# Deconvolutional Paragraph Representation Learning

arXiv: https://arxiv.org/abs/1708.04729 · HTML: https://mlsanity.com/paper/1708.04729/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 Aug 2017.

## Built on by (most cited first, 6 of 6)

- [Hierarchical Learning for Generation with Long Source Sequences](https://mlsanity.com/paper/2104.07545/) (2021)
- [Deep Learning-based Sentiment Classification: A Comparative Survey](https://mlsanity.com/paper/2312.17253/) (2023)
- [THINK: A Novel Conversation Model for Generating Grammatically Correct and Coherent Responses](https://mlsanity.com/paper/2105.13630/) (2021)
- [Can Taxonomy Help? Improving Semantic Question Matching using Question Taxonomy](https://mlsanity.com/paper/2101.08201/) (2021)
- [Predicting Parking Lot Availability by Graph-to-Sequence Model: A Case Study with SmartSantander](https://mlsanity.com/paper/2206.10160/) (2022)
- [Mixture of Decoders for Diverse Dialog Response Generation](https://mlsanity.com/paper/2610.00621/) (2026)

## Abstract (arXiv)

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.