Recent Extensions to BI: A Resource-Bounded Information Gathering System

BIG (resource-Bounded Information Gathering) is a next generation information gathering agent which integrates several areas of Artificial Intelligence research under a single umbrella. To date, reported work has presented the rationale, architecture, and implementation of the system. This has included planning, reasoning about resource trade-offs of different possible gathering and extraction approaches, information extraction from both structured as well as unstructured documents, and opportunistic refinement of the search process using the extracted information. In this paper, we present recent improvements made to BIG, which make it a more versatile and robust system. These include documentation classification to handle distraction, sophisticated information fusion techniques, and finally the logistics behind search precision versus coverage tradeoffs. We also present empirical evaluations which show the performance improvement due to these extensions.