Machine translation (MT) systems often translate terms with ambiguous gender (e.g., English term "the nurse") into the gendered form that is most prevalent in the systems' training data (e.g., "enfermera", the Spanish term for a female nurse). This often reflects and perpetuates harmful stereotypes present in society. With MT user interfaces in mind that allow for resolving gender ambiguity in a frictionless manner, we study the problem of generating all grammatically correct gendered translation alternatives. We open source train and test datasets for five language pairs and establish benchmarks for this task. Our key technical contribution is a novel semi-supervised solution for generating alternatives that integrates seamlessly with standard MT models and maintains high performance without requiring additional components or increasing inference overhead.

翻译：机器翻译系统常将具有性别歧义的术语（如英语术语"the nurse"）翻译为训练数据中最普遍的性别形式（例如西班牙语中表示女性护士的"enfermera"）。这种现象往往反映并固化了社会中存在的有害刻板印象。着眼于设计能够以无摩擦方式解决性别歧义的用户界面，我们研究了生成所有语法正确的性别化翻译替代方案的问题。我们开源了五个语言对的训练和测试数据集，并为该任务建立了基准。我们的核心技术贡献是一种新颖的半监督解决方案，用于生成替代翻译，该方案可与标准机器翻译模型无缝集成，在无需额外组件或增加推理开销的情况下保持高性能。