AURA: Capturing Knowledge and Answering Questions on Science Textbooks
by Vinay K. Chaudhri and Peter E. Clark and Sunil Mishra and John Pacheco and Aaron Spaulding and Jing Tien
Institution: Proceedings of the 4th international conference on Knowledge capture
AURA is an AI-motivated system with a healthy intersec-tion with the sciences: its short-term goal is to enable do-main experts to construct declarative knowledge bases (KBs) from 50 pages of a science textbook for Physics, Chemistry, and Biology in a way that another user can pose questions similar to those in an Advanced Placement (AP) exam and get answers and explanations. In building AURA, and in line with the conference theme of The Inter-disciplinary Reach of AI, a key question and challenge has been: How much of the knowledge in the three domains can be captured through a generic knowledge capture and rea-soning capability and to what extent does it need to be spe-cialized for each domain? This paper contributes an answer to this question based on the experience of designing and implementing AURA. It also presents the first concise dis-tillation of the key ideas in AURA, integrating ideas from previous specialized publications.
The goal of this project is to build a generic knowledge acquisition capability for Physics, Chemistry, and Biology. Using the system, the scientists will be able to formulate their knowledge in the three science domains, and the high school students will be able to pose Advanced-Placement style questions and get user appropriate explanations.
|Chaudhri, Vinay K||Program Director|
|Clark, Peter E.||Allen Institute of Artificial Intelligence|
|Mishra, Sunil||Computer Scientist|
|Pacheco, John||Research Engineer|
|Spaulding, Aaron||Computer Scientist|