Name
Abstract | ||
|---|---|---|
Project Halo is a multistaged effort, sponsored by Vulcan Inc, aimed at creating Digital Aristotle, an application that will encompass much of the world's scientific knowledge and be capable of applying sophisticated problem solving to answer novel questions. Vulcan envisions two primary roles for Digital Aristotle: as a tutor to instruct students in the sciences and as an interdisciplinary research assistant to help scientists in their work. As a first step towards this goal, we have just completed a six-month pilot phase designed to assess the state of the art in applied knowledge representation and reasoning (KR&R). Vulcan selected three teams, each of which was to formally represent 70 pages from the advanced placement (AP) chemistry syllabus and deliver knowledge-based systems capable of answering questions on that syllabus. The evaluation quantified each system's coverage of the syllabus in terms of its ability to answer novel, previously unseen questions and to provide human-readable answer justifications. These justifications will play a critical role in building user trust in the question-answering capabilities of Digital Aristotle. Prior to the final evaluation, a "failure taxonomy" was collaboratively developed in an attempt to standardize failure analysis and to facilitate cross-platform comparisons. Despite differences in approach, all three systems did very well on the challenge, achieving performance comparable to the human median. The analysis also provided key insights into how the approaches might be scaled, while at the same time suggesting how the cost of producing Such systems might be reduced. This outcome leaves us highly optimistic that the technical challenges facing this effort in the years to come can be identified and overcome. This article presents the motivation and long-term goals of Project Halo, describes in detail the six-month first phase of the project-the Halo Pilot-its KR&R challenge, empirical evaluation, results, and failure analysis. The pilot's outcome is used to define challenges for the next phase of the project and beyond. |
Year | DOI | Venue |
|---|---|---|
2004 | 10.1609/aimag.v25i4.1783 | AI MAGAZINE |
Keywords | Field | DocType |
scientific knowledge,question answering,knowledge based system,advanced placement,knowledge representation and reasoning,failure analysis | TUTOR,Knowledge representation and reasoning,Syllabus,Sociology of scientific knowledge,Simulation,Computer science,Artificial intelligence,Advanced Placement | Journal |
Volume | Issue | ISSN |
25 | 4 | 0738-4602 |
Citations | PageRank | References |
34 | 3.79 | 9 |
Authors | ||
22 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Noah S. Friedland | 1 | 50 | 7.15 |
| Paul G. Allen | 2 | 41 | 5.83 |
| Gavin Matthews | 3 | 41 | 5.83 |
| Michael J. Witbrock | 4 | 360 | 55.04 |
| David Baxter | 5 | 72 | 7.31 |
| Jon Curtis | 6 | 419 | 24.88 |
| Blake Shepard | 7 | 54 | 6.74 |
| Pierluigi Miraglia | 8 | 59 | 8.21 |
| J. Angele | 9 | 213 | 28.97 |
| Steffen Staab | 10 | 6658 | 593.89 |
| Eddie Mönch | 11 | 41 | 6.12 |
| Henrik Oppermann | 12 | 56 | 6.09 |
| Dirk Wenke | 13 | 211 | 19.58 |
| David J. Israel | 14 | 961 | 291.98 |
| Vinay K. Chaudhri | 15 | 587 | 246.49 |
| Bruce Porter | 16 | 316 | 30.66 |
| Ken Barker | 17 | 834 | 83.23 |
| James Fan | 18 | 851 | 50.94 |
| Shaw Yi Chaw | 19 | 142 | 12.39 |
| Peter Z. Yeh | 20 | 380 | 28.42 |
| dan g tecuci | 21 | 131 | 12.84 |
| Peter Clark | 22 | 780 | 72.67 |