English

SCAT: Second Chance Autoencoder for Textual Data

Computation and Language 2020-09-10 v3 Machine Learning

Abstract

We present a k-competitive learning approach for textual autoencoders named Second Chance Autoencoder (SCAT). SCAT selects the kk 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.

Keywords

Cite

@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}
}
R2 v1 2026-06-23T15:31:52.833Z