Title :
Sparse Distributed Representations for Words with Thresholded Independent Component Analysis
Author :
Väyrynen, Jaakko J. ; Lindqvist, Lasse ; Honkela, Timo
Author_Institution :
Helsinki Univ. of Technol., Espoo
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.
Keywords :
independent component analysis; singular value decomposition; text analysis; vocabulary; multiple choice vocabulary task; singular value decomposition; sparse distributed representation; thresholded independent component analysis; word analysis; Humans; Image coding; Independent component analysis; Natural languages; Neural networks; Noise reduction; Singular value decomposition; Testing; Unsupervised learning; Vocabulary;
Conference_Titel :
Neural Networks, 2007. IJCNN 2007. International Joint Conference on
Conference_Location :
Orlando, FL
Print_ISBN :
978-1-4244-1379-9
Electronic_ISBN :
1098-7576
DOI :
10.1109/IJCNN.2007.4371100
