ICA2TEXTUn sistema para la descripción automática en lenguaje natural de series temporales de calidad del aire

  1. Andrea Cascallar Fuentes 1
  2. Javier Gallego Fernández 1
  3. Alejandro Ramos Soto 1
  4. Anthony Saunders Estévez 2
  5. Alberto José Bugarín Diz 1
  1. 1 Universidade de Santiago de Compostela

    Universidade de Santiago de Compostela

    Santiago de Compostela, España

    ROR https://ror.org/030eybx10

  2. 2 Xunta de Galicia

    Xunta de Galicia

    Santiago de Compostela, España

    ROR https://ror.org/0181xnw06

SEPLN-PD 2022: Annual Conference of the Spanish Association for Natural Language Processing 2022: Projects and Demonstrations
  1. Miguel Á. Alonso (ed. lit.)
  2. Margarita Alonso-Ramos (ed. lit.)
  3. Carlos Gómez Rodríguez (ed. lit.)
  4. David Vilares Calvo (ed. lit.)
  5. Jesús Vilares (ed. lit.)

Editorial: CEUR Workshop Proceedings

Ano de publicación: 2022

Páxinas: 62-65

Tipo: Capítulo de libro


In this project we describe ICA2TEXT, a data-to-text system to automatically generate textualdescriptions about air quality time series provided by MeteoGalicia. Assessment results by two experts meteorologists werevery satisfactory, which confirm that the proposed textual descriptions fit this type of data and service both in content and layout.This system is currently in a final testing phase and will be deployed as a public service on the MeteoGalicia website