Anchor & Transform: Learning Sparse Representations of Discrete Objects

Liang Paul Pu
Liang Paul Pu
Wang Yuan
Wang Yuan
Cited by: 0|Bibtex|Views71
Other Links: arxiv.org

Abstract:

Learning continuous representations of discrete objects such as text, users, and URLs lies at the heart of many applications including language and user modeling. When using discrete objects as input to neural networks, we often ignore the underlying structures (e.g. natural groupings and similarities) and embed the objects independentl...More

Code:

Data:

Full Text
Your rating :
0

 

Tags
Comments