In this paper, we describe the lessons we learned in developing AgentBuilder, a commercial system for rapidly creating agents that extract information from web sites. AgentBuilder...
The World Wide Web (WWW) has provided us with a plethora of information. However, given its unstructured format, this information is useful mainly to humans and cannot be effectiv...
This paper addresses the various facets of emergent semantics in content retrieval systems such as Knowledge Sifter, an architecture and system based on the use of specialized agen...
In the past, many attempts have been made to improve the interoperability between different Web-based information systems. In most approaches the remaining problems are still twof...
In this paper, we define and study a novel search problem: Comparative Web Search (CWS). The task of CWS is to seek relevant and comparative information from the Web to help users...