Abstract
We describe a corpus of naturally occurring road ice weather forecasts and the associated weather prediction data they are based upon. We also show how observations from an analysis of this corpus have been applied to build a prototype Natural Language Generation (NLG) system for producing road ice forecasts. While this corpus occurs in a narrow domain, it has much wider applicability due to the nature of its spatial descriptions, whose primary communicative goal is to describe the interaction between meteorological parameters and geographic features.
| Original language | English |
|---|---|
| Title of host publication | Proceedings of LREC08 Workshop on Methodologies and Resources for Processing Spatial Language |
| Publisher | LREC |
| Pages | 28-35 |
| Number of pages | 8 |
| Publication status | Published - 2008 |
| Event | Methodologies and Resources for Processing Spatial Language - Marrakech, Morocco Duration: 31 May 2008 → 31 May 2008 http://www.lrec-conf.org/lrec2008/ |
Workshop
| Workshop | Methodologies and Resources for Processing Spatial Language |
|---|---|
| Country/Territory | Morocco |
| City | Marrakech |
| Period | 31/05/08 → 31/05/08 |
| Internet address |
Bibliographical note
Many thanks to our collaborators at Aerospace and Marine International UK, especially Keith Thomson and the other Meteorologists, for their helpful feedback and comments.The RoadSafe project is supported jointly by Aerospace and Marine International UK, and the UK Engineering and Physical Sciences Research Council (EPSRC), under a CASE PhD studentship.