Deconvolutional Paragraph Representation Learning
Yizhe Zhang, Dinghan Shen, Guoyin Wang, Zhe Gan, Ricardo Henao, Lawrence Carin
Abstract
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.
BibTeX
@inproceedings{NIPS2017_4b4edc26,
author = {Zhang, Yizhe and Shen, Dinghan and Wang, Guoyin and Gan, Zhe and Henao, Ricardo and Carin, Lawrence},
booktitle = {Advances in Neural Information Processing Systems},
editor = {I. Guyon and U. Von Luxburg and S. Bengio and H. Wallach and R. Fergus and S. Vishwanathan and R. Garnett},
pages = {},
publisher = {Curran Associates, Inc.},
title = {Deconvolutional Paragraph Representation Learning},
url = {https://proceedings.neurips.cc/paper_files/paper/2017/file/4b4edc2630fe75800ddc29a7b4070add-Paper.pdf},
volume = {30},
year = {2017}
}