Abstract
Project Halo is a multi-staged effort, sponsored by Vulcan Inc, aimed at creating the Digital Aristotle (DA), 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 the 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, there was 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 the Digital Aristotle.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.
Full support for this research was provided by Vulcan Inc. as part of Project Halo.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Voorhees, E.M.: The TREC-8 Question Answering Track Report. In: The Eighth Text RE-trieval Conference (TREC-8), pp. 77–82 (1999)
Brown, T.L., et al.: Chemistry: The Central Science. Prentice Hall, New Jersey (2003)
Barker, K., et al.: A Question-answering System for AP Chemistry: Assessing KRR Technologies. In: 9th International Conference on Principles of Knowledge Representation and Reasoning, Whistler, Canada (2004)
Angele, J., et al.: Ontology-based Query and Answering in Chemistry: Ontonova @ Project Halo (2003)
Witbrock, M., Matthews, G.: Cycorp Project Halo Final Report (2003)
Barker, K., Porter, B., Clark, P.: A Library of Generic Concepts for Composing Knowledge Bases. In: Proc. 1st Int. Conf. on Knowledge Capture (K-Cap 2001), pp. 14–21 (2001)
Novak, G.: Conversion of Units of Measurement. IEEE Transactions on Software Engineering 21(8), 651–661 (1995)
Clancey, W.J.: The epistemology of a rule-based expert system: A framework for explanation. Artificial Intelligence 20, 215–251 (1983)
Voorheese, E.M.: Overview of TREC Question Answering Task (2001)
Chaudhri, V., Fikes, R. (eds.): AAAI Fall Symposium on Question Answering Systems. AAAI, Menlo Park (1999)
Neches, R., et al.: Enabling Technology for Knowledge Sharing. AI Magazine 12(3), 36–56 (1991)
Cohen, P., et al.: The DARPA High Performance Knowledge Bases Project. AI Magazine 19(4), 25–49 (1998)
Brachman, R.J., et al.: Reducing CLASSIC to Practice: Knowledge Representation Theory Meets Reality. Artificial Intelligence Journal 114, 203–237 (1999)
Keyes, J.: Why Expert Systems Fail? IEEE Expert 4, 50–53 (1989)
Batanov, D., Brezillon, P. (eds.): First International Conference on Successes and Failures of Knowledge-based Systems in Real World Applications, Asian Institute of Technology, Bangkok, Thailand (1996)
Pool, M., Murray, J.F.K., Mehrotra, M., Schrag, R., Blythe, J., Kim, H.C.J., Miraglia, P., Russ, T., Schneider, D.: Evaluation of Expert Knowledge Elicited for Critiquing Military Courses of Action. In: Proceedings of the Second International Conference on Knowledge Capture, KCAP 2003 (2003)
Van Gelder, A., Ross, K.A., Schlipf, J.S.: The well-founded semantics for general logic programs. Journal of the ACM 38(3), 620–650 (1991)
Kifer, M., Lozinskii, E.: A framework for an efficient implementation of deductive databases. In: Proceedings of the 6th Advanced Database Symposium, Tokyo, August 1986, pp. 109–116 (1986)
Kifer, M., Lausen, G., Wu, J.: Logical foundations of object-oriented and framebased languages. Journal of the ACM 42, 741–843 (1995)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2005 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Angele, J., Moench, E., Oppermann, H., Wenke, D. (2005). Halo I: A Controlled Experiment for Large Scale Knowledge Base Development. In: Baral, C., Greco, G., Leone, N., Terracina, G. (eds) Logic Programming and Nonmonotonic Reasoning. LPNMR 2005. Lecture Notes in Computer Science(), vol 3662. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11546207_3
Download citation
DOI: https://doi.org/10.1007/11546207_3
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-28538-0
Online ISBN: 978-3-540-31827-9
eBook Packages: Computer ScienceComputer Science (R0)