提出首个法语中性重写系统，用集体名词消除性别偏见
GeNRe: A French Gender-Neutral Rewriting System Using Collective Nouns
- 基于规则+生成数据微调模型，结合集体名词实现法语中性化
- 使用自建词典与Claude 3 Opus模型，性能接近规则系统
- 适合关注法语公平性、偏见缓解的研究者和应用开发者
自然语言处理领域大量文本存在性别偏见，尤其源于男性泛指（masculine generics），可能加剧刻板印象。性别重写任务旨在自动识别并替换性别化表达为中性或相反形式（如从阳性转为阴性）。尽管已有多种语言（英语、阿拉伯语、葡萄牙语、德语、法语）的系统，但仅英语研究过真正的中性化技术。本文提出首个基于集体名词的法语中性重写系统GeNRe，包含一个专为法语设计的规则系统（RBS），以及两个由RBS生成数据微调的语言模型。还探索了指令模型提升效果，发现Claude 3 Opus搭配自建词典可达到接近RBS的性能。本工作推动法语NLP中的性别偏见缓解技术发展。
原文摘要 · Abstract (English)
A significant portion of the textual data used in the field of Natural Language Processing (NLP) exhibits gender biases, particularly due to the use of masculine generics (masculine words that are supposed to refer to mixed groups of men and women), which can perpetuate and amplify stereotypes. Gender rewriting, an NLP task that involves automatically detecting and replacing gendered forms with neutral or opposite forms (e.g., from masculine to feminine), can be employed to mitigate these biases. While such systems have been developed in a number of languages (English, Arabic, Portuguese, German, French), automatic use of gender neutralization techniques (as opposed to inclusive or gender-switching techniques) has only been studied for English. This paper presents GeNRe, the very first French gender-neutral rewriting system using collective nouns, which are gender-fixed in French. We introduce a rule-based system (RBS) tailored for the French language alongside two fine-tuned language models trained on data generated by our RBS. We also explore the use of instruct-based models to enhance the performance of our other systems and find that Claude 3 Opus combined with our dictionary achieves results close to our RBS. Through this contribution, we hope to promote the advancement of gender bias mitigation techniques in NLP for French.
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。