Automatic generation of weather forecast texts using comprehensive probabilistic generation-space models

• Published in: Natural language engineering Vol. 14; no. 4; pp. 431 - 455
• Main Author: BELZ, ANJA
• Format: Journal Article
• Language: English
• Published: Cambridge, UK Cambridge University Press 01.10.2008
• Subjects: Automatic Text Generation; Computational Linguistics; Computer Modeling and Simulation; Language; Natural language; Natural Language Generation; Natural Language Processing; Statistical Analysis; Statistical methods; Subject specialists; Trends; Weather forecasting

Two important recent trends in natural language generation are (i) probabilistic techniques and (ii) comprehensive approaches that move away from traditional strictly modular and sequential models. This paper reports experiments in which pcru – a generation framework that combines probabilistic gene...