Abstract
This paper introduces our domain independent approach to “free generation”
from single RDF triples without using any domain dependent knowledge. Our approach is developed based on our argument that RDF representations carry rich linguistic information, which can be used to achieve readable domain independent generation. In order to examine to what extent our argument is realistic, we carry out an evaluation experiment, which is the first evaluation of this kind of domain independent generation in the field.
from single RDF triples without using any domain dependent knowledge. Our approach is developed based on our argument that RDF representations carry rich linguistic information, which can be used to achieve readable domain independent generation. In order to examine to what extent our argument is realistic, we carry out an evaluation experiment, which is the first evaluation of this kind of domain independent generation in the field.
| Original language | English |
|---|---|
| Title of host publication | Proceedings of the Eleventh European Workshop on Natural Language Generation |
| Editors | Stephan Busemann |
| Place of Publication | Stroudsburg, PA, USA |
| Publisher | Association for Computational Linguistics |
| Pages | 105-108 |
| Number of pages | 4 |
| Publication status | Published - 2007 |