🤖 AI Summary
This work proposes the first end-to-end natural language query system tailored for spatiotemporal databases, addressing the challenge that non-expert users face in directly utilizing specialized query languages. The system employs a three-tier interactive architecture that integrates a domain-specific knowledge base, entity linking, and an automatic physical query plan generation mechanism to efficiently translate natural language inputs into executable queries. Evaluated on four real-world and synthetic datasets, the system demonstrates high accuracy and effectiveness in query generation. An online demonstration platform has been deployed, significantly lowering the barrier to accessing and querying spatiotemporal data for non-specialist users.
📝 Abstract
The advancement of mobile computing devices and positioning technologies has led to an explosive growth of spatio-temporal data managed in databases. Representative queries over such data include range queries, nearest neighbor queries, and join queries. However, formulating those queries usually requires domain-specific expertise and familiarity with executable query languages, which would be a challenging task for non-expert users. It leads to a great demand for well-supported natural language queries (NLQs) in spatio-temporal databases. To bridge the gap between non-experts and query plans in databases, we present NL4ST, an interactive tool that allows users to query spatio-temporal databases in natural language. NL4ST features a three-layer architecture: (i) knowledge base and corpus for knowledge preparation, (ii) natural language understanding for entity linking, and (iii) generating physical plans. Our demonstration will showcase how NL4ST provides effective spatio-temporal physical plans, verified by using four real and synthetic datasets. We make NL4ST online and provide the demo video at https://youtu.be/-J1R7R5WoqQ.
