In several domains spatio-temporal data consisting of references to both space and time are collected in large volumes. Textual summaries of spatio-temporal data will complement the map displays used in Geographical Information Systems (GIS) to present data to decision makers. In the RoadSafe project we are working on developing Natural Language Generation (NLG) techniques to generate textual summaries of spatiotemporal numerical weather prediction data. Our approach exploits existing video processing techniques to analyse spatio-temporal weather prediction data and uses Qualitative Spatial Reasoning(QSR) techniques to reason with geographical data in order to compute the required content (information) for generating descriptions of geographically located events. Our evaluation shows that our approach extracts information similar to human experts. 1

Georeferenced data sets are often large and complex. Natural Language Generation (NLG) systems are beginning to emerge that generate texts from such data. One of the challenges these systems face is the generation of geographic descriptions referring to the location of events or patterns in the data. Based on our studies in the domain of meteorology we present a two staged approach to generating geographic descriptions. The first stage involves using domain knowledge based on the task context to select a frame of reference, and the second involves using constraints imposed by the end user to select values within a frame of reference. Because geographic concepts are inherently vague our approach does not guarantee a distinguishing description. Our evaluation studies show that NLG systems, because they can analyse input data exhaustively, can produce more fine-grained geographic descriptions that are more useful to end users than those generated by human experts. 1

This paper describes how spatial description selection can be tied to discourse and spatial context to improve text coherence in a natural language generation domain. The paper argues that, given coherence relations and discourse goals, the selection of spatial descriptions which reflect the hearer’s spatial expectations and echo the intended coherence relation can improve text coherence and thereby facilitate better text comprehension. Five coherence relations and algorithms for selecting spatial descriptions are presented and an experiment evaluating this hypothesis is presented. Context-based Spatial Description Selection 3 Context-based Spatial Description Selection One of the biggest challenges for data-to-text Natural Language Generation (NLG) systems describing geographic space is to determine appropriate spatial descriptions (SDs) for areas to be described. Typically such systems aim to report how geo-referenced data (data which has a geographic component) like pollen (Turner, Sripada, Reiter, & Davy, 2006), ice on roads (Turner, Sripada, Reiter, & Davy, 2008) or census data (Thomas &