Text Meets Space: Geographic Content Extraction, Resolution and Information Retrieval

Abstract

In this half-day tutorial, we will review the basic concepts of, methods for, and applications of geographic information retrieval, also showing some possible applications in fields such as the digital humanities. The tutorial is organized in four parts. First we introduce some basic ideas about geography, and demonstrate why text is a powerful way of exploring relevant questions. We then introduce a basic end-toend pipeline discussing geographic information in documents, spatial and multi-dimensional indexing [19], and spatial retrieval and spatial filtering. After showing a range of possible applications, we conclude with suggestions for future work in the area.

Neural factoid geospatial question answering

“…Geospatial semantics is a broad area of research that focuses on understanding and formalizing geographic content [30]. Hu [30] identified six major research areas contributing to geospatial semantics through a systematic literature review: (1) semantic interoperability and ontologies, focused on identifying geospatial concepts to increase interoperability of geospatial data and services [31,39]; (2) digital gazetteers, that use geospatial ontologies to label geospatial objects and events with spatial and non-spatial properties and relations [21]; (3) geographic information retrieval, which focuses on extracting geospatial semantics from Web queries and retrieving content through semantic matching [35,41]; (4) geospatial linked data, which formally captures spatial objects and their relationships to establish spatially-aware knowledge bases [34]; (5) place semantics, which is a component of geospatial semantics and aimed at formalizing the notion of place [26,59]; and (6) qualitative reasoning over cognitive geographic concepts, to provide the ability to capture and reason over human qualitative spatial knowledge [17].…”