Good, but not always Fair: An Evaluation of Gender Bias for three commercial Machine Translation Systems

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Piazzolla, Silvia Alma, Savoldi, Beatrice, Bentivogli, Luisa
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916178508644352
author Piazzolla, Silvia Alma
Savoldi, Beatrice
Bentivogli, Luisa
author_facet Piazzolla, Silvia Alma
Savoldi, Beatrice
Bentivogli, Luisa
contents Machine Translation (MT) continues to make significant strides in quality and is increasingly adopted on a larger scale. Consequently, analyses have been redirected to more nuanced aspects, intricate phenomena, as well as potential risks that may arise from the widespread use of MT tools. Along this line, this paper offers a meticulous assessment of three commercial MT systems - Google Translate, DeepL, and Modern MT - with a specific focus on gender translation and bias. For three language pairs (English/Spanish, English/Italian, and English/French), we scrutinize the behavior of such systems at several levels of granularity and on a variety of naturally occurring gender phenomena in translation. Our study takes stock of the current state of online MT tools, by revealing significant discrepancies in the gender translation of the three systems, with each system displaying varying degrees of bias despite their overall translation quality.
format Preprint
id arxiv_https___arxiv_org_abs_2306_05882
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Good, but not always Fair: An Evaluation of Gender Bias for three commercial Machine Translation Systems
Piazzolla, Silvia Alma
Savoldi, Beatrice
Bentivogli, Luisa
Computation and Language
Machine Translation (MT) continues to make significant strides in quality and is increasingly adopted on a larger scale. Consequently, analyses have been redirected to more nuanced aspects, intricate phenomena, as well as potential risks that may arise from the widespread use of MT tools. Along this line, this paper offers a meticulous assessment of three commercial MT systems - Google Translate, DeepL, and Modern MT - with a specific focus on gender translation and bias. For three language pairs (English/Spanish, English/Italian, and English/French), we scrutinize the behavior of such systems at several levels of granularity and on a variety of naturally occurring gender phenomena in translation. Our study takes stock of the current state of online MT tools, by revealing significant discrepancies in the gender translation of the three systems, with each system displaying varying degrees of bias despite their overall translation quality.
title Good, but not always Fair: An Evaluation of Gender Bias for three commercial Machine Translation Systems
topic Computation and Language
url https://arxiv.org/abs/2306.05882