# Cycle-Consistent Adversarial Autoencoders for Unsupervised Text Style Transfer

arXiv: https://arxiv.org/abs/2010.00735 · HTML: https://mlsanity.com/paper/2010.00735/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 Oct 2020.

## Built on by (most cited first, 18 of 18)

- [Inducing Positive Perspectives with Text Reframing](https://mlsanity.com/paper/2204.02952/) (2022)
- [Shifted Chunk Transformer for Spatio-Temporal Representational Learning](https://mlsanity.com/paper/2108.11575/) (2021)
- [A Review of Text Style Transfer using Deep Learning](https://mlsanity.com/paper/2109.15144/) (2021)
- [Test-Time Training for Deformable Multi-Scale Image Registration](https://mlsanity.com/paper/2103.13578/) (2021)
- [Watermarking Autoregressive Image Generation](https://mlsanity.com/paper/2506.16349/) (2025)
- [Boosting Distress Support Dialogue Responses with Motivational Interviewing Strategy](https://mlsanity.com/paper/2305.10195/) (2023)
- [A Call for Standardization and Validation of Text Style Transfer Evaluation](https://mlsanity.com/paper/2306.00539/) (2023)
- [Human Judgement as a Compass to Navigate Automatic Metrics for Formality Transfer](https://mlsanity.com/paper/2204.07549/) (2022)
- [So Different Yet So Alike! Constrained Unsupervised Text Style Transfer](https://mlsanity.com/paper/2205.04093/) (2022)
- [Cycle Consistency Driven Object Discovery](https://mlsanity.com/paper/2306.02204/) (2023)
- [A Review of Human Emotion Synthesis Based on Generative Technology](https://mlsanity.com/paper/2412.07116/) (2024)
- [Striking a Balance: Alleviating Inconsistency in Pre-trained Models for Symmetric Classification Tasks](https://mlsanity.com/paper/2203.13491/) (2022)
- [Self-Supervised Knowledge Assimilation for Expert-Layman Text Style Transfer](https://mlsanity.com/paper/2110.02950/) (2021)
- [StyleFlow: Disentangle Latent Representations via Normalizing Flow for Unsupervised Text Style Transfer](https://mlsanity.com/paper/2212.09670/) (2022)
- [SpeechNAS: Towards Better Trade-off between Latency and Accuracy for Large-Scale Speaker Verification](https://mlsanity.com/paper/2109.08839/) (2021)
- [Positive Text Reframing under Multi-strategy Optimization](https://mlsanity.com/paper/2407.17940/) (2024)
- [Image class translation: visual inspection of class-specific hypotheticals and classification based on translation distance](https://mlsanity.com/paper/2408.08973/) (2024)
- [Bridging Compositional and Distributional Semantics: A Survey on Latent Semantic Geometry via AutoEncoder](https://mlsanity.com/paper/2506.20083/) (2025)

## Abstract (arXiv)

Unsupervised text style transfer is full of challenges due to the lack of parallel data and difficulties in content preservation. In this paper, we propose a novel neural approach to unsupervised text style transfer, which we refer to as Cycle-consistent Adversarial autoEncoders (CAE) trained from non-parallel data. CAE consists of three essential components: (1) LSTM autoencoders that encode a text in one style into its latent representation and decode an encoded representation into its original text or a transferred representation into a style-transferred text, (2) adversarial style transfer networks that use an adversarially trained generator to transform a latent representation in one style into a representation in another style, and (3) a cycle-consistent constraint that enhances the capacity of the adversarial style transfer networks in content preservation. The entire CAE with these three components can be trained end-to-end. Extensive experiments and in-depth analyses on two widely-used public datasets consistently validate the effectiveness of proposed CAE in both style transfer and content preservation against several strong baselines in terms of four automatic evaluation metrics and human evaluation.