TY - GEN
T1 - GeoQAMap - Geographic Question Answering with Maps Leveraging LLM and Open Knowledge Base
AU - Feng, Yu
AU - Ding, Linfang
AU - Xiao, Guohui
N1 - Publisher Copyright:
© Yu Feng, Linfang Ding, and Guohui Xiao.
PY - 2023/9
Y1 - 2023/9
N2 - GeoQA (Geographic Question Answering) is an emerging research field in GIScience, aimed at answering geographic questions in natural language. However, developing systems that seamlessly integrate structured geospatial data with unstructured natural language queries remains challenging. Recent advancements in Large Language Models (LLMs) have facilitated the application of natural language processing in various tasks. To achieve this goal, this study introduces GeoQAMap, a system that first translates natural language questions into SPARQL queries, then retrieves geospatial information from Wikidata, and finally generates interactive maps as visual answers. The system exhibits great potential for integration with other geospatial data sources such as OpenStreetMap and CityGML, enabling complicated geographic question answering involving further spatial operations.
AB - GeoQA (Geographic Question Answering) is an emerging research field in GIScience, aimed at answering geographic questions in natural language. However, developing systems that seamlessly integrate structured geospatial data with unstructured natural language queries remains challenging. Recent advancements in Large Language Models (LLMs) have facilitated the application of natural language processing in various tasks. To achieve this goal, this study introduces GeoQAMap, a system that first translates natural language questions into SPARQL queries, then retrieves geospatial information from Wikidata, and finally generates interactive maps as visual answers. The system exhibits great potential for integration with other geospatial data sources such as OpenStreetMap and CityGML, enabling complicated geographic question answering involving further spatial operations.
KW - Geographic Question Answering
KW - Knowledge Base
KW - Large Language Models
KW - SPARQL
KW - Wikidata
UR - http://www.scopus.com/inward/record.url?scp=85172403010&partnerID=8YFLogxK
U2 - 10.4230/LIPIcs.GIScience.2023.28
DO - 10.4230/LIPIcs.GIScience.2023.28
M3 - Conference contribution
AN - SCOPUS:85172403010
T3 - Leibniz International Proceedings in Informatics, LIPIcs
BT - 12th International Conference on Geographic Information Science, GIScience 2023
A2 - Beecham, Roger
A2 - Long, Jed A.
A2 - Smith, Dianna
A2 - Zhao, Qunshan
A2 - Wise, Sarah
PB - Schloss Dagstuhl- Leibniz-Zentrum fur Informatik GmbH, Dagstuhl Publishing
T2 - 12th International Conference on Geographic Information Science, GIScience 2023
Y2 - 12 September 2023 through 15 September 2023
ER -