mlsanityData to 14 Oct 2026

Style Transfer in Text: Exploration and Evaluation

arXiv 1711.06861 ↗First posted 18 Nov 2017cs.CLcited by 146

Not on the map. Why?

Abstract (arXiv)

Style transfer is an important problem in natural language processing (NLP). However, the progress in language style transfer is lagged behind other domains, such as computer vision, mainly because of the lack of parallel data and principle evaluation metrics. In this paper, we propose to learn style transfer with non-parallel data. We explore two models to achieve this goal, and the key idea behind the proposed models is to learn separate content representations and style representations using adversarial networks. We also propose novel evaluation metrics which measure two aspects of style transfer: transfer strength and content preservation. We access our models and the evaluation metrics on two tasks: paper-news title transfer, and positive-negative review transfer. Results show that the proposed content preservation metric is highly correlate to human judgments, and the proposed models are able to generate sentences with higher style transfer strength and similar content preservation score comparing to auto-encoder.

Key facts. Cited by 146 papers in the map (data through 14 Oct 2026). First posted on arXiv 18 Nov 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 46; 2022: 38; 2023: 25; 2024: 15; 2025: 14; 2026: 8.

146 papers.

Sort:

By area:

  1. 2021Mind the Style of Text! Adversarial and Backdoor Attacks Based on Text Style Transfercited by 158
  2. 2022A Survey of Controllable Text Generation using Transformer-based Pre-trained Language Modelscited by 129
  3. 2021A Recipe For Arbitrary Text Style Transfer with Large Language Modelscited by 107
  4. 2021Continual Learning for Text Classification with Information Disentanglement Based Regularizationcited by 86
  5. 2021Types of Out-of-Distribution Texts and How to Detect Themcited by 80
  6. 2022Prompt-and-Rerank: A Method for Zero-Shot and Few-Shot Arbitrary Textual Style Transfer with Small Language Modelscited by 49
  7. 2021Generating Syntactically Controlled Paraphrases without Using Annotated Parallel Pairscited by 45
  8. 2021MuseMorphose: Full-Song and Fine-Grained Piano Music Style Transfer with One Transformer VAEcited by 40
  9. 2021LEWIS: Levenshtein Editing for Unsupervised Text Style Transfercited by 40
  10. 2021The Threat of Offensive AI to Organizationscited by 38
  11. 2021A Novel Estimator of Mutual Information for Learning to Disentangle Textual Representationscited by 37
  12. 2021StylePTB: A Compositional Benchmark for Fine-grained Controllable Text Style Transfercited by 34
38 more
  1. 2021Civil Rephrases Of Toxic Texts With Self-Supervised Transformerscited by 32
  2. 2023Controllable Mixed-Initiative Dialogue Generation through Promptingcited by 32
  3. 2022Inducing Positive Perspectives with Text Reframingcited by 31
  4. 2023Learning Interpretable Style Embeddings via Prompting LLMscited by 30
  5. 2021Thank you BART! Rewarding Pre-Trained Models Improves Formality Style Transfercited by 28
  6. 2022Text Style Transfer for Bias Mitigation using Masked Language Modelingcited by 28
  7. 2021Attribute Alignment: Controlling Text Generation from Pre-trained Language Modelscited by 27
  8. 2021Parallel Refinements for Lexically Constrained Text Generation with BARTcited by 24
  9. 2021Disentangling Semantics and Syntax in Sentence Embeddings with Pre-trained Language Modelscited by 22
  10. 2022NewsEdits: A News Article Revision Dataset and a Document-Level Reasoning Challengecited by 20
  11. 2022Controllable Data Generation by Deep Learning: A Reviewcited by 20
  12. 2022Dance Style Transfer with Cross-modal Transformercited 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. 2023Evade ChatGPT Detectors via A Single Spacecited by 18
  16. 2024GhostWriter: Augmenting Collaborative Human-AI Writing Experiences Through Personalization and Agencycited by 18
  17. 2024StyleRemix: Interpretable Authorship Obfuscation via Distillation and Perturbation of Style Elementscited by 18
  18. 2022Text Revision by On-the-Fly Representation Optimizationcited by 17
  19. 2023Prompt-Based Editing for Text Style Transfercited by 16
  20. 2023A Systematic Study of Knowledge Distillation for Natural Language Generation with Pseudo-Target Trainingcited by 16
  21. 2024Real or Robotic? Assessing Whether LLMs Accurately Simulate Qualities of Human Responses in Dialoguecited by 16
  22. 2023Boosting Distress Support Dialogue Responses with Motivational Interviewing Strategycited by 15
  23. 2022Learning Disentangled Textual Representations via Statistical Measures of Similaritycited by 14
  24. 2023A Call for Standardization and Validation of Text Style Transfer Evaluationcited by 14
  25. 2021Improving Formality Style Transfer with Context-Aware Rule Injectioncited by 13
  26. 2021A Survey of Natural Language Generationcited by 13
  27. 2022Learning Disentangled Representations of Negation and Uncertaintycited by 13
  28. 2021Transductive Learning for Unsupervised Text Style Transfercited by 12
  29. 2022Non-Parallel Text Style Transfer with Self-Parallel Supervisioncited by 11
  30. 2023Stylized Data-to-Text Generation: A Case Study in the E-Commerce Domaincited by 11
  31. 2024Text Detoxification as Style Transfer in English and Hindicited by 11
  32. 2021Generic resources are what you need: Style transfer tasks without task-specific parallel training datacited by 10
  33. 2021Sketch and Customize: A Counterfactual Story Generatorcited by 9
  34. 2021Improving Code-switching Language Modeling with Artificially Generated Texts using Cycle-consistent Adversarial Networkscited by 9
  35. 2024Multilingual Text Style Transfer: Datasets & Models for Indian Languagescited by 9
  36. 2022Metric-guided Distillation: Distilling Knowledge from the Metric to Ranker and Retriever for Generative Commonsense Reasoningcited by 8
  37. 2021NAST: A Non-Autoregressive Generator with Word Alignment for Unsupervised Text Style Transfercited by 7
  38. 2022Efficient Reinforcement Learning for Unsupervised Controlled Text Generationcited by 7

50 most cited of 146 All 146 (JSON)