Chronos让历史学家用自然语言操作AI,自动提取古籍信息。
Chronos: The AI Co-Historian

- 通过自然语言构建可定制的历史研究流程
- 在三类百年古籍上实现高精度信息提取
- 专为非技术历史学者设计,支持共享扩展
人工智能正加速科学发现,但历史研究领域仍缺乏专用工具。为此,我们提出Chronos——一位能与历史学家协作的AI助手。它支持研究人员通过自然语言创建和定制研究流程,并可将这些流程作为Chronos-Extensions共享。首个扩展Chronos-Extract实现了对历史文献图像扫描件中目标信息的自动化提取。我们在三个历史文献语料库上进行基准测试,结果表明其在跨越三个世纪、多种语言、版式和字体的原始史料上均达到高任务准确率。Chronos开源可用,历史学者可直接用于自有的一手与二手资料。
原文摘要 · Abstract (English)
AI is increasingly supporting, accelerating, and automating scientific discovery across subjects. Yet, the adoption of AI in historical research remains limited due to the lack of specialised solutions for historians. To change this, we introduce Chronos, an AI Co-Historian designed to support historians. It allows researchers to create and customize research workflows through natural-language interaction and share these as Chronos-Extensions with others. Chronos specifically addresses the need of historians for a tool that is specialised, non-technical, highly customizable, and facilitates extensive task evaluation. As a first extension, we introduce Chronos-Extract, which enables researchers to automate the targeted extraction of information from image scans of historical sources. We benchmark Chronos-Extract on three historical source corpora and find that it achieves high task-accuracy across primary sources spanning three centuries and diverse languages, layouts, and typefaces. Chronos is openly available and ready for historians to use on their own primary and secondary sources.
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。