Article 272
  • A. Ramos-Soto, A. Bugarín, S. Barro, J. Taboada
  • IEEE Computational Intelligence Magazine, 2015 - Q1

Reseña sobre "Linguistic Descriptions for Automatic Generation of Textual Short-Term Weather Forecasts on Real Prediction Data"

In this paper, the authors present an innovative way computing with perceptions techniques and strategies for linguistic description of data, together with a natural language generations (NLG) system practical application, to deal with real-life applications that can automatically generate textual short-term weather forecasts for every municipality in Galicia. Furthermore, the automatically generated textual forecasts were thoroughly evaluated by a meteorologist in order to assess the quality of their contents and to check whether his expert knowledge was included correctly. The real data is obtained from the Galician Meteorology Agency (MeteoGalicia), and then, the application, which is named GALiWeather, extracts relevant information into intermediate descriptions using linguistic variables and temporal references. The obtained results show that the textual forecasts fulfill the expert’s requirements in a very high degree (4.83 out of 5). Finally, GALiWeather will be released as a real service, offering custom forecasts for a wide public.
Keywords: linguistic descriptions of data, natural language generation, computing with perceptions, open data
Canonical link