Correctness Comparison of ChatGPT‐4, Gemini, Claude‐3, and Copilot for Spatial Tasks
HH Hochmair, L Juhász, T Kemp - Transactions in GIS, 2024 - Wiley Online Library
Generative AI including large language models (LLMs) has recently gained significant
interest in the geoscience community through its versatile task‐solving capabilities including …
interest in the geoscience community through its versatile task‐solving capabilities including …
PolygonGNN: Representation learning for polygonal geometries with heterogeneous visibility graph
Polygon representation learning is essential for diverse applications, encompassing tasks
such as shape coding, building pattern classification, and geographic question answering …
such as shape coding, building pattern classification, and geographic question answering …
[HTML][HTML] The question answering system GeoQA2 and a new benchmark for its evaluation
We present the question answering engine GeoQA2 which is able to answer geospatial
questions over the union of knowledge graphs YAGO2 and YAGO2geo. We also present the …
questions over the union of knowledge graphs YAGO2 and YAGO2geo. We also present the …
Probabilistic qualitative spatial reasoning with applications to GeoQA
M Kazemi Beydokhti, M Duckham… - International Journal …, 2024 - Taylor & Francis
This paper explores the use of probabilistic and conventional qualitative spatial reasoning
(QSR) in the context of geospatial question answering (GeoQA) systems. The paper …
(QSR) in the context of geospatial question answering (GeoQA) systems. The paper …
[PDF][PDF] The question answering system geoqa2
We present the geospatial question answering engine GeoQA2 which is the most recent
version of the engine GeoQA, originally proposed by Punjani et al. GeoQA2 has been …
version of the engine GeoQA, originally proposed by Punjani et al. GeoQA2 has been …
[HTML][HTML] Schema Retrieval for Korean Geographic Knowledge Base Question Answering Using Few-Shot Prompting
S Lee, K Yu - ISPRS International Journal of Geo-Information, 2024 - mdpi.com
Geographic Knowledge Base Question Answering (GeoKBQA) has garnered increasing
attention for its ability to process complex geographic queries. This study focuses on schema …
attention for its ability to process complex geographic queries. This study focuses on schema …
[HTML][HTML] A DeBERTa-Based Semantic Conversion Model for Spatiotemporal Questions in Natural Language
W Lu, D Ming, X Mao, J Wang, Z Zhao, Y Cheng - Applied Sciences, 2025 - mdpi.com
To address current issues in natural language spatiotemporal queries, including insufficient
question semantic understanding, incomplete semantic information extraction, and …
question semantic understanding, incomplete semantic information extraction, and …
Geographic Knowledge Base Question Answering over OpenStreetMap
J Yang, H Jang, K Yu - ISPRS International Journal of Geo-Information, 2023 - mdpi.com
In recent years, question answering on knowledge bases (KBQA) has emerged as a
promising approach for providing unified, user-friendly access to knowledge bases …
promising approach for providing unified, user-friendly access to knowledge bases …
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 …
encyclopedic knowledge graphs like DBpedia and Wikidata. These studies cover, if at all …
Generating a Semantic Parsing Dataset for GeoKBQA Over OpenStreetMap
EH Jeong, TJ Yang, J Yang, K Yu - 2024 IEEE International …, 2024 - ieeexplore.ieee.org
This study tries to automatically construct a GeoKBQA dataset to transition to more
comprehensive, neural-based GeoKBQA. The current GeoKBQA datasets are lacking in …
comprehensive, neural-based GeoKBQA. The current GeoKBQA datasets are lacking in …