Project Halo

A project of the Knowledge Systems Group, UT-Austin

The goal of Project Halo is to create a Digital Aristotle - a Knowledge System capable of answering hard, novel questions and solving advanced problems in a broad range of scientific disciplines.

Project Halo is sponsored and managed by Vulcan, Inc. Vulcan has a nice website that describes the long-term goals of the project and provides a browser for viewing the results of the first phase of the Project ("the Pilot").

The Halo Pilot produced an important data point for the field of knowledge systems. It proved that knowledge systems can be built quickly, using off-the-shelf technologies, and they can perform very well on novel, hard questions. Here's what the Halo Pilot taught us.

As part of the SRI team, we're now in Phase II of Project Halo, which focuses on developing and testing a suite of tools to enable Subject Matter Experts (chemists, physicists and biologists, in particular) to build knowledge systems unassisted by knowledge engineers. The goals are closely aligned with those of DARPA's Rapid Knowledge Formation project (2000-2004), in which we were key participants.

Key Publications

• Clark, P., et. al., Capturing and Answering Questions Posed to a Knowledge-Based System , in Proceedings of the Fourth International Conference on Knowledge Capture (KCAP2007), 2007. (Abstract and pdf).
• Chaw, S., Fan, J., Tecuci, D., and Yeh, P. Capturing a Taxonomy of Failures During Automatic Interpretation of Questions Posed in Natural Language, in Proceedings of the Fourth International Conference on Knowledge Capture (KCAP2007), 2007. (Abstract and pdf).
• Barker, K., et.al., A Question-Answering System for AP Chemistry: Assessing KR&R Technologies, The Ninth International Conference on the Principles of Knowledge Representation and Reasoning (KR2004), 2004. (Abstract and pdf).
• Friedland, N., et.al., Towards a Quantitative, Platform-Independent Analysis of Knowledge Systems, The Ninth International Conference on the Principles of Knowledge Representation and Reasoning (KR2004), 2004. (Abstract and pdf).