Automatically generating extraction patterns from untagged text
AAAI'96 Proceedings of the thirteenth national conference on Artificial intelligence - Volume 2
Hi-index | 0.00 |
A modular Information Extraction system is proposed to exploit special domain texts by processing metalinguistic segments where information about the rules or units of a technical sublanguage is put forward. Final output results in a Metalinguistic Information Database with computationally tractable data that can be useful not only for lexicographers and terminologists, but also for AI systems that need unorthodox information not readily available in existing semantic networks, lexicons or traditional ontologies.