How adaptive is adaptive machine translation, really? A gender-neutral language use case

Publication type
C1
Publication status
Published
Authors
Kostikova, A., Daems, J, & Lazarov, T.
Editor
Eva Vanmassenhove, Beatrice Savoldi, Luisa Bentivogli, Joke Daems and Janiça Hackenbuchner
Series
Proceedings of the First Workshop on Gender-Inclusive Translation Technologies
Pagination
95-97
Publisher
Open Press TiU (Tilburg)
Conference
First International Workshop on Gender-Inclusive Translation Technologies (GITT) at EAMT 2023 (Tampere, Finland)
Download
(.pdf)
View in Biblio
(externe link)

Abstract

This study examines the effectiveness of
adaptive machine translation (AMT) for
gender-neutral language (GNL) use in
English-German translation using the
ModernMT engine. It investigates gender bias
in initial output and adaptability to two distinct
GNL strategies, as well as the influence of
translation memory (TM) use on adaptivity.
Findings indicate that despite inherent gender
bias, machine translation (MT) systems show
potential for adapting to GNL with appropriate
exposure and training, highlighting the
importance of customisation, exposure to
diverse examples, and better representation of
different forms for enhancing gender-fair
translation strategies.