DisasterLex: An Expert Concept-to-Schema Knowledge Graph for Geospatial Reasoning in Disaster Analytics
Researchers have developed DisasterLex, a novel framework designed to improve natural language querying of disaster analytics databases. This system utilizes an Expert Knowledge Graph (EKG) to bridge user queries with complex geospatial schemas, enabling more accurate and context-aware data retrieval. DisasterLex orchestrates a four-stage process that identifies query entities, routes them to the correct domain, plans operations over causal relationships, and finally grounds the query into SQL, outperforming existing text-to-SQL methods. AI
IMPACT Improves accuracy and efficiency of accessing critical disaster data, potentially speeding up response efforts.