NL4ST: A Natural Language Query Tool for Spatio-Temporal Databases
Xieyang Wang, Mengyi Liu, Weijia Yi, Jianqiu Xu, Raymond Chi-Wing Wong
TL;DR
NL4ST addresses the challenge of non-experts querying spatio-temporal databases by mapping natural language inputs directly to spatio-temporal query plans, rather than SQL. It introduces a three-layer framework—knowledge preparation, natural language understanding, and physical plan generation—underpinned by a spatio-temporal knowledge base and a 5,000-template NLQ corpus, plus an LSTM-based type classifier and a rule-driven query mapper. The system demonstrates effective plan generation and execution, achieving high translatability and translation precision across multiple datasets, and provides interactive visualization and error guidance. This approach enables explicit control over execution semantics and index usage, offering a practical, user-friendly path for NL querying of complex spatio-temporal data.
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.