<$BlogRSDUrl$>
Marcus P. Zillman, M.S., A.M.H.A. Author/Speaker/Consultant
Marcus P. Zillman, M.S., A.M.H.A. Author/Speaker/Consultant Internet Happenings, Events and Sources
Wednesday, October 18, 2006
The Semantic Indexing Project - Creating Tools To Identify the Latent Knowledge Found in Text http://www.knowledgesearch.org/
Semantic indexing is their name for a family of techniques for searching and organizing large data collections. The goal of semantic indexing is to find patterns in unstructured data (documents without descriptors such as keywords or special tags) and use those patterns to offer more effective search and categorization services. During the past four years, a team of linguists and computer scientists at NITLE and Middlebury College has developed a prototype Semantic Engine. This prototype was designed to address the universal problem of accessing and organizing large amounts of unstructured digital text. Using mathematical algorithms to index the latent semantic content of documents, the prototype engine has been demonstrated to drastically reduce, if not eliminate, the need for expensive and time-consuming metadata tagging, and to produce results superior to keyword searches in limited test domains. The Semantic Engine is at the center of our research and development mission. This has been added to the semantic web research section of Deep Web Research Subject Tracer™ Information Blog. This has been added to Knowledge Discovery Subject Tracer™ Information Blog.
posted by Marcus Zillman |
4:58 AM
