Fifth International Joint Conference on Artificial Intelligence

Augmenting ATNs

and

Augmented Transition Networks have become a popular and effective tool for constructing natural language understanding systems. Our own system, PLANES, is based on a large “semantic grammar” which is implemented as an ATN network. In developing our system, we were frustrated by numerous problems and shortcomings in the basic ATN formalism. Consequently, we have augmented and extended the model to overcome some of these problems. We have also developed an optimizing compiler for ATN net-works which translates them into LISP functions and an interactive program which allows one to easily extend and modify an ATN grammar.


  • 75134 bytes

natural language processing

InProceedings

Morgan Kaufmann Publishers Inc.

1

Downloads: 945 downloads

UMBC ebiquity