用时空知识图谱和大模型实现历史地图问答，让普通人也能轻松查询历史地理信息。
Geospatial Question Answering on Historical Maps Using Spatio-Temporal Knowledge Graphs and Large Language Models
- 构建历史地图的时空知识图谱，结合大语言模型实现自然语言问答。
- 在事实型和描述型问答任务中均达到高准确率和高召回率。
- 支持图像与网络信息融合，适合历史地理研究者与公众用户使用。
近年来，数字历史地图的矢量化特征提取技术取得进展。为充分挖掘这些特征价值，需将其组织成结构化、可高效访问的形态。问答系统是一种有效方式，使不熟悉数据库查询语言的用户也能以自然语言获取知识。本文构建了一个地理问答（GeoQA）系统，将从历史地图数据构建的时空知识图谱与大语言模型（LLMs）相结合。我们定义了本体以指导时空知识图谱构建，并研究了两类地理问答流程：事实型与描述型。额外引入历史地图图像及网络搜索结果作为上下文，增强描述型问答能力。评估结果显示，系统具备高交付率与高语义准确率。为进一步提升可用性，开发了支持交互式查询与可视化的网页应用。
原文摘要 · Abstract (English)
Recent advances have enabled the extraction of vectorized features from digital historical maps. To fully leverage this information, however, the extracted features must be organized in a structured and meaningful way that supports efficient access and use. One promising approach is question answering (QA), which allows users -- especially those unfamiliar with database query languages -- to retrieve knowledge in a natural and intuitive manner. In this project, we developed a GeoQA system by integrating a spatio-temporal knowledge graph (KG) constructed from historical map data with large language models (LLMs). Specifically, we have defined the ontology to guide the construction of the spatio-temporal KG and investigated workflows of two different types of GeoQA: factual and descriptive. Additional data sources, such as historical map images and internet search results, are incorporated into our framework to provide extra context for descriptive GeoQA. Evaluation results demonstrate that the system can generate answers with a high delivery rate and a high semantic accuracy. To make the framework accessible, we further developed a web application that supports interactive querying and visualization.
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。