Intelligent Query Answering Through Rule Learning and Generalization

摘要

The Department of Defense (DoD) relies heavily on information systems to complete a myriad of tasks, from day-to-day personnel actions to mission critical imagery retrieval, intelligence analysis, and mission planning. The astronomical growth in size and performance of data storage systems leads to problems in processing the amount of data returned on any given query. Typical relational database systems return a set of unordered records. This approach is acceptable in small information systems, but in large systems, such as military image retrieval systems with more than 1 million records, it requires considerable time (often hours to days) to sort through thousands of records and select the relevant for analysis. This research introduces Intelligent Query Answering (IQA) as a novel approach to information retrieval. IQA implements the FOIL algorithm to learn rules based upon user feedback QUI90. The Winnow algorithm adjusts rule weights based on user classification, for improved document orderings BLU97. A semantic tree specific to the domain allows rule generalization across the domain. Testing shows a document sort accuracy rate of 63-93% against a controlled test dataset and 78-89% accuracy rate on a subset of declassified National Air Intelligence Center imagery metadata. These results demonstrate that this research provides groundwork for future efforts in rule learning and rule generalization in the information retrieval field.