English

Squeezing bottlenecks: exploring the limits of autoencoder semantic representation capabilities

Information Retrieval 2014-02-14 v1 Machine Learning Machine Learning

Abstract

We present a comprehensive study on the use of autoencoders for modelling text data, in which (differently from previous studies) we focus our attention on the following issues: i) we explore the suitability of two different models bDA and rsDA for constructing deep autoencoders for text data at the sentence level; ii) we propose and evaluate two novel metrics for better assessing the text-reconstruction capabilities of autoencoders; and iii) we propose an automatic method to find the critical bottleneck dimensionality for text language representations (below which structural information is lost).

Keywords

Cite

@article{arxiv.1402.3070,
  title  = {Squeezing bottlenecks: exploring the limits of autoencoder semantic representation capabilities},
  author = {Parth Gupta and Rafael E. Banchs and Paolo Rosso},
  journal= {arXiv preprint arXiv:1402.3070},
  year   = {2014}
}
R2 v1 2026-06-22T03:07:27.057Z