用大模型标注性别标签，提升英译罗语的性别准确性
Mitigating Gender Bias in English to Romanian Machine Translation
- 用微调大模型识别英文中目标词的性别意图并插入标签
- 在双语数据集上，性别准确率比基线提升超40个百分点
- 适合关注性别公平的机器翻译研究者与多语言应用开发者
机器翻译系统在将英语等无性别语言翻译为罗马尼亚语等有性别语言时，常错误使用男性形式或强化性别刻板印象。本文提出一种混合流水线方法，结合大语言模型（LLM）进行性别分类与神经机器翻译（NMT）。系统首先用微调后的LLM检测英文句子中目标词的预期性别，并插入内联性别提示标签；随后将带标签的句子输入经过微调的Transformer模型，生成语法正确的罗马尼亚语翻译。为此，我们构建了三个新的性别消歧与翻译数据集。实验表明，该方法在WinoMT和WinoGender基准测试中，性别准确率较基线系统提升超过40个百分点。这是首个同时使用大模型推理与标签感知翻译来显式应对并评估英-罗语机器翻译性别偏见的方法。
原文摘要 · Abstract (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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。