-
-
Luke McDowell
-
Oren Etzioni
-
Alon Halevy
-
University of Washington
-
In Proc. 3rd International Semantic Web Conference (ISWC2004),
Hiroshima, Japan,
7-11 November 2004.
-
Abstract:
-
The development of intelligent agents is a key part of the Semantic
Web vision, but how does an ordinary person tell an agent what to
do? One approach to this problem is to use RDF templates that
are authored once but then instantiated many times by ordinary
users. This approach, however, raises a number of challenges. For
instance, how can templates concisely represent a broad range of
potential uses, yet ensure that each possible instantiation will
function properly? And how does the agent explain its actions to the
humans involved? This paper addresses these challenges in the
context of a case study carried out on our fully-deployed system for semantic email agents. We describe how high-level
features of our template language enable the concise specification
of flexible goals. In response to the first question, we show that
it is possible to verify, in polynomial time, that a given template
will always produce a valid instantiation. Second, we show how to
automatically generate explanations for the agent's actions, and
identify cases where explanations can be computed in polynomial
time. These results both improve the usefulness of semantic email
and suggest general issues and techniques that may be applicable in
other Semantic Web systems.