# Disentangled Representation Learning for Non-Parallel Text Style Transfer

arXiv: https://arxiv.org/abs/1808.04339 · HTML: https://mlsanity.com/paper/1808.04339/

## Key facts

- Cited by 127 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 Aug 2018.

## Built on by (most cited first, 30 of 127)

- [FUDGE: Controlled Text Generation With Future Discriminators](https://mlsanity.com/paper/2104.05218/) (2021)
- [Text Embeddings Reveal (Almost) As Much As Text](https://mlsanity.com/paper/2310.06816/) (2023)
- [Mind the Style of Text! Adversarial and Backdoor Attacks Based on Text Style Transfer](https://mlsanity.com/paper/2110.07139/) (2021)
- [Disentangled Representation Learning](https://mlsanity.com/paper/2211.11695/) (2022)
- [Continual Learning for Text Classification with Information Disentanglement Based Regularization](https://mlsanity.com/paper/2104.05489/) (2021)
- [Text Detoxification using Large Pre-trained Neural Models](https://mlsanity.com/paper/2109.08914/) (2021)
- [MuseMorphose: Full-Song and Fine-Grained Piano Music Style Transfer with One Transformer VAE](https://mlsanity.com/paper/2105.04090/) (2021)
- [LEWIS: Levenshtein Editing for Unsupervised Text Style Transfer](https://mlsanity.com/paper/2105.08206/) (2021)
- [A Novel Estimator of Mutual Information for Learning to Disentangle Textual Representations](https://mlsanity.com/paper/2105.02685/) (2021)
- [StylePTB: A Compositional Benchmark for Fine-grained Controllable Text Style Transfer](https://mlsanity.com/paper/2104.05196/) (2021)
- [Unified Detoxifying and Debiasing in Language Generation via Inference-time Adaptive Optimization](https://mlsanity.com/paper/2210.04492/) (2022)
- [Civil Rephrases Of Toxic Texts With Self-Supervised Transformers](https://mlsanity.com/paper/2102.05456/) (2021)
- [Disentangled Sequence to Sequence Learning for Compositional Generalization](https://mlsanity.com/paper/2110.04655/) (2021)
- [Learning Interpretable Style Embeddings via Prompting LLMs](https://mlsanity.com/paper/2305.12696/) (2023)
- [Thank you BART! Rewarding Pre-Trained Models Improves Formality Style Transfer](https://mlsanity.com/paper/2105.06947/) (2021)
- [DisenHAN: Disentangled Heterogeneous Graph Attention Network for Recommendation](https://mlsanity.com/paper/2106.10879/) (2021)
- [Detect and Perturb: Neutral Rewriting of Biased and Sensitive Text via Gradient-based Decoding](https://mlsanity.com/paper/2109.11708/) (2021)
- [Disentangling Semantics and Syntax in Sentence Embeddings with Pre-trained Language Models](https://mlsanity.com/paper/2104.05115/) (2021)
- [Convex Aggregation for Opinion Summarization](https://mlsanity.com/paper/2104.01371/) (2021)
- [DyTed: Disentangled Representation Learning for Discrete-time Dynamic Graph](https://mlsanity.com/paper/2210.10592/) (2022)
- [Fuse It More Deeply! A Variational Transformer with Layer-Wise Latent Variable Inference for Text Generation](https://mlsanity.com/paper/2207.06130/) (2022)
- [Controllable Data Generation by Deep Learning: A Review](https://mlsanity.com/paper/2207.09542/) (2022)
- [VCNet: A self-explaining model for realistic counterfactual generation](https://mlsanity.com/paper/2212.10847/) (2022)
- [DisenKGAT: Knowledge Graph Embedding with Disentangled Graph Attention Network](https://mlsanity.com/paper/2108.09628/) (2021)
- [Disentangling Generative Factors in Natural Language with Discrete Variational Autoencoders](https://mlsanity.com/paper/2109.07169/) (2021)
- [Why is constrained neural language generation particularly challenging?](https://mlsanity.com/paper/2206.05395/) (2022)
- [A Review of Text Style Transfer using Deep Learning](https://mlsanity.com/paper/2109.15144/) (2021)
- [How to keep text private? A systematic review of deep learning methods for privacy-preserving natural language processing](https://mlsanity.com/paper/2205.10095/) (2022)
- [Prompt-Based Editing for Text Style Transfer](https://mlsanity.com/paper/2301.11997/) (2023)
- [Are AI-Generated Text Detectors Robust to Adversarial Perturbations?](https://mlsanity.com/paper/2406.01179/) (2024)

## Abstract (arXiv)

This paper tackles the problem of disentangling the latent variables of style and content in language models. We propose a simple yet effective approach, which incorporates auxiliary multi-task and adversarial objectives, for label prediction and bag-of-words prediction, respectively. We show, both qualitatively and quantitatively, that the style and content are indeed disentangled in the latent space. This disentangled latent representation learning method is applied to style transfer on non-parallel corpora. We achieve substantially better results in terms of transfer accuracy, content preservation and language fluency, in comparison to previous state-of-the-art approaches.