Claims in connection with the mechanisms that will be used to capture the knowledge

1. START has been used for years in unrestricted Web-based environments for question answering. The HAWK system will build on START, enabling knowledge acquisition in the same environment.

2. When START and HAWK are integrated into the WWW environment, they can be used as a vehicle for collaborative knowledge acquisition from a large number of contributing domain experts.

3. Recapturing languagelike knowledge previously entered into databases takes that knowledge out of a representational black hole and makes it generally available for machine reasoning. We have an early demonstration of a system that performs such recapture.