Self-Organizing Maps for Interactive Search in Document Databases
Andreas Nürnberger, Aljoscha Klose, Rudolf Kruse · Studies in fuzziness and soft computing · 2003
In this contribution we discuss the application of self-organizing maps to arrange documents based on a similarity measure. For this, the concepts of self-organizing systems will be briefly reviewed, an overview of methods for the required document pre-processing and encoding will be given and applications of self-organizing maps in document retrieval will be discussed. Furthermore, a prototypical implementation of a software tool for interactive search in document databases will be presented, which combines conventional keyword search methods with the possibility to interactively explore a document collection. The usability of the presented approach is shown by sample searches.