mlsanityData to 7 Oct 2026

Disentangled Representation Learning for Non-Parallel Text Style Transfer

arXiv 1808.04339 ↗First posted 13 Aug 2018cs.CLcited by 127

Not on the map. Why?

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.

Key facts. Cited by 127 papers in the map (data through 7 Oct 2026). First posted on arXiv 13 Aug 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 39; 2022: 30; 2023: 29; 2024: 16; 2025: 9; 2026: 4.

127 papers.

Sort:

By area:

  1. 2021FUDGE: Controlled Text Generation With Future Discriminatorscited by 374
  2. 2023Text Embeddings Reveal (Almost) As Much As Textcited by 189
  3. 2021Mind the Style of Text! Adversarial and Backdoor Attacks Based on Text Style Transfercited by 147
  4. 2022Disentangled Representation Learningcited by 111
  5. 2021Continual Learning for Text Classification with Information Disentanglement Based Regularizationcited by 86
  6. 2021Text Detoxification using Large Pre-trained Neural Modelscited by 52
  7. 2021LEWIS: Levenshtein Editing for Unsupervised Text Style Transfercited by 40
  8. 2021MuseMorphose: Full-Song and Fine-Grained Piano Music Style Transfer with One Transformer VAEcited by 39
  9. 2021A Novel Estimator of Mutual Information for Learning to Disentangle Textual Representationscited by 37
  10. 2021StylePTB: A Compositional Benchmark for Fine-grained Controllable Text Style Transfercited by 34
  11. 2021Civil Rephrases Of Toxic Texts With Self-Supervised Transformerscited by 32
  12. 2022Unified Detoxifying and Debiasing in Language Generation via Inference-time Adaptive Optimizationcited by 32
38 more
  1. 2021Disentangled Sequence to Sequence Learning for Compositional Generalizationcited by 30
  2. 2023Learning Interpretable Style Embeddings via Prompting LLMscited by 29
  3. 2021Thank you BART! Rewarding Pre-Trained Models Improves Formality Style Transfercited by 28
  4. 2021DisenHAN: Disentangled Heterogeneous Graph Attention Network for Recommendationcited by 28
  5. 2021Detect and Perturb: Neutral Rewriting of Biased and Sensitive Text via Gradient-based Decodingcited by 23
  6. 2021Disentangling Semantics and Syntax in Sentence Embeddings with Pre-trained Language Modelscited by 22
  7. 2021Convex Aggregation for Opinion Summarizationcited by 21
  8. 2022DyTed: Disentangled Representation Learning for Discrete-time Dynamic Graphcited by 21
  9. 2022Fuse It More Deeply! A Variational Transformer with Layer-Wise Latent Variable Inference for Text Generationcited by 20
  10. 2022Controllable Data Generation by Deep Learning: A Reviewcited by 20
  11. 2022VCNet: A self-explaining model for realistic counterfactual generationcited by 20
  12. 2021DisenKGAT: Knowledge Graph Embedding with Disentangled Graph Attention Networkcited by 19
  13. 2021Disentangling Generative Factors in Natural Language with Discrete Variational Autoencoderscited by 19
  14. 2022Why is constrained neural language generation particularly challenging?cited by 19
  15. 2021A Review of Text Style Transfer using Deep Learningcited by 18
  16. 2022How to keep text private? A systematic review of deep learning methods for privacy-preserving natural language processingcited by 16
  17. 2023Prompt-Based Editing for Text Style Transfercited by 16
  18. 2024Are AI-Generated Text Detectors Robust to Adversarial Perturbations?cited by 16
  19. 2021Disentangling Representations of Text by Masking Transformerscited by 15
  20. 2022Unsupervised Structure-Texture Separation Network for Oracle Character Recognitioncited by 15
  21. 2023Exploring Methods for Cross-lingual Text Style Transfer: The Case of Text Detoxificationcited by 15
  22. 2021Methods for Detoxification of Texts for the Russian Languagecited by 13
  23. 2022Learning Disentangled Representations of Negation and Uncertaintycited by 13
  24. 2023A Call for Standardization and Validation of Text Style Transfer Evaluationcited by 13
  25. 2024Counterfactual Generation with Identifiability Guaranteescited by 13
  26. 2021Transductive Learning for Unsupervised Text Style Transfercited by 12
  27. 2022Learning Disentangled Representations for Natural Language Definitionscited by 12
  28. 2023Multidimensional Evaluation for Text Style Transfer Using ChatGPTcited by 12
  29. 2022Human Judgement as a Compass to Navigate Automatic Metrics for Formality Transfercited by 11
  30. 2022Non-Parallel Text Style Transfer with Self-Parallel Supervisioncited by 11
  31. 2023Stylized Data-to-Text Generation: A Case Study in the E-Commerce Domaincited by 11
  32. 2021Generic resources are what you need: Style transfer tasks without task-specific parallel training datacited by 10
  33. 2023Simple Disentanglement of Style and Content in Visual Representationscited by 10
  34. 2021Political Depolarization of News Articles Using Attribute-aware Word Embeddingscited by 9
  35. 2022StoryTrans: Non-Parallel Story Author-Style Transfer with Discourse Representations and Content Enhancingcited by 8
  36. 2021NAST: A Non-Autoregressive Generator with Word Alignment for Unsupervised Text Style Transfercited by 7
  37. 2022Efficient Reinforcement Learning for Unsupervised Controlled Text Generationcited by 7
  38. 2022Towards Robust and Semantically Organised Latent Representations for Unsupervised Text Style Transfercited by 7

50 most cited of 127 All 127 (JSON)