High-Performance Knowledge Retrieval

KEYNET is a knowledge retrieval model and architecture based on the vector space model that unifies and extends many commonly used retrieval mechanisms. A distributed architecture, communication protocol and indexing algorithm for high-performance retrieval using this model has been developed. A prototype system has been built that achieves a throughput of 500 queries per second with a response time of less than one second on an 8-node network of workstations. The model and algorithm are designed for retrieval from a corpus of information objects in a single subject area. The objects need not be textual, and must be annotated with content labels. With current technology, the KEYNET system can be scaled up to support a corpus of several million information objects. Finally, the model allows for content labels that are semantically more complex than just attributes, keywords and subject classifications.


Technical Reports on KEYNET

A distributed approach to high-performance information retrieval

KEYNET: Fast indexing for semantically rich information retrieval

High-Performance, Distributed Information Retrieval

KEYNET: An architecture and protocol for high-performance semantically rich information retrieval

A unified approach to high-performance, vector-based information retrieval


The KEYNET Architecture


Ken Baclawski
207 Cullinane Hall
College of Computer Science
Northeastern University
360 Huntington Avenue
Boston, MA 02115
kenb@ccs.neu.edu
(617) 373-4631 / Fax: (617) 373-5121