Track:
Contents
Downloads:
Abstract:
It is argued that a knowledge representation language intended to be applied across diverse domains must be based on natural language. It is also indicated that such a representation language will facilitate the acquisition of knowledge from natural language and the interaction with other programs in need of obtaining some knowledge. The main aspects of a knowledge representation language based on these ideas are presented, and the results of such a language in its application to the task of acquiring knowledge from encyclopedic texts are briefly discussed.