Deconvolutional paragraph representation learning

Published

Journal Article

© 2017 Neural information processing systems foundation. All rights reserved. Learning latent representations from long text sequences is an important first step in many natural language processing applications. Recurrent Neural Networks (RNNs) have become a cornerstone for this challenging task. However, the quality of sentences during RNN-based decoding (reconstruction) decreases with the length of the text. We propose a sequence-to-sequence, purely convolutional and deconvolutional autoencoding framework that is free of the above issue, while also being computationally efficient. The proposed method is simple, easy to implement and can be leveraged as a building block for many applications. We show empirically that compared to RNNs, our framework is better at reconstructing and correcting long paragraphs. Quantitative evaluation on semi-supervised text classification and summarization tasks demonstrate the potential for better utilization of long unlabeled text data.

Duke Authors

Cited Authors

  • Zhang, Y; Shen, D; Wang, G; Gan, Z; Henao, R; Carin, L

Published Date

  • January 1, 2017

Published In

Volume / Issue

  • 2017-December /

Start / End Page

  • 4170 - 4180

International Standard Serial Number (ISSN)

  • 1049-5258

Citation Source

  • Scopus