# Plug and Play Autoencoders for Conditional Text Generation

arXiv: https://arxiv.org/abs/2010.02983 · HTML: https://mlsanity.com/paper/2010.02983/

## Key facts

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

## Built on by (most cited first, 26 of 26)

- [Extracting Latent Steering Vectors from Pretrained Language Models](https://mlsanity.com/paper/2205.05124/) (2022)
- [Towards Facilitating Empathic Conversations in Online Mental Health Support: A Reinforcement Learning Approach](https://mlsanity.com/paper/2101.07714/) (2021)
- [Mix and Match: Learning-free Controllable Text Generation using Energy Language Models](https://mlsanity.com/paper/2203.13299/) (2022)
- [A Distributional Lens for Multi-Aspect Controllable Text Generation](https://mlsanity.com/paper/2210.02889/) (2022)
- [Composable Text Controls in Latent Space with ODEs](https://mlsanity.com/paper/2208.00638/) (2022)
- [Controllable Text Generation via Probability Density Estimation in the Latent Space](https://mlsanity.com/paper/2212.08307/) (2022)
- [Towards Practical Plug-and-Play Diffusion Models](https://mlsanity.com/paper/2212.05973/) (2022)
- [Plug-and-Blend: A Framework for Controllable Story Generation with Blended Control Codes](https://mlsanity.com/paper/2104.04039/) (2021)
- [Sentence Bottleneck Autoencoders from Transformer Language Models](https://mlsanity.com/paper/2109.00055/) (2021)
- [Transductive Learning for Unsupervised Text Style Transfer](https://mlsanity.com/paper/2109.07812/) (2021)
- [So Different Yet So Alike! Constrained Unsupervised Text Style Transfer](https://mlsanity.com/paper/2205.04093/) (2022)
- [A Block Metropolis-Hastings Sampler for Controllable Energy-based Text Generation](https://mlsanity.com/paper/2312.04510/) (2023)
- [From Theories on Styles to their Transfer in Text: Bridging the Gap with a Hierarchical Survey](https://mlsanity.com/paper/2110.15871/) (2021)
- [ZeroGen: Zero-shot Multimodal Controllable Text Generation with Multiple Oracles](https://mlsanity.com/paper/2306.16649/) (2023)
- [Towards Personalised and Document-level Machine Translation of Dialogue](https://mlsanity.com/paper/2102.10979/) (2021)
- [Controlled Neural Sentence-Level Reframing of News Articles](https://mlsanity.com/paper/2109.04957/) (2021)
- [Modelling Direct Messaging Networks with Multiple Recipients for Cyber Deception](https://mlsanity.com/paper/2111.11932/) (2021)
- [PCAE: A Framework of Plug-in Conditional Auto-Encoder for Controllable Text Generation](https://mlsanity.com/paper/2210.03496/) (2022)
- [Conversation Style Transfer using Few-Shot Learning](https://mlsanity.com/paper/2302.08362/) (2023)
- [Language Rectified Flow: Advancing Diffusion Language Generation with Probabilistic Flows](https://mlsanity.com/paper/2403.16995/) (2024)
- [vec2text with Round-Trip Translations](https://mlsanity.com/paper/2209.06792/) (2022)
- [Economics of Semantic Communication System: An Auction Approach](https://mlsanity.com/paper/2208.05040/) (2022)
- [Feature-aware conditional GAN for category text generation](https://mlsanity.com/paper/2308.00939/) (2023)
- [Bag-of-Vectors Autoencoders for Unsupervised Conditional Text Generation](https://mlsanity.com/paper/2110.07002/) (2021)
- [An Overview on Controllable Text Generation via Variational Auto-Encoders](https://mlsanity.com/paper/2211.07954/) (2022)
- [Bridging Compositional and Distributional Semantics: A Survey on Latent Semantic Geometry via AutoEncoder](https://mlsanity.com/paper/2506.20083/) (2025)

## 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.