Natural Language to Overpass Query: A Multi-Step Approach Using Task Decomposition and Key-Value Correction

• Published in: Proceedings / IEEE International Conference on Mobile Data Management pp. 1 - 11
• Main Authors: Zhang, Haodi, Zhu, Xinrui, Wang, Xuan, Song, Yuanfeng, Gu, Hanlin, Ma, Lin
• Format: Conference Proceeding
• Language: English
• Published: IEEE 02.06.2025
• Subjects: Data models; Error correction; Few shot learning; Large language models; Measurement; multistep prompting; Natural languages; OpenStreetMap; Performance gain; Syntactics; Text-to-OverpassQL
• ISSN: 2375-0324
• DOI: 10.1109/MDM65600.2025.00024

We investigate the challenge of generating OverpassQL from natural language in the Text-to-OverpassQL task and explore the data in the existing OverpassNL dataset. To address the structural mismatch between natural language and OverpassQL, we propose a task decomposition-based multi-step prompting approach that generates auxiliary information to help align natural language with OverpassQL structures, thereby enhancing model performance. Furthermore, we introduce a Key-Value Correction Module specifically targeting key-value pair matching difficulties in Text-to-OverpassQL tasks, designed to rectify potential syntactic errors and key-value mismatches in generated queries. Our experiments on GPT-3.5 Turbo and GPT-4 demonstrate absolute performance gains of \mathbf{1. 4 \%} and 0.6 % respectively. Under retrieval-augmented setting ablation, we achieve a more significant 3.5 % improvement with GPT-3.5 Turbo. Experimental results confirm that our method consistently improves performance across various models and configurations, particularly showing enhanced effectiveness in medium and small-scale models.