Geospatial Question Answering on Historical Maps Using Spatio-Temporal Knowledge Graphs and Large Language Models
OPEN ACCESS
Loading...
Author / Producer
Date
2025-12-08
Publication Type
Conference Paper
ETH Bibliography
yes
Citations
Scopus:
Altmetric
OPEN ACCESS
Data
Rights / License
Abstract
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.
Permanent link
Publication status
published
External links
Book title
GeoHCC '25: Proceedings of the 1st ACM SIGSPATIAL International Workshop on Human-Centered Geospatial Computing
Journal / series
Volume
Pages / Article No.
24 - 28
Publisher
Association for Computing Machinery
Event
33rd ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems (ACM SIGSPATIAL 2025)
Edition / version
Methods
Software
Geographic location
Date collected
Date created
Subject
GeoQA; Historical map; KG; LLM
Organisational unit
03466 - Hurni, Lorenz / Hurni, Lorenz
Notes
Funding
Related publications and datasets
Is new version of: https://doi.org/10.48550/arXiv.2508.21491
Is part of: https://doi.org/10.1145/3764917