Modeling Spatial Knowledge for Generating Verbal and Visual Route Directions

Abstract

Abstract. Challenges in the development of state-of-the-art navigation tools involve the synchronous generation of user-tailored natural language directions and accompanying graphical representations. Of particular interest is the combination of indoor and outdoor scenarios. We describe an architecture for simultaneously generating route directions and suitable visualizations of the navigational context for walking directions. We present a representation model for 3D environments, the spatial model, and a route representation format based on OpenGIS standards, aiming at an elegant and efficient way to support users with and without knowledge about the environment.

Using Open Geographic Data to Generate Natural Language Descriptions for Hydrological Sensor Networks

“…Examples of such datasets include OpenStreetMap, Geonames, DBpedia, and many others inside and outside the geographical domain (e.g., the datasets available in the Linked Open Data cloud). Some authors [ 19 , 20 ] have successfully used this type of dataset in geographic problems (route directions).…”

Modeling Spatial Knowledge from Verbal Descriptions

“…Several recent studies have attempted to model navigation knowledge from human verbal descriptions [12,16]. The research challenge relies not only on the modeling of the cognitive abstractions that help to model such displacements, but also to map these concepts to appropriate linguistic constructs that can be in turn mapped towards a structured representation [13]. In particular, a close relationship between what is perceived and what can be logically described should be investigated and formalized.…”