Artificial intelligence publications

We describe an algorithm that learns simple, low-coverage wrapper-like extraction patterns, which we then apply to conventional information extraction problems using boosting.

We address: modeling sequential data with HMMs, problems with previous methods: motivation, the maximum entropy Markov model, segmentation of FAQs: experiments and results.

Distributed SIPE (DSIPE) is a distributed planning system that provides decision support to human planners in a collaborative planning environment.

In this article, we describe a new paradigm for planning in complex, dynamic environments, which we term distributed, continual planning (DCP). We argue that developing DCP systems will be necessary…

A new approach to characterizing the performance of point- correspondence algorithms is presented.

This paper describes how techniques from the AI community, specifically reactive control, planning, and scheduling, could be leveraged to develop powerful, next-generation adaptive workflow engines that provide many of the…

We are constructing a system, called the Task-based Information Distribution Environment (TIDE), that delivers information to participants in a dynamic collaboration by evaluating the relevance of incoming and newly generated…

In this paper we extend a theory of action, IPT to try to elucidate these concepts. This attempt at elucidation is itself at most a prolegomena to a study that…

This article reports on the first phase of the continuous planning and execution framework (CPEF), a system that employs sophisticated plan-generation, -execution, -monitoring, and -repair capabilities to solve complex tasks…

A major theme of Johan’s Exploring Logical Dynamics is the move from using the tools of logic to analyze the products of cognitive processes to using those tools, including perhaps…