mlsanityData to 7 Oct 2026

Transforming Delete, Retrieve, Generate Approach for Controlled Text Style Transfer

arXiv 1908.09368 ↗First posted 25 Aug 2019cs.CL cs.LGcited by 81

Not on the map. Why?

Abstract (arXiv)

Text style transfer is the task of transferring the style of text having certain stylistic attributes, while preserving non-stylistic or content information. In this work we introduce the Generative Style Transformer (GST) - a new approach to rewriting sentences to a target style in the absence of parallel style corpora. GST leverages the power of both, large unsupervised pre-trained language models as well as the Transformer. GST is a part of a larger `Delete Retrieve Generate' framework, in which we also propose a novel method of deleting style attributes from the source sentence by exploiting the inner workings of the Transformer. Our models outperform state-of-art systems across 5 datasets on sentiment, gender and political slant transfer. We also propose the use of the GLEU metric as an automatic metric of evaluation of style transfer, which we found to compare better with human ratings than the predominantly used BLEU score.

Key facts. Cited by 81 papers in the map (data through 7 Oct 2026). First posted on arXiv 25 Aug 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 25; 2022: 20; 2023: 19; 2024: 12; 2025: 2; 2026: 3.

81 papers.

Sort:

By area:

  1. 2021DExperts: Decoding-Time Controlled Text Generation with Experts and Anti-Expertscited by 434
  2. 2022Quark: Controllable Text Generation with Reinforced Unlearningcited by 236
  3. 2021Mind the Style of Text! Adversarial and Backdoor Attacks Based on Text Style Transfercited by 147
  4. 2021A Recipe For Arbitrary Text Style Transfer with Large Language Modelscited by 107
  5. 2021COVID-Fact: Fact Extraction and Verification of Real-World Claims on COVID-19 Pandemiccited by 100
  6. 2023Detecting and Grounding Multi-Modal Media Manipulationcited by 98
  7. 2021The Perils of Using Mechanical Turk to Evaluate Open-Ended Text Generationcited by 96
  8. 2023Reward-Augmented Decoding: Efficient Controlled Text Generation With a Unidirectional Reward Modelcited by 79
  9. 2022Machine Generated Text: A Comprehensive Survey of Threat Models and Detection Methodscited by 75
  10. 2024Detecting Multimedia Generated by Large AI Models: A Surveycited by 73
  11. 2021Controlled Text Generation as Continuous Optimization with Multiple Constraintscited by 70
  12. 2023Detecting and Grounding Multi-Modal Media Manipulation and Beyondcited by 55
38 more
  1. 2021Text Detoxification using Large Pre-trained Neural Modelscited by 52
  2. 2022Prompt-and-Rerank: A Method for Zero-Shot and Few-Shot Arbitrary Textual Style Transfer with Small Language Modelscited by 49
  3. 2022Critic-Guided Decoding for Controlled Text Generationcited by 45
  4. 2023You Only Prompt Once: On the Capabilities of Prompt Learning on Large Language Models to Tackle Toxic Contentcited by 37
  5. 2021StylePTB: A Compositional Benchmark for Fine-grained Controllable Text Style Transfercited by 34
  6. 2022Inducing Positive Perspectives with Text Reframingcited by 31
  7. 2021Exploring the Efficacy of Automatically Generated Counterfactuals for Sentiment Analysiscited by 30
  8. 2022Composable Text Controls in Latent Space with ODEscited by 28
  9. 2022Text Style Transfer for Bias Mitigation using Masked Language Modelingcited by 27
  10. 2021Detect and Perturb: Neutral Rewriting of Biased and Sensitive Text via Gradient-based Decodingcited by 23
  11. 2024A Survey on Natural Language Counterfactual Generationcited by 21
  12. 2022Controllable Data Generation by Deep Learning: A Reviewcited by 20
  13. 2022Why is constrained neural language generation particularly challenging?cited by 19
  14. 2021A Review of Text Style Transfer using Deep Learningcited by 18
  15. 2024Parameter-Efficient Detoxification with Contrastive Decodingcited by 18
  16. 2021Text Counterfactuals via Latent Optimization and Shapley-Guided Searchcited by 16
  17. 2023Think Twice: A Human-like Two-stage Conversational Agent for Emotional Response Generationcited by 14
  18. 2023STEER: Unified Style Transfer with Expert Reinforcementcited by 14
  19. 2023A Call for Standardization and Validation of Text Style Transfer Evaluationcited by 13
  20. 2021Transductive Learning for Unsupervised Text Style Transfercited by 12
  21. 2022Human Judgement as a Compass to Navigate Automatic Metrics for Formality Transfercited by 11
  22. 2022Non-Parallel Text Style Transfer with Self-Parallel Supervisioncited by 11
  23. 2021ENTRUST: Argument Reframing with Language Models and Entailmentcited by 10
  24. 2021Transferable Persona-Grounded Dialogues via Grounded Minimal Editscited by 10
  25. 2022Low-Resource Authorship Style Transfer: Can Non-Famous Authors Be Imitated?cited by 9
  26. 2023Learning to Generate Text in Arbitrary Writing Stylescited by 9
  27. 2021Similar Scenes arouse Similar Emotions: Parallel Data Augmentation for Stylized Image Captioningcited by 7
  28. 2021Idiomatic Expression Paraphrasing without Strong Supervisioncited by 7
  29. 2022Efficient Reinforcement Learning for Unsupervised Controlled Text Generationcited by 7
  30. 2023Fine-grained Text Style Transfer with Diffusion-Based Language Modelscited by 7
  31. 2023Advancements in Scientific Controllable Text Generation Methodscited by 7
  32. 2024Unsupervised Text Style Transfer via LLMs and Attention Masking with Multi-way Interactionscited by 7
  33. 2022Nano: Nested Human-in-the-Loop Reward Learning for Few-shot Language Model Controlcited by 6
  34. 2022T-STAR: Truthful Style Transfer using AMR Graph as Intermediate Representationcited by 6
  35. 2023Don't Take This Out of Context! On the Need for Contextual Models and Evaluations for Stylistic Rewritingcited by 6
  36. 2023Prefix-Tuning Based Unsupervised Text Style Transfercited by 6
  37. 2021From Solving a Problem Boldly to Cutting the Gordian Knot: Idiomatic Text Generationcited by 5
  38. 2021From Theories on Styles to their Transfer in Text: Bridging the Gap with a Hierarchical Surveycited by 5

50 most cited of 81 All 81 (JSON)