Gender Neutralization for an Inclusive Machine Translation: from Theoretical Foundations to Open Challenges
This addresses gender inclusivity in language technologies, particularly for Italian speakers, but is incremental as it reviews existing work rather than presenting new methods.
The paper tackles gender bias in machine translation by exploring gender-neutral translation from English to Italian, reviewing guidelines and technical challenges to propose solutions for more inclusive systems.
Gender inclusivity in language technologies has become a prominent research topic. In this study, we explore gender-neutral translation (GNT) as a form of gender inclusivity and a goal to be achieved by machine translation (MT) models, which have been found to perpetuate gender bias and discrimination. Specifically, we focus on translation from English into Italian, a language pair representative of salient gender-related linguistic transfer problems. To define GNT, we review a selection of relevant institutional guidelines for gender-inclusive language, discuss its scenarios of use, and examine the technical challenges of performing GNT in MT, concluding with a discussion of potential solutions to encourage advancements toward greater inclusivity in MT.