Search
Now showing items 1-2 of 2
Random Manhattan Integer Indexing: Incremental L1 Normed Vector Space Construction
(2014)
Vector space models (VSMs) are mathematically well-defined frameworks that have been widely used in the distributional approaches to semantics. In VSMs, high-dimensional vectors represent linguistic entities. In an ...
Random indexing revisited
(Springer, 2015-05-17)
Random indexing is a method for constructing vector spaces at a reduced dimensionality.
Previously, the method has been proposed using Kanerva's sparse distributed memory model. Although intuitively plausible, this ...