We investigate the problem of non-covariant behavior of policy gradient reinforcement learning algorithms. The policy gradient approach is amenable to analysis by information geom...
Speculative execution of information gathering plans can dramatically reduce the effect of source I/O latencies on overall performance. However, the utility of speculation is clos...
Speculative execution of information gathering plans can dramatically reduce the effect of source I/O latencies on overall performance. However, the utility of speculation is clos...
Writer’s Aid is a collaborative system that works simultaneously with an author editing a document providing assistance in identifying and inserting citation keys and autonomous...
Tamara Babaian, Barbara J. Grosz, Stuart M. Shiebe...
Cyclic definitions in description logics have until now been investigated only for description logics allowing for value restrictions. Even for the most basic language which allow...
This paper presents a new measure of semantic relatedness between concepts that is based on the number of shared words (overlaps) in their definitions (glosses). This measure is ...
This paper investigates a new approach for training discriminant classifiers when only a small set of labeled data is available together with a large set of unlabeled data. This a...
Multi-agent systems result from interactions between individual agents. Through these interactions different kinds of relationships are formed, which can impact substantially on t...
In this paper we present strategies for successfully capturing updates at Web sources. Web-based information agents provide integrated access to autonomous Web sources that can ge...