GeoQAMap - Geographic Question Answering with Maps Leveraging LLM and Open Knowledge Base

Yu Feng, Linfang Ding, Guohui Xiao

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

10 Scopus citations

Abstract

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.

Original languageEnglish
Title of host publication12th International Conference on Geographic Information Science, GIScience 2023
EditorsRoger Beecham, Jed A. Long, Dianna Smith, Qunshan Zhao, Sarah Wise
PublisherSchloss Dagstuhl- Leibniz-Zentrum fur Informatik GmbH, Dagstuhl Publishing
ISBN (Electronic)9783959772884
DOIs
StatePublished - Sep 2023
Event12th International Conference on Geographic Information Science, GIScience 2023 - Leeds, United Kingdom
Duration: 12 Sep 202315 Sep 2023

Publication series

NameLeibniz International Proceedings in Informatics, LIPIcs
Volume277
ISSN (Print)1868-8969

Conference

Conference12th International Conference on Geographic Information Science, GIScience 2023
Country/TerritoryUnited Kingdom
CityLeeds
Period12/09/2315/09/23

Keywords

  • Geographic Question Answering
  • Knowledge Base
  • Large Language Models
  • SPARQL
  • Wikidata

Fingerprint

Dive into the research topics of 'GeoQAMap - Geographic Question Answering with Maps Leveraging LLM and Open Knowledge Base'. Together they form a unique fingerprint.

Cite this