Query expansion and neural network
Mohand Boughanem, Chantal Soulé Dupuy · Multimedia Information Retrieval · 1994
Automatic query expansion methods has historically been an important method for increasing the performance of Information Retrieval System (IRS). In this paper, we present an IRS based on three-layer neural network. This network is able to adapt itself to the user's needs by restructuring the information in the base, on the basis of the user's reaction to the retrieved documents. In other words, the user's judgments of the relevance or of the non relevance of retrieved documents are used to modify the weighted links connecting different term nodes in the network. The preliminary results indicate the usefulness of neural networks in adaptative information retrieval system.