Semantic mapping (statistics)

The Semantic Mapping (SM) is a dimensionality reduction method that extract new features by clustering the original features in semantic clusters and combining those features mapped in the same cluster to generate a extracted feature. Given a data set, this method construct a projection matrix that can be used to mapping of data elements from one high dimensional space into reduced dimensional space. The Semantic Mapping can be applied in construction of text mining and information retrieval systems, as well as systems managing vectors of high dimensionality. The SM is an alternative to Principal Component Analysis and Latent Semantic Indexing methods.

The Semantic mapping can be also:

• In Semantic Web context - the name of a process done by semantic mappers.
• In Literacy context - the name of the process of generates a semantic map, a graphical model designed to help students identify important ideas and how these ideas fit together in a text.

See also

• Semantic mapper
• Dimensionality reduction
• Principal Component Analysis
• Latent Semantic Indexing

References

• Author for Semantic Mapping method
• [1] CORRÊA, R. F. and LUDERMIR, T. B. Dimensionality Reduction of very large document collections by Semantic. Proceedings of 6th Int. Workshop on Self-Organizing Maps (WSOM), 2007, ISBN 978-3-00-022473-7.

R. F. Correa 21:56, 10 July 2008 (UTC)