缓解英罗机器翻译中的性别偏见

摘要

机器翻译（MT）系统常常无法正确翻译性别，尤其是在从英语这样的性别中立语言转换为罗马尼亚语等有语法性别的目标语言时。这种偏差导致译文默认使用阳性形式，或强化性别刻板印象。我们提出一种混合流水线，将基于大语言模型（LLM）的性别分类与神经机器翻译（NMT）相结合，以缓解这一问题。该系统使用微调后的 LLM 检测英语句子中目标词的预期性别，并插入行内性别提示标签。随后，这些带标签的句子被送入一个经过微调的 Transformer 模型，以生成形态学上正确的罗马尼亚语译文。为此，我们引入了三个用于性别消歧和翻译的新数据集。与基线 MT 系统相比，我们的方法在 WinoMT 和 WinoGender 基准上的性别准确率提升了超过 40 个百分点。这是首个同时利用 LLM 推理和标签感知翻译来明确处理并评估英语-罗马尼亚语机器翻译中性别偏差的方法。

English

Machine translation (MT) systems often fail to correctly translate gender, especially when converting from a gender-neutral language like English to a gendered target language such as Romanian. This bias results in translations that default to masculine forms or reinforce gender stereotypes. We propose a hybrid pipeline to mitigate this issue by combining large language model (LLM)-based gender classification with neural machine translation (NMT). Our system uses a fine-tuned LLM to detect the intended gender of target words in English sentences and insert inline gender hint tags. These tagged sentences are then passed to a Transformer model fine-tuned to generate morphologically correct Romanian translations. To support this, we introduce three novel datasets for gender disambiguation and translation. Our approach improves gender accuracy on the WinoMT and WinoGender benchmarks by over 40 percentage points compared to a baseline MT system. This is the first method to explicitly address and evaluate gender bias in English-Romanian MT using both LLM inference and tag-aware translation.