A Tool for Semantic-Aware Spatial Corpus Construction
Wei Huang, Xieyang Wang, Jianqiu Xu, Guidong Zhang
TL;DR
SSCC addresses the scarcity of high-quality spatial NLQ corpora for NLIDB by introducing a geometry-aware two-stage framework: (i) knowledge base construction that determines spatial relations with geometric validation, and (ii) template-augmented query pair generation that maintains semantic fidelity through parameter synchronization. It generates NLQ–NLQ-EXE pairs via a template library and a knowledge-base-driven matching process, with diversity controls to ensure broad coverage. The approach yields a 53× improvement in knowledge base construction throughput and a 2.5× improvement in corpus effectiveness relative to a SpaCor baseline, including 91.7% query-pair validity on a test set. These results indicate substantial gains in both the efficiency and quality of spatial NLIDB training data, enabling scalable corpus construction for spatial databases such as SECONDO.
Abstract
Spatial natural language interface to database systems provide non-expert users with convenient access to spatial data through natural language queries. However, the scarcity of high-quality spatial natural language query corpora limits the performance of such systems. Existing methods rely on manual knowledge base construction and template-based dynamic generation, which suffer from low construction efficiency and unstable corpus quality. This paper presents semantic-aware spatial corpus construction (SSCC), a tool designed for constructing high-quality spatial natural language query and executable language query pair corpora. SSCC consists of two core modules: (i) a knowledge base construction module based on spatial relations, which extracts and determines spatial relations from datasets, and (ii) a template-augmented query pair corpus generation module, which produces query pairs via template matching and parameter substitution. The tool ensures geometric consistency and adherence to spatial logic in the generated spatial relations. Experimental results demonstrate that SSCC achieves (i) a 53x efficiency improvement for knowledge base construction and (ii) a 2.5x effectiveness improvement for query pair corpus. SSCC provides high-quality corpus support for spatial natural language interface training, substantially reducing both time and labor costs in corpus construction.