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.
@article{arxiv.2005.06632,
title = {SCAT: Second Chance Autoencoder for Textual Data},
author = {Somaieh Goudarzvand and Gharib Gharibi and Yugyung Lee},
journal= {arXiv preprint arXiv:2005.06632},
year = {2020}
}