Capturing a Taxonomy of Failures During Automatic
by Chaw, S.-Y., Fan, J.J., Tecuci, D.G., Yeh, P.Z.
The Proceedings of The Fourth International Conference on Knowledge Capture (K-CAP), October 2007.
An important problem in artificial intelligence is capturing, from natural language, formal representations that can be used by a reasoner to compute an answer. Many researchers have studied this problem by developing algorithms addressing specific phenomena in natural language interpretation, but few have studied (or cataloged)the types of failures associated with this problem. Knowledge of these failures can help researchers by providing a road map of open research problems and help practitioners by providing a checklist of issues to address in order to build systems that can achieve good performance on this problem. In this paper, we present a study – conducted in the context of the Halo Project – cataloging the types of failures that occur when capturing knowledge from natural language. We identified the categories of failures by examining a corpus of questions posed by naýve users to a knowledge based question answering system and empirically demonstrated the generality of our categorizations. We also describe available technologies that can address some of the failures we have identified.
 Adobe PDF |
 BibTeX |
 EndNote |
 |
Automated User-Centered Reasoning and Acquisition SystemThe 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. |
