Neural navigation interfaces for Information Retrieval: Are they more than an appealing idea?

Abstract

Neural networks have recently been proposed for the construction of navigation interfaces for Information Retrieval systems. In this paper, we give an overview of some current research in this area. Most of the cited approaches use (variants) of the well-known Kohonen network. The Kohonen network implements a topology-preserving dimensionalityreducing mapping, which can be applied for information visualization. We identify a number of problems in the application of Kohonen networks for Information Retrieval, most notably scalability, reliability and retrieval effectiveness. To solve these problems we propose to use the Growing Cell Structures network, a variant of the Kohonen network which shows a more flexible adaptation to the domain structure.This network was tested on two standard test-collections, using a combined recall and precision measure, and compared to traditional IR methods such as the Vector Space Model and various clustering algorithms. The network performs at a competitive level ofeffectiveness, and is suitable for visualization purposes. However, the incremental training procedures for the networks result in a reliability problem, and the approach is computationally intensive. Also, the utility of the resulting maps for navigation will need further improvement.

A spatial user interface to the astronomical literature

“…The results presented here are contrary to the claim made in Zavrel (1996) that the Kohonen map does not scale well. We have also found convergence properties, and in particular stability, not to give rise to undue difficulties.…”

“…In fact there are quite varied approaches to visual information retrieval interfaces (Pörner 1995). Nor is the SOM approach the only neural network approach which could be used: for example Zavrel (1996) favours an adaptive grid (growing cell structures network). However we find the Kohonen approach to be a highly effective method.…”

Mining massive document collections by the WEBSOM method

“…Merkl has organized software library components [41][42][43] and studied hierarchical document map formation [44][45][46]. Document maps have also been created by Zavrel [47]. A system rather similar in appearance to the WEBSOM has been used to organize collections of scientific articles in the field of astronomy [48,49].…”

Visualization in information retrieval: a three-level analysis

“…The documents with topical relevance are clustered close to one another. Some systems using this approach and multidimensional scaling technique are Bead [19], Lin's works [66,67], WEBSOM [99], NETCLUST [117], DEPICT [90] and Galaxies [114].…”