This paper describes USI Answers -- a natural language question answering system for enterprise data. We report on the progress towards the goal of offering easy access to enterprise data to a large number of business users, most of whom are not familiar with the specific syntax or semantics of the underlying data sources. Additional complications come from the nature of the data, which comes both as structured and unstructured. The proposed solution allows users to express questions in natural language, makes apparent the system's interpretation of the query, and allows easy query adjustment and reformulation.
Gunning, David (Vulcan, Inc.) | Chaudhri, Vinay K. (SRI International) | Clark, Peter E. (Boeing Research and Technology) | Barker, Ken (University of Texas at Austin) | Chaw, Shaw-Yi (University of Texas at Austin) | Greaves, Mark (Vulcan, Inc.) | Grosof, Benjamin (Vulcan, Inc.) | Leung, Alice (Raytheon BBN Technologies Corporation) | McDonald, David D. (Raytheon BBN Technologies Corporation) | Mishra, Sunil (SRI International) | Pacheco, John (SRI International) | Porter, Bruce (University of Texas at Austin) | Spaulding, Aaron (SRI International) | Tecuci, Dan (University of Texas at Austin) | Tien, Jing (SRI International)
In the winter, 2004 issue of AI Magazine, we reported Vulcan Inc.'s first step toward creating a question-answering system called "Digital Aristotle." The goal of that first step was to assess the state of the art in applied Knowledge Representation and Reasoning (KRR) by asking AI experts to represent 70 pages from the advanced placement (AP) chemistry syllabus and to deliver knowledge-based systems capable of answering questions from that syllabus. This paper reports the next step toward realizing a Digital Aristotle: we present the design and evaluation results for a system called AURA, which enables domain experts in physics, chemistry, and biology to author a knowledge base and that then allows a different set of users to ask novel questions against that knowledge base. These results represent a substantial advance over what we reported in 2004, both in the breadth of covered subjects and in the provision of sophisticated technologies in knowledge representation and reasoning, natural language processing, and question answering to domain experts and novice users.
Friedland, Noah S., Allen, Paul G., Matthews, Gavin, Witbrock, Michael, Baxter, David, Curtis, Jon, Shepard, Blake, Miraglia, Pierluigi, Angele, Jurgen, Staab, Steffen, Moench, Eddie, Oppermann, Henrik, Wenke, Dirk, Israel, David, Chaudhri, Vinay, Porter, Bruce, Barker, Ken, Fan, James, Chaw, Shaw Yi, Yeh, Peter, Tecuci, Dan, Clark, Peter
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. This article presents the motivation and longterm 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.