mlsanityData to 7 Oct 2026

CatVRNN: Generating Category Texts via Multi-task Learning

arXiv 2107.05219 ↗First posted 12 Jul 2021cs.CLcited by 0

Not on the map. Why?

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.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 21 of its 40 references that are in the map. First posted on arXiv 12 Jul 2021.

Builds on

21 of 40 references.

References · 21

  1. 2014Convolutional Neural Networks for Sentence Classificationcited by 1,124
  2. 2017An Overview of Multi-Task Learning in Deep Neural Networkscited by 791
  3. 2015Scheduled Sampling for Sequence Prediction with Recurrent Neural Networkscited by 779
  4. 2015Image-based Recommendations on Styles and Substitutescited by 702
  5. 2015Generating Sentences from a Continuous Spacecited by 607
  6. 2016SeqGAN: Sequence Generative Adversarial Nets with Policy Gradientcited by 375
  7. 2015A Recurrent Latent Variable Model for Sequential Datacited by 362
  8. 2017Toward Controlled Generation of Textcited by 271
  9. 2016Coupled Generative Adversarial Networkscited by 216
  10. 2016Variational Lossy Autoencodercited by 175
  11. 2020Deep Learning Based Text Classification: A Comprehensive Reviewcited by 140
  12. 2019Lagging Inference Networks and Posterior Collapse in Variational Autoencoderscited by 124
9 more
  1. 2017Long Text Generation via Adversarial Training with Leaked Informationcited by 100
  2. 2017Z-Forcing: Training Stochastic Recurrent Networkscited by 51
  3. 2018Toward Diverse Text Generation with Inverse Reinforcement Learningcited by 41
  4. 2017A Hybrid Convolutional Variational Autoencoder for Text Generationcited by 33
  5. 2020Structured Attention for Unsupervised Dialogue Structure Inductioncited by 19
  6. 2019CatGAN: Category-aware Generative Adversarial Networks with Hierarchical Evolutionary Learning for Category Text Generationcited by 16
  7. 2019On the Importance of the Kullback-Leibler Divergence Term in Variational Autoencoders for Text Generationcited by 9
  8. 2019Graph Generation with Variational Recurrent Neural Networkcited by 7
  9. 2016An Architecture for Deep, Hierarchical Generative Modelscited by 6

Built on by

Not cited yet.