Automatic Generation of Air Quality Index Textual Forecasts Using a Data-To-Text Approach

In this paper we present a data-to-text service which automatically produces textual forecasts about the air quality state for every municipality in Galicia (NW Spain) for the Galician Meteorology Agency (MeteoGalicia). We discuss the context and the details about the conception of the service, as well as a technical and formal description of the solution adopted. This approach complements and is integrated into GALiWeather, an application which issues daily textual short-term weather forecasts including information about the sky state, precipitation, wind and temperatures.

keywords: linguistic descriptions of data, natural language generation, data-to-text