Traditional vector-based models use word co-occurrence counts from large corpora to represent lexical meaning. In this paper we present a novel approach for constructing semantic ...
—This study examines the ability of nonnegative matrix factorization (NMF) as a method for constructing semantic spaces, in which the meaning of each word is represented by a hig...
The representation of physical space has traditionally focused on keyphrases such as “Computer Science Building” or “Physics Department” that help us in describing and nav...
We propose the use of latent space models applied to local invariant features for object classification. We investigate whether using latent space models enables to learn patterns...
Florent Monay, Pedro Quelhas, Daniel Gatica-Perez,...