Automatic text processing: the transformation, analysis, and retrieval of information by computer
Automatic text processing: the transformation, analysis, and retrieval of information by computer
A self-organizing semantic map for information retrieval
SIGIR '91 Proceedings of the 14th annual international ACM SIGIR conference on Research and development in information retrieval
Self-Organizing Maps
The SOMLib Digital Library System
ECDL '99 Proceedings of the Third European Conference on Research and Advanced Technology for Digital Libraries
DEXA '99 Proceedings of the 10th International Conference on Database and Expert Systems Applications
The Growing Hierarchical Self-Organizing Map
IJCNN '00 Proceedings of the IEEE-INNS-ENNS International Joint Conference on Neural Networks (IJCNN'00)-Volume 6 - Volume 6
Self organization of a massive document collection
IEEE Transactions on Neural Networks
On wires and cables: content analysis of wikileaks using self-organising maps
WSOM'11 Proceedings of the 8th international conference on Advances in self-organizing maps
Hi-index | 0.00 |
With the increasing amount of information available in electronic document collections, methods for organizing these collections to allow topic-oriented browsing and orientation gain increasing importance. The SOMLib digital library system provides such an organization based on the Self-Organizing Map, a popular neural network model by producing a map of the document space. However, hierarchical relations between documents are hidden in the display. Moreover, with increasing size of document archives the required maps grow larger, thus leading to problems for the user in finding proper orientation within the map. In this case, a hierarchically structured representation of the document space would be highly preferable. In this paper, we present the Growing Hierarchical Self-Organizing Map, a dynamically growing neural network model, providing a content-based hierarchical decomposition and organization of document spaces. This architecture evolves into a hierarchical structure according to the requisites of the input data during an unsupervised training process. A recent enhancement of the training process further ensures proper orientation of the various topical partitions. This facilitates intuitive navigation between neighboring topical branches. The benefits of this approach are shown by organizing a real-world document collection according to semantic similarities.