakti, Sakriani
%Y Xue, Nianwen
%S Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F mash-etal-2024-unmasking
%X This paper presents a comprehensive evaluation of gender bias in English-Catalan machine translation, encompassing the creation of a novel language resource and an analysis of translation quality across four different tokenization models. The study introduces a new dataset derived from the MuST-SHE corpus, focusing on gender-neutral terms that necessitate gendered translations in Catalan. The results reveal noteworthy gender bias across all translation models, with a consistent preference for masculine forms. Notably, the study finds that when context is available, BPE and Sentencepiece Unigram tokenization methods outperform others, achieving higher accuracy in gender translation. However, when no context is provided, Morfessor outputs more feminine forms than other tokenization methods, albeit still a small percentage. The study also reflects that stereotypes present in the data are amplified in the translation output. Ultimately, this work serves as a valuable resource for addressing and mitigating gender bias in machine translation, emphasizing the need for improved awareness and sensitivity to gender issues in natural language processing applications.
%U https://aclanthology.org/2024.lrec-main.1489/
%P 17144-17153
Markdown (Informal)
[Unmasking Biases: Exploring Gender Bias in English-Catalan Machine Translation through Tokenization Analysis and Novel Dataset](https://aclanthology.org/2024.lrec-main.1489/) (Mash et al., LREC-COLING 2024)
ACL