Generating a Question Answering Dataset About Geographic Changes in a Knowledge Graph

Most studies on semantic question answering ({QA}) are predominantly focused on encyclopedic knowledge graphs like {DBpedia} and Wikidata. These studies cover, if at all, the spatial and temporal characteristics of geospatial entities in isolation, not addressing them simultaneously. In this paper, we introduce a pipeline for creating question answering datasets for evaluating the reasoning capabilities of {QA} models in the context of geographic changes over time. This pipeline generates questions, {GeoSPARQL} queries, and corresponding answers by leveraging subgraph and query template extraction techniques.

  • Published in:
    Knowledge Engineering and Knowledge Management. EKAW 2024
  • Type:
    Inproceedings
  • Authors:
    Mitsios, Michalis; Punjani, Dharmen; Abdollahi, Sara; Gottschalk, Simon; Tsalapati, Eleni; Demidova, Elena; Koubarakis, Manolis
  • Year:
    2025

Citation information

Mitsios, Michalis; Punjani, Dharmen; Abdollahi, Sara; Gottschalk, Simon; Tsalapati, Eleni; Demidova, Elena; Koubarakis, Manolis: Generating a Question Answering Dataset About Geographic Changes in a Knowledge Graph, Knowledge Engineering and Knowledge Management. EKAW 2024, 2025, 471--489, Springer Nature Switzerland, https://link.springer.com/chapter/10.1007/978-3-031-77792-9_28, Mitsios.etal.2025a,

Associated Lamarr Researchers

lamarr institute person demidova elena e1663924269458 - Lamarr Institute for Machine Learning (ML) and Artificial Intelligence (AI)

Prof. Dr. Elena Demidova

Principal Investigator Hybrid ML to the profile