Proceedings of International Conference on Neural Networks (ICNN'97) · 2002 · 222 citations · 1 references
ComputingComputer ScienceInformation TechnologyData MiningDatabasesInformation RetrievalDatabase ManagementDocument ManagementDocument StructureInformation Retrieval ArchitectureQuery ProcessingText StructureBrowsing InterfacesContent-addressable MemoryContent-addressable Memory (Cam)Data OrganizationIndexingRetrieval ArchitectureSelf-organizing MapsWeb Search Architecture
The paper introduces WEBSOM, a data organization system and content‑addressable memory. WEBSOM uses a two‑layer self‑organizing map that places documents as points on an upper map, enabling similarity‑based browsing and free‑form query retrieval, and is implemented in software on a general‑purpose computer. The system organized over one million documents across a map with more than 100,000 nodes and 315 inputs per node.
This paper describes a data organization system and genuine content-addressable memory called the WEBSOM. It is a two-layer self-organizing map (SOM) architecture where documents become mapped as points on the upper map, in a geometric order that describes the similarity of their contents. By standard browsing tools one can select from the map subsets of documents that are most similar mutually. It is also possible to submit free-form queries about the wanted documents whereby the WEBSOM locates the best-matching documents. The document map exemplified in this paper has over 100000 map nodes, with 315 inputs at each, and over 1000000 documents have been organized by it. The system has been implemented by software on a general-purpose computer.
1
Helge Ritter, Teuvo Kohonen · Biological Cybernetics · 1989 · 623 citations