Abstract
This paper reports experiments in which pC RU — a generation framework that combines probabilistic generation methodology with a comprehensive model of the generation space — is used to semi-automatically create several versions of a weather forecast text generator. The generators are 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 pC RU generators receive higher scores from human judges than forecasts written by experts.
| Original language | English |
|---|---|
| Title of host publication | Human Language Technology Conference of the North American Chapter of the Association of Computational Linguistics |
| Place of Publication | Stroudsburg, PA, USA |
| Publisher | Association for Computational Linguistics |
| Pages | 164-171 |
| Number of pages | 8 |
| Publication status | Published - 1 Jan 2007 |
| Event | Human Language Technology Conference of the North American Chapter of the Association of Computational Linguistics - Rochester, New York, USA Duration: 1 Jan 2007 → … |
Conference
| Conference | Human Language Technology Conference of the North American Chapter of the Association of Computational Linguistics |
|---|---|
| Period | 1/01/07 → … |