Two important recent trends in nlg are (i) probabilistic techniques and (ii) comprehensive approaches that move away from traditional strictly modular and sequential models. This paper reports experiments in which p cru — a generation framework that combines probabilistic generation methodology with a comprehensive model of the generation space — was used to semi-automatically create five different versions of a weather forecast generator. The generators were evaluated in terms of output quality, development time and computational efficiency against (i) human forecasters, (ii) a traditional handcrafted pipelined nlg system, and (iii) a halogen-style statistical generator. The most striking result is that despite acquiring all decision-making abilities automatically, the best p cru generators produce outputs of high enough quality to be scored more highly by human judges than forecasts written by experts.
展开▼
