mlsanityData to 14 Oct 2026

Plug and Play Autoencoders for Conditional Text Generation

arXiv 2010.02983 ↗First posted 6 Oct 2020cs.CL cs.AIcited by 26

Not on the map. Why?

Abstract (arXiv)

Text autoencoders are commonly used for conditional generation tasks such as style transfer. We propose methods which are plug and play, where any pretrained autoencoder can be used, and only require learning a mapping within the autoencoder's embedding space, training embedding-to-embedding (Emb2Emb). This reduces the need for labeled training data for the task and makes the training procedure more efficient. Crucial to the success of this method is a loss term for keeping the mapped embedding on the manifold of the autoencoder and a mapping which is trained to navigate the manifold by learning offset vectors. Evaluations on style transfer tasks both with and without sequence-to-sequence supervision show that our method performs better than or comparable to strong baselines while being up to four times faster.

Key facts. Cited by 26 papers in the map (data through 14 Oct 2026). First posted on arXiv 6 Oct 2020.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 9; 2022: 11; 2023: 4; 2024: 1; 2025: 1.

26 papers.

Sort:

By area:

  1. 2022Extracting Latent Steering Vectors from Pretrained Language Modelscited by 225
  2. 2021Towards Facilitating Empathic Conversations in Online Mental Health Support: A Reinforcement Learning Approachcited by 75
  3. 2022Mix and Match: Learning-free Controllable Text Generation using Energy Language Modelscited by 66
  4. 2022A Distributional Lens for Multi-Aspect Controllable Text Generationcited by 33
  5. 2022Composable Text Controls in Latent Space with ODEscited by 28
  6. 2022Controllable Text Generation via Probability Density Estimation in the Latent Spacecited by 27
  7. 2022Towards Practical Plug-and-Play Diffusion Modelscited by 20
  8. 2021Plug-and-Blend: A Framework for Controllable Story Generation with Blended Control Codescited by 19
  9. 2021Sentence Bottleneck Autoencoders from Transformer Language Modelscited by 19
  10. 2021Transductive Learning for Unsupervised Text Style Transfercited by 12
  11. 2022So Different Yet So Alike! Constrained Unsupervised Text Style Transfercited by 7
  12. 2023A Block Metropolis-Hastings Sampler for Controllable Energy-based Text Generationcited by 6
14 more
  1. 2021From Theories on Styles to their Transfer in Text: Bridging the Gap with a Hierarchical Surveycited by 5
  2. 2023ZeroGen: Zero-shot Multimodal Controllable Text Generation with Multiple Oraclescited by 5
  3. 2021Towards Personalised and Document-level Machine Translation of Dialoguecited by 4
  4. 2021Controlled Neural Sentence-Level Reframing of News Articlescited by 4
  5. 2021Modelling Direct Messaging Networks with Multiple Recipients for Cyber Deceptioncited by 4
  6. 2022PCAE: A Framework of Plug-in Conditional Auto-Encoder for Controllable Text Generationcited by 4
  7. 2023Conversation Style Transfer using Few-Shot Learningcited by 4
  8. 2024Language Rectified Flow: Advancing Diffusion Language Generation with Probabilistic Flowscited by 4
  9. 2022vec2text with Round-Trip Translationscited by 3
  10. 2022Economics of Semantic Communication System: An Auction Approachcited by 2
  11. 2023Feature-aware conditional GAN for category text generationcited by 2
  12. 2021Bag-of-Vectors Autoencoders for Unsupervised Conditional Text Generationcited by 1
  13. 2022An Overview on Controllable Text Generation via Variational Auto-Encoderscited by 1
  14. 2025Bridging Compositional and Distributional Semantics: A Survey on Latent Semantic Geometry via AutoEncodercited by 0