Inproceedings,

Sparse distributed representations for words with thresholded independent component analysis

, , and .
Proceedings of the International Joint Conference on Neural Networks (IJCNN 2007), page 1031--1036. Orlando, Florida, USA, (2007)

Abstract

We show that independent component analysis (ICA) can be used to find distributed representations for words that can be further processed by thresholding to produce sparse representations. The applicability of the thresholded ICA representation is compared to singular value decomposition (SVD) in a multiple choice vocabulary task with three data sets.

Tags

Users

  • @jjv
  • @dblp

Comments and Reviews