Database learning for software agents
Mike Perkowitz, Oren Etzioni · 1994
With the amount of information available rapidly outstripping the ability of individuals to use it, we wish to explore how a software agent can learn a description of an information resource (such as a database on the internet) in order turn it into a well-understood tool at the agent’s disposal. An agent who could do this would have access to all the information it could find without having to cache the internet. As the agent makes queries to an information re-source, it will generalize from those queries and gener-ate hypotheses about the structure and content of the database. We therefore formulate this problem as a learning problem in which the input is (1) the agent’s model- its representation of the world; and (2) a se-ries of queries to and responses from a database. The