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).
@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}
}