An algorithm for finding nearest neighbours in (approximately) constant average time
Pattern Recognition Letters
Annual review of information science and technology, vol. 22
Information Processing and Management: an International Journal - The Potential for Improvments in Commerical Document Retrieval Systems
Computer image retrieval by features: suspect identification
CHI '93 Proceedings of the INTERACT '93 and CHI '93 Conference on Human Factors in Computing Systems
Introduction to Modern Information Retrieval
Introduction to Modern Information Retrieval
Fast Nearest-Neighbor Search in Dissimilarity Spaces
IEEE Transactions on Pattern Analysis and Machine Intelligence
Software Measurement: A Necessary Scientific Basis
IEEE Transactions on Software Engineering
Fast algorithm for assessing semantic similarity of texts
International Journal of Intelligent Information and Database Systems
| Hi-index | 0.00 |
This paper takes another look at information retrieval. It starts from the purposes of retrieval, looks at what people would like from a retrieval system, builds a conceptual model for how a retrieval system could work and from that determines what and how to do appropriate indexing to fit the model. The approach leads to the idea of the duality of indexing and retrieval. The ideas are illustrated by giving the design of a text based system and of a system to store pictures of faces. It is shown that the underlying mechanisms are the same for both systems and it suggests that other retrieval systems using this approach will have similar structures. Other implications of the approach are that retrieval and indexing can be monitored by the machine and the systems can learn to better respond to human needs. Ongoing research in this area is outlined.