Spreading activation methods in information retrieval — A connectionist approach

doi:10.1016/0925-2312(92)90041-M

Neurocomputing

Volume 4, Issues 1–2, February 1992, Pages 31-36

https://doi.org/10.1016/0925-2312(92)90041-M Get rights and content

Abstract

An improvement of spreading activation methods in information retrieval (IR) systems is designed. As a new tool an appropriate type of neural network was developed. The neural network, called RETRIEVALNET here, is a composition of two subnets (recursive and feed-forward) extended by a layer of inhibitory neurons.

References (9)

E.A Fox et al.
Practical enhanced Boolean retrieval: experiences with the SMART and SIRE systems
Inform. Processing Management
(1988)
W.S Cooper
Getting beyond Boole
Inform. Processing Management
(1988)
G Salton
The use of extended Boolean logic in information retrieval
G Salton et al.
Term-weighting approaches in automatic text retrieval
Inform. Processing Management
(1988)

There are more references available in the full text version of this article.

Cited by (0)

View full text

PaperSpreading activation methods in information retrieval — A connectionist approach

Abstract

Inform. Processing Management

Getting beyond Boole

Inform. Processing Management

The use of extended Boolean logic in information retrieval

Term-weighting approaches in automatic text retrieval

Inform. Processing Management

Paper
Spreading activation methods in information retrieval — A connectionist approach