Can I read SCAT: Second Chance Autoencoder for Textual Data on EtoBox?

SCAT: Second Chance Autoencoder for Textual Data by Goudarzvand, Somaieh; Gharibi, Gharib; Lee, Yugyung is a scholarly article available to read on EtoBox.

What is SCAT: Second Chance Autoencoder for Textual Data about?

We present a k-competitive learning approach for textual autoencoders named Second Chance Autoencoder (SCAT). SCAT selects the $k$ largest and smallest positive activations as the winner neurons, which gain the activation values of the loser neurons during the learning process, and thus focus on retrieving well-representative features for topics. Our experiments show that SCAT achieves outstanding performance in classification, topic modeling, and document visualization compared to LDA, K-Sparse, NVCTM, and KATE.

Author

Goudarzvand, Somaieh; Gharibi, Gharib; Lee, Yugyung

Published

2020

Language

EN