Gender-Neutral Machine Translation Strategies in Practice

TL;DR

This paper evaluates how well 21 machine translation systems handle gender neutrality, revealing a general lack of gender-neutral outputs but identifying some systems that adapt strategies based on language context.

Contribution

It provides an empirical assessment of MT systems' sensitivity to gender ambiguity and categorizes the strategies used for gender-neutral translation in practice.

Findings

Most MT systems do not produce gender-neutral translations when needed.

A few systems adapt strategies to achieve gender neutrality depending on language.

Gender stereotypes influence the choice of gender-neutral strategies.

Abstract

Gender-inclusive machine translation (MT) should preserve gender ambiguity in the source to avoid misgendering and representational harms. While gender ambiguity often occurs naturally in notional gender languages such as English, maintaining that gender neutrality in grammatical gender languages is a challenge. Here we assess the sensitivity of 21 MT systems to the need for gender neutrality in response to gender ambiguity in three translation directions of varying difficulty. The specific gender-neutral strategies that are observed in practice are categorized and discussed. Additionally, we examine the effect of binary gender stereotypes on the use of gender-neutral translation. In general, we report a disappointing absence of gender-neutral translations in response to gender ambiguity. However, we observe a small handful of MT systems that switch to gender neutral translation using specific strategies, depending on the target language.