mlsanityData to 7 Oct 2026

StyleFlow: Disentangle Latent Representations via Normalizing Flow for Unsupervised Text Style Transfer

arXiv 2212.09670 ↗First posted 19 Dec 2022cs.CLcited by 4

Not on the map. Why?

Abstract (arXiv)

Text style transfer aims to alter the style of a sentence while preserving its content. Due to the lack of parallel corpora, most recent work focuses on unsupervised methods and often uses cycle construction to train models. Since cycle construction helps to improve the style transfer ability of the model by rebuilding transferred sentences back to original-style sentences, it brings about a content loss in unsupervised text style transfer tasks. In this paper, we propose a novel disentanglement-based style transfer model StyleFlow to enhance content preservation. Instead of the typical encoder-decoder scheme, StyleFlow can not only conduct the forward process to obtain the output, but also infer to the input through the output. We design an attention-aware coupling layers to disentangle the content representations and the style representations of a sentence. Besides, we propose a data augmentation method based on Normalizing Flow to improve the robustness of the model. Experiment results demonstrate that our model preserves content effectively and achieves the state-of-the-art performance on the most metrics.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 75 of its 108 references that are in the map. First posted on arXiv 19 Dec 2022.

Builds on

75 of 108 references.

References · 75

  1. 2017Attention Is All You Needcited by 59,932
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  3. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  4. 2020Language Models are Few-Shot Learnerscited by 32,199
  5. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,266
  6. 2014Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translationcited by 4,016
  7. 2015Variational Inference with Normalizing Flowscited by 2,161
  8. 2016Density estimation using Real NVPcited by 2,029
  9. 2018A Call for Clarity in Reporting BLEU Scorescited by 1,790
  10. 2018Glow: Generative Flow with Invertible 1x1 Convolutionscited by 1,539
  11. 2014NICE: Non-linear Independent Components Estimationcited by 1,052
  12. 2015Effective Approaches to Attention-based Neural Machine Translationcited by 1,024
38 more
  1. 2018Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representationscited by 929
  2. 2019Plug and Play Language Models: A Simple Approach to Controlled Text Generationcited by 793
  3. 2019CTRL: A Conditional Transformer Language Model for Controllable Generationcited by 754
  4. 2016Improving Variational Inference with Inverse Autoregressive Flowcited by 636
  5. 2021Prompt Programming for Large Language Models: Beyond the Few-Shot Paradigmcited by 599
  6. 2019Neural Spline Flowscited by 590
  7. 2016Ups and Downs: Modeling the Visual Evolution of Fashion Trends with One-Class Collaborative Filteringcited by 517
  8. 2017Toward Controlled Generation of Textcited by 271
  9. 2019Flow++: Improving Flow-Based Generative Models with Variational Dequantization and Architecture Designcited by 258
  10. 2017Style Transfer from Non-Parallel Text by Cross-Alignmentcited by 246
  11. 2018Dear Sir or Madam, May I introduce the GYAFC Dataset: Corpus, Benchmarks and Metrics for Formality Style Transfercited by 209
  12. 2018Delete, Retrieve, Generate: A Simple Approach to Sentiment and Style Transfercited by 191
  13. 2020Reformulating Unsupervised Style Transfer as Paraphrase Generationcited by 181
  14. 2018Adversarial Removal of Demographic Attributes from Text Datacited by 166
  15. 2020Deep Learning for Text Style Transfer: A Surveycited by 161
  16. 2017Style Transfer in Text: Exploration and Evaluationcited by 145
  17. 2018Disentangled Representation Learning for Non-Parallel Text Style Transfercited by 127
  18. 2021ArtFlow: Unbiased Image Style Transfer via Reversible Neural Flowscited by 113
  19. 2021A Survey on Data Augmentation for Text Classificationcited by 111
  20. 2019Noise Flow: Noise Modeling with Conditional Normalizing Flowscited by 108
  21. 2021A Recipe For Arbitrary Text Style Transfer with Large Language Modelscited by 107
  22. 2021Pretrained Language Models for Text Generation: A Surveycited by 95
  23. 2019FlowSeq: Non-Autoregressive Conditional Sequence Generation with Generative Flowcited by 89
  24. 2017Generating Sentences by Editing Prototypescited by 88
  25. 2019Style Transformer: Unpaired Text Style Transfer without Disentangled Latent Representationcited by 84
  26. 2019Transforming Delete, Retrieve, Generate Approach for Controlled Text Style Transfercited by 81
  27. 2018Style Augmentation: Data Augmentation via Style Randomizationcited by 79
  28. 2016Edinburgh Neural Machine Translation Systems for WMT 16cited by 76
  29. 2019Semi-Supervised Learning with Normalizing Flowscited by 76
  30. 2019Personalized Dialogue Generation with Diversified Traitscited by 73
  31. 2018Unsupervised Text Style Transfer using Language Models as Discriminatorscited by 70
  32. 2022Mix and Match: Learning-free Controllable Text Generation using Energy Language Modelscited by 66
  33. 2019A Dual Reinforcement Learning Framework for Unsupervised Text Style Transfercited by 65
  34. 2019Generating Sentences from Disentangled Syntactic and Semantic Spacescited by 59
  35. 2020PowerTransformer: Unsupervised Controllable Revision for Biased Language Correctioncited by 59
  36. 2018Unpaired Sentiment-to-Sentiment Translation: A Cycled Reinforcement Learning Approachcited by 55
  37. 2018Fighting Offensive Language on Social Media with Unsupervised Text Style Transfercited by 55
  38. 2021XFORMAL: A Benchmark for Multilingual Formality Style Transfercited by 51

50 most cited of 75 All 75 (JSON)

Built on by

Cited by year

Citing papers per year: 2023: 1; 2024: 1; 2025: 2.

4 papers.

  1. 2024StyleDistance: Stronger Content-Independent Style Embeddings with Synthetic Parallel Examplescited by 32
  2. 2023Learning Interpretable Style Embeddings via Prompting LLMscited by 29
  3. 2025Discovering Semantic Subdimensions through Disentangled Conceptual Representationscited by 1
  4. 2025Neurobiber: Fast and Interpretable Stylistic Feature Extractioncited by 0