Text-to-OverpassQL

• Verfasst von: Staniek, Michael [VerfasserIn]
• Verfasst von: Schumann, Raphael [VerfasserIn]
• Verfasst von: Züfle, Maike [VerfasserIn]
• Verfasst von: Riezler, Stefan [VerfasserIn]
• Titel: Text-to-OverpassQL
• Titelzusatz: a natural language interface for complex geodata querying of OpenStreetMap
• Verf.angabe: Michael Staniek, Raphael Schumann, Maike Züfle, Stefan Riezler
• E-Jahr: 2024
• Jahr: April 30, 2024
• Umfang: 14 S.
• Illustrationen: Illustrationen
• Fussnoten: Gesehen am 15.08.2024
• Titel Quelle: Enthalten in: Transactions of the Association for Computational Linguistics
• Ort Quelle: [Erscheinungsort nicht ermittelbar] : Association for Computational Linguistics, 2013
• Jahr Quelle: 2024
• Band/Heft Quelle: 12(2024), Seite 562-575
• ISSN Quelle: 2307-387X
• DOI: doi:10.1162/tacl_a_00654
• Datenträger: Online-Ressource
• Sprache: eng
• K10plus-PPN: 1898744955

Abstract

We present Text-to-OverpassQL, a task designed to facilitate a natural language interface for querying geodata from OpenStreetMap (OSM). The Overpass Query Language (OverpassQL) allows users to formulate complex database queries and is widely adopted in the OSM ecosystem. Generating Overpass queries from natural language input serves multiple use-cases. It enables novice users to utilize OverpassQL without prior knowledge, assists experienced users with crafting advanced queries, and enables tool-augmented large language models to access information stored in the OSM database. In order to assess the performance of current sequence generation models on this task, we propose OverpassNL,1 a dataset of 8,352 queries with corresponding natural language inputs. We further introduce task specific evaluation metrics and ground the evaluation of the Text-to-OverpassQL task by executing the queries against the OSM database. We establish strong baselines by finetuning sequence-to-sequence models and adapting large language models with in-context examples. The detailed evaluation reveals strengths and weaknesses of the considered learning strategies, laying the foundations for further research into the Text-to-OverpassQL task.