# CatVRNN: Generating Category Texts via Multi-task Learning

arXiv: https://arxiv.org/abs/2107.05219 · HTML: https://mlsanity.com/paper/2107.05219/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 21 of its 40 references that are in the map.
- First posted on arXiv 12 Jul 2021.

## Builds on (most cited first, 21 of 21)

- [Convolutional Neural Networks for Sentence Classification](https://mlsanity.com/paper/1408.5882/) (2014)
- [Scheduled Sampling for Sequence Prediction with Recurrent Neural Networks](https://mlsanity.com/paper/1506.03099/) (2015)
- [An Overview of Multi-Task Learning in Deep Neural Networks](https://mlsanity.com/paper/1706.05098/) (2017)
- [Image-based Recommendations on Styles and Substitutes](https://mlsanity.com/paper/1506.04757/) (2015)
- [Generating Sentences from a Continuous Space](https://mlsanity.com/paper/1511.06349/) (2015)
- [SeqGAN: Sequence Generative Adversarial Nets with Policy Gradient](https://mlsanity.com/paper/1609.05473/) (2016)
- [A Recurrent Latent Variable Model for Sequential Data](https://mlsanity.com/paper/1506.02216/) (2015)
- [Toward Controlled Generation of Text](https://mlsanity.com/paper/1703.00955/) (2017)
- [Coupled Generative Adversarial Networks](https://mlsanity.com/paper/1606.07536/) (2016)
- [Variational Lossy Autoencoder](https://mlsanity.com/paper/1611.02731/) (2016)
- [Deep Learning Based Text Classification: A Comprehensive Review](https://mlsanity.com/paper/2004.03705/) (2020)
- [Lagging Inference Networks and Posterior Collapse in Variational Autoencoders](https://mlsanity.com/paper/1901.05534/) (2019)
- [Long Text Generation via Adversarial Training with Leaked Information](https://mlsanity.com/paper/1709.08624/) (2017)
- [Z-Forcing: Training Stochastic Recurrent Networks](https://mlsanity.com/paper/1711.05411/) (2017)
- [Toward Diverse Text Generation with Inverse Reinforcement Learning](https://mlsanity.com/paper/1804.11258/) (2018)
- [A Hybrid Convolutional Variational Autoencoder for Text Generation](https://mlsanity.com/paper/1702.02390/) (2017)
- [Structured Attention for Unsupervised Dialogue Structure Induction](https://mlsanity.com/paper/2009.08552/) (2020)
- [CatGAN: Category-aware Generative Adversarial Networks with Hierarchical Evolutionary Learning for Category Text Generation](https://mlsanity.com/paper/1911.06641/) (2019)
- [On the Importance of the Kullback-Leibler Divergence Term in Variational Autoencoders for Text Generation](https://mlsanity.com/paper/1909.13668/) (2019)
- [Graph Generation with Variational Recurrent Neural Network](https://mlsanity.com/paper/1910.01743/) (2019)
- [An Architecture for Deep, Hierarchical Generative Models](https://mlsanity.com/paper/1612.04739/) (2016)

## Abstract (arXiv)

Controlling the model to generate texts of different categories is a challenging task that is receiving increasing attention. Recently, generative adversarial networks (GANs) have shown promising results for category text generation. However, the texts generated by GANs usually suffer from problems of mode collapse and training instability. To avoid the above problems, in this study, inspired by multi-task learning, a novel model called category-aware variational recurrent neural network (CatVRNN) is proposed. In this model, generation and classification tasks are trained simultaneously to generate texts of different categories. The use of multi-task learning can improve the quality of the generated texts, when the classification task is appropriate. In addition, a function is proposed to initialize the hidden state of the CatVRNN to force the model to generate texts of a specific category. Experimental results on three datasets demonstrate that the model can outperform state-of-the-art text generation methods based on GAN in terms of diversity of generated texts.