A taxonomy of bias-causing ambiguities in machine translation

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216224%3A14330%2F22%3A00139270" target="_blank" >RIV/00216224:14330/22:00139270 - isvavai.cz</a>

Result on the web

<a href="http://dx.doi.org/10.18653/v1/2022.gebnlp-1.18" target="_blank" >http://dx.doi.org/10.18653/v1/2022.gebnlp-1.18</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.18653/v1/2022.gebnlp-1.18" target="_blank" >10.18653/v1/2022.gebnlp-1.18</a>

Result language

angličtina

Original language name

A taxonomy of bias-causing ambiguities in machine translation

Original language description

This paper introduces a taxonomy of phenomena which cause bias in machine translation, covering gender bias (people being male and/or female), number bias (singular you versus plural you) and formality bias (informal you versus formal you). Our taxonomy is a formalism for describing situations in machine translation when the source text leaves some of these properties unspecified (eg. does not say whether doctor is male or female) but the target language requires the property to be specified (eg. because it does not have a gender-neutral word for doctor). The formalism described here is used internally by Fairslator, a web-based tool for detecting and correcting bias in the output of any machine translator.

Czech name

—

Czech description

—

Type

D - Article in proceedings

CEP classification

—

OECD FORD branch

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Project

—

Continuities

I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace

Publication year

2022

Confidentiality

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Article name in the collection

4th Workshop on Gender Bias in Natural Language Processing, GeBNLP 2022

ISBN

9781955917681

ISSN

—

e-ISSN

—

Number of pages

6

Pages from-to

168-173

Publisher name

Association for Computational Linguistics (ACL)

Place of publication

Seattle

Event location

Seattle

Event date

Jan 1, 2022

Type of event by nationality

CST - Celostátní akce

UT code for WoS article

—