Evaluating Gender Bias in the Translation of Gender-Neutral Languages into English
This addresses the problem of gender bias in machine translation for researchers and developers, but it is incremental as it extends an existing corpus and focuses on evaluation.
The paper tackles the lack of benchmarks for evaluating gender bias in machine translation from gender-neutral languages to English by introducing GATE X-E, a dataset with human translations from Turkish, Hungarian, Finnish, and Persian, containing 1250-1850 instances per language pair and gender variants, and uses it to evaluate a GPT-3.5 Turbo-based rewriting solution.
Machine Translation (MT) continues to improve in quality and adoption, yet the inadvertent perpetuation of gender bias remains a significant concern. Despite numerous studies into gender bias in translations from gender-neutral languages such as Turkish into more strongly gendered languages like English, there are no benchmarks for evaluating this phenomenon or for assessing mitigation strategies. To address this gap, we introduce GATE X-E, an extension to the GATE (Rarrick et al., 2023) corpus, that consists of human translations from Turkish, Hungarian, Finnish, and Persian into English. Each translation is accompanied by feminine, masculine, and neutral variants for each possible gender interpretation. The dataset, which contains between 1250 and 1850 instances for each of the four language pairs, features natural sentences with a wide range of sentence lengths and domains, challenging translation rewriters on various linguistic phenomena. Additionally, we present an English gender rewriting solution built on GPT-3.5 Turbo and use GATE X-E to evaluate it. We open source our contributions to encourage further research on gender debiasing.