Template-Based Question Answering over Linked Geospatial Data

TL;DR

This paper presents a question-answering system that interprets natural language questions and retrieves answers from linked geospatial data sources, leveraging a modular architecture and providing a benchmark dataset for evaluation.

Contribution

It introduces a novel natural language question-answering engine for linked geospatial data, integrated into the Frankenstein architecture, with a comprehensive evaluation and a gold standard dataset.

Findings

System successfully answers 201 natural language questions.

Provides a reusable component architecture for geospatial QA.

Offers a benchmark dataset for future research.

Abstract

Large amounts of geospatial data have been made available recently on the linked open data cloud and the portals of many national cartographic agencies (e.g., OpenStreetMap data, administrative geographies of various countries, or land cover/land use data sets). These datasets use various geospatial vocabularies and can be queried using SPARQL or its OGC-standardized extension GeoSPARQL. In this paper, we go beyond these approaches to offer a question-answering engine for natural language questions on top of linked geospatial data sources. Our system has been implemented as re-usable components of the Frankenstein question answering architecture. We give a detailed description of the system's architecture, its underlying algorithms, and its evaluation using a set of 201 natural language questions. The set of questions is offered to the research community as a gold standard dataset for the comparative evaluation of future geospatial question answering engines.