@inproceedings{sandoval-etal-2023-rose,
title = "A Rose by Any Other Name would not Smell as Sweet: Social Bias in Names Mistranslation",
author = "Sandoval, Sandra and
Zhao, Jieyu and
Carpuat, Marine and
Daum{\'e} III, Hal",
editor = "Bouamor, Houda and
Pino, Juan and
Bali, Kalika",
booktitle = "Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing",
month = dec,
year = "2023",
address = "Singapore",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.emnlp-main.239",
doi = "10.18653/v1/2023.emnlp-main.239",
pages = "3933--3945",
abstract = "We ask the question: Are there widespread disparities in machine translations of names across race/ethnicity, and gender? We hypothesize that the translation quality of names and surrounding context will be lower for names associated with US racial and ethnic minorities due to these systems{'} tendencies to standardize language to predominant language patterns. We develop a dataset of names that are strongly demographically aligned and propose a translation evaluation procedure based on round-trip translation. We analyze the effect of name demographics on translation quality using generalized linear mixed effects models and find that the ability of translation systems to correctly translate female-associated names is significantly lower than male-associated names. This effect is particularly pronounced for female-associated names that are also associated with racial (Black) and ethnic (Hispanic) minorities. This disparity in translation quality between social groups for something as personal as someone{'}s name has significant implications for people{'}s professional, personal, and cultural identities, self-worth and ease of communication. Our findings suggest that more MT research is needed to improve the translation of names and to provide high-quality service for users regardless of gender, race, and ethnicity.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sandoval-etal-2023-rose">
<titleInfo>
<title>A Rose by Any Other Name would not Smell as Sweet: Social Bias in Names Mistranslation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sandra</namePart>
<namePart type="family">Sandoval</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jieyu</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marine</namePart>
<namePart type="family">Carpuat</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hal</namePart>
<namePart type="family">Daumé III</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Houda</namePart>
<namePart type="family">Bouamor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Juan</namePart>
<namePart type="family">Pino</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kalika</namePart>
<namePart type="family">Bali</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Singapore</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We ask the question: Are there widespread disparities in machine translations of names across race/ethnicity, and gender? We hypothesize that the translation quality of names and surrounding context will be lower for names associated with US racial and ethnic minorities due to these systems’ tendencies to standardize language to predominant language patterns. We develop a dataset of names that are strongly demographically aligned and propose a translation evaluation procedure based on round-trip translation. We analyze the effect of name demographics on translation quality using generalized linear mixed effects models and find that the ability of translation systems to correctly translate female-associated names is significantly lower than male-associated names. This effect is particularly pronounced for female-associated names that are also associated with racial (Black) and ethnic (Hispanic) minorities. This disparity in translation quality between social groups for something as personal as someone’s name has significant implications for people’s professional, personal, and cultural identities, self-worth and ease of communication. Our findings suggest that more MT research is needed to improve the translation of names and to provide high-quality service for users regardless of gender, race, and ethnicity.</abstract>
<identifier type="citekey">sandoval-etal-2023-rose</identifier>
<identifier type="doi">10.18653/v1/2023.emnlp-main.239</identifier>
<location>
<url>https://aclanthology.org/2023.emnlp-main.239</url>
</location>
<part>
<date>2023-12</date>
<extent unit="page">
<start>3933</start>
<end>3945</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Rose by Any Other Name would not Smell as Sweet: Social Bias in Names Mistranslation
%A Sandoval, Sandra
%A Zhao, Jieyu
%A Carpuat, Marine
%A Daumé III, Hal
%Y Bouamor, Houda
%Y Pino, Juan
%Y Bali, Kalika
%S Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing
%D 2023
%8 December
%I Association for Computational Linguistics
%C Singapore
%F sandoval-etal-2023-rose
%X We ask the question: Are there widespread disparities in machine translations of names across race/ethnicity, and gender? We hypothesize that the translation quality of names and surrounding context will be lower for names associated with US racial and ethnic minorities due to these systems’ tendencies to standardize language to predominant language patterns. We develop a dataset of names that are strongly demographically aligned and propose a translation evaluation procedure based on round-trip translation. We analyze the effect of name demographics on translation quality using generalized linear mixed effects models and find that the ability of translation systems to correctly translate female-associated names is significantly lower than male-associated names. This effect is particularly pronounced for female-associated names that are also associated with racial (Black) and ethnic (Hispanic) minorities. This disparity in translation quality between social groups for something as personal as someone’s name has significant implications for people’s professional, personal, and cultural identities, self-worth and ease of communication. Our findings suggest that more MT research is needed to improve the translation of names and to provide high-quality service for users regardless of gender, race, and ethnicity.
%R 10.18653/v1/2023.emnlp-main.239
%U https://aclanthology.org/2023.emnlp-main.239
%U https://doi.org/10.18653/v1/2023.emnlp-main.239
%P 3933-3945
Markdown (Informal)
[A Rose by Any Other Name would not Smell as Sweet: Social Bias in Names Mistranslation](https://aclanthology.org/2023.emnlp-main.239) (Sandoval et al., EMNLP 2023)
ACL