mlsanityData to 7 Oct 2026

A Hybrid Convolutional Variational Autoencoder for Text Generation

arXiv 1702.02390 ↗First posted 8 Feb 2017cs.CLcited by 33

Not on the map. Why?

Abstract (arXiv)

In this paper we explore the effect of architectural choices on learning a Variational Autoencoder (VAE) for text generation. In contrast to the previously introduced VAE model for text where both the encoder and decoder are RNNs, we propose a novel hybrid architecture that blends fully feed-forward convolutional and deconvolutional components with a recurrent language model. Our architecture exhibits several attractive properties such as faster run time and convergence, ability to better handle long sequences and, more importantly, it helps to avoid some of the major difficulties posed by training VAE models on textual data.

Key facts. Cited by 33 papers in the map (data through 7 Oct 2026). First posted on arXiv 8 Feb 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 10; 2022: 9; 2023: 9; 2024: 2; 2025: 2; 2026: 1.

33 papers.

Sort:

By area:

  1. 2023On the Creativity of Large Language Modelscited by 57
  2. 2021Protein sequence design with deep generative modelscited by 35
  3. 2023BayesDiff: Estimating Pixel-wise Uncertainty in Diffusion via Bayesian Inferencecited by 30
  4. 2021Creativity and Machine Learning: A Surveycited by 21
  5. 2022Fuse It More Deeply! A Variational Transformer with Layer-Wise Latent Variable Inference for Text Generationcited by 20
  6. 2022Amortized Variational Inference: A Systematic Reviewcited by 16
  7. 2021TextBox: A Unified, Modularized, and Extensible Framework for Text Generationcited by 15
  8. 2021Controllable and Diverse Text Generation in E-commercecited by 13
  9. 2021Learning Interpretable Representations of Entanglement in Quantum Optics Experiments using Deep Generative Modelscited by 12
  10. 2022AdaVAE: Exploring Adaptive GPT-2s in Variational Auto-Encoders for Language Modelingcited by 10
  11. 2021Learning Disentangled Representations for Time Seriescited by 8
  12. 2021Regularizing Variational Autoencoder with Diversity and Uncertainty Awarenesscited by 6
21 more
  1. 2023Beyond Vanilla Variational Autoencoders: Detecting Posterior Collapse in Conditional and Hierarchical Variational Autoencoderscited by 6
  2. 2022Assessing Dataset Bias in Computer Visioncited by 4
  3. 2024Deep Learning for Spatio-Temporal Fusion in Land Surface Temperature Estimation: A Comprehensive Survey, Experimental Analysis, and Future Trendscited by 4
  4. 2022Learning to Drop Out: An Adversarial Approach to Training Sequence VAEscited by 3
  5. 2021Discrete Auto-regressive Variational Attention Models for Text Modelingcited by 2
  6. 20226GCVAE: Gated Convolutional Variational Autoencoder for IPv6 Target Generationcited by 1
  7. 2022Fair Inference for Discrete Latent Variable Modelscited by 1
  8. 2022An Overview on Controllable Text Generation via Variational Auto-Encoderscited by 1
  9. 2023Predicting Visit Cost of Obstructive Sleep Apnea using Electronic Healthcare Records with Transformercited by 1
  10. 2023Methods for generating and evaluating synthetic longitudinal patient data: a systematic reviewcited by 1
  11. 2024A Study of Posterior Stability for Time-Series Latent Diffusioncited by 1
  12. 2025Fairness in Machine Learning-based Hand Load Estimation: A Case Study on Load Carriage Taskscited by 1
  13. 2021Meta-learning Amidst Heterogeneity and Ambiguitycited by 0
  14. 2021CatVRNN: Generating Category Texts via Multi-task Learningcited by 0
  15. 2022Noun2Verb: Probabilistic frame semantics for word class conversioncited by 0
  16. 2023Dior-CVAE: Pre-trained Language Models and Diffusion Priors for Variational Dialog Generationcited by 0
  17. 2023On the Adversarial Robustness of Generative Autoencoders in the Latent Spacecited by 0
  18. 2023Feature Extraction Using Deep Generative Models for Bangla Text Classification on a New Comprehensive Datasetcited by 0
  19. 2023Boosting Summarization with Normalizing Flows and Aggressive Trainingcited by 0
  20. 2025FASTGEN: Fast and Cost-Effective Synthetic Tabular Data Generation with LLMscited by 0
  21. 2026Entropic Auto-Encoding via Implicit Free-Energy Minimizationcited by 0