A Tool for Semantic-Aware Spatial Corpus Construction

2026-01-04

arXiv.org

AI Summary

This study addresses the scarcity of high-quality spatial natural language query corpora, which severely limits the performance of natural language interfaces for spatial databases. To this end, we propose SSCC, a semantic-aware corpus construction tool that, for the first time, integrates automatic spatial relation extraction with a template augmentation mechanism. By building a spatial relation knowledge base and generating and validating geometrically consistent and logically sound natural language–executable query pairs, SSCC significantly enhances both corpus quality and construction efficiency. Experimental results demonstrate that SSCC improves knowledge base construction efficiency by 53-fold and increases query pair validity by 2.5-fold, substantially reducing both time and human labor costs.

Technology Category

• Data Mining & Knowledge Management: Mining of Spatial, Temporal or Spatio-Temporal Data
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning
• Natural Language Processing: Information Extraction

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Web query analysis, representation and understanding
• Graph Algorithms and Modeling for the Web: Querying, indexing, and retrieval in Web-related graphs

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.

Problem

• spatial natural language interface
• corpus construction
• spatial query
• natural language processing
• knowledge base

Innovation

• semantic-aware
• spatial corpus construction
• natural language interface
• spatial relations
• template-augmented generation