mlsanityData to 14 Oct 2026

Style Transfer from Non-Parallel Text by Cross-Alignment

arXiv 1705.09655 ↗First posted 26 May 2017cs.CL cs.LGcited by 248

Not on the map. Why?

Abstract (arXiv)

This paper focuses on style transfer on the basis of non-parallel text. This is an instance of a broad family of problems including machine translation, decipherment, and sentiment modification. The key challenge is to separate the content from other aspects such as style. We assume a shared latent content distribution across different text corpora, and propose a method that leverages refined alignment of latent representations to perform style transfer. The transferred sentences from one style should match example sentences from the other style as a population. We demonstrate the effectiveness of this cross-alignment method on three tasks: sentiment modification, decipherment of word substitution ciphers, and recovery of word order.

Key facts. Cited by 248 papers in the map (data through 14 Oct 2026). First posted on arXiv 26 May 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 79; 2022: 57; 2023: 42; 2024: 33; 2025: 23; 2026: 14.

248 papers.

Sort:

By area:

  1. 2022Generative Adversarial Networkscited by 5,627
  2. 2022RLPrompt: Optimizing Discrete Text Prompts with Reinforcement Learningcited by 366
  3. 2021Towards Understanding and Mitigating Social Biases in Language Modelscited by 296
  4. 2023In-context Vectors: Making In Context Learning More Effective and Controllable Through Latent Space Steeringcited by 245
  5. 2022Extracting Latent Steering Vectors from Pretrained Language Modelscited by 225
  6. 2022Challenges and Strategies in Cross-Cultural NLPcited by 218
  7. 2021Mind the Style of Text! Adversarial and Backdoor Attacks Based on Text Style Transfercited by 158
  8. 2021ZeroCap: Zero-Shot Image-to-Text Generation for Visual-Semantic Arithmeticcited by 150
  9. 2021A Recipe For Arbitrary Text Style Transfer with Large Language Modelscited by 107
  10. 2024Bias in Large Language Models: Origin, Evaluation, and Mitigationcited by 77
  11. 2021Towards Facilitating Empathic Conversations in Online Mental Health Support: A Reinforcement Learning Approachcited by 75
  12. 2021Break-It-Fix-It: Unsupervised Learning for Program Repaircited by 71
38 more
  1. 2021Controlled Text Generation as Continuous Optimization with Multiple Constraintscited by 70
  2. 2022Mix and Match: Learning-free Controllable Text Generation using Energy Language Modelscited by 66
  3. 2021Compression, Transduction, and Creation: A Unified Framework for Evaluating Natural Language Generationcited by 60
  4. 2024Style Vectors for Steering Generative Large Language Modelcited by 56
  5. 2024Measuring and Controlling Instruction (In)Stability in Language Model Dialogscited by 53
  6. 2021XFORMAL: A Benchmark for Multilingual Formality Style Transfercited by 52
  7. 2021Text Detoxification using Large Pre-trained Neural Modelscited by 52
  8. 2022Prompt-and-Rerank: A Method for Zero-Shot and Few-Shot Arbitrary Textual Style Transfer with Small Language Modelscited by 49
  9. 2023Teach LLMs to Personalize -- An Approach inspired by Writing Educationcited by 48
  10. 2021Generating Syntactically Controlled Paraphrases without Using Annotated Parallel Pairscited by 45
  11. 2022A Causal Lens for Controllable Text Generationcited by 45
  12. 2023The Shifted and The Overlooked: A Task-oriented Investigation of User-GPT Interactionscited by 45
  13. 2021Transformer-based Conditional Variational Autoencoder for Controllable Story Generationcited by 44
  14. 2021MReD: A Meta-Review Dataset for Structure-Controllable Text Generationcited by 42
  15. 2022DiffusER: Discrete Diffusion via Edit-based Reconstructioncited by 41
  16. 2021LEWIS: Levenshtein Editing for Unsupervised Text Style Transfercited by 40
  17. 2021Controllable Neural Dialogue Summarization with Personal Named Entity Planningcited by 36
  18. 2022Detoxifying Text with MaRCo: Controllable Revision with Experts and Anti-Expertscited by 36
  19. 2021StylePTB: A Compositional Benchmark for Fine-grained Controllable Text Style Transfercited by 34
  20. 2021Civil Rephrases Of Toxic Texts With Self-Supervised Transformerscited by 32
  21. 2022Meet Your Favorite Character: Open-domain Chatbot Mimicking Fictional Characters with only a Few Utterancescited by 32
  22. 2022Inducing Positive Perspectives with Text Reframingcited by 31
  23. 2022Learning to Model Editing Processescited by 30
  24. 2023Learning Interpretable Style Embeddings via Prompting LLMscited by 30
  25. 2022CTRLEval: An Unsupervised Reference-Free Metric for Evaluating Controlled Text Generationcited by 29
  26. 2021Thank you BART! Rewarding Pre-Trained Models Improves Formality Style Transfercited by 28
  27. 2022Text Style Transfer for Bias Mitigation using Masked Language Modelingcited by 28
  28. 2022Composable Text Controls in Latent Space with ODEscited by 28
  29. 2024Tradeoffs Between Alignment and Helpfulness in Language Models with Steering Methodscited by 28
  30. 2021Math Word Problem Generation with Mathematical Consistency and Problem Context Constraintscited by 27
  31. 2022NEWTS: A Corpus for News Topic-Focused Summarizationcited by 27
  32. 2022Zero-Shot Video Captioning with Evolving Pseudo-Tokenscited by 25
  33. 2023Don't lose the message while paraphrasing: A study on content preserving style transfercited by 25
  34. 2021Parallel Refinements for Lexically Constrained Text Generation with BARTcited by 24
  35. 2021Unsupervised Neural Machine Translation with Generative Language Models Onlycited by 24
  36. 2022Certified Robustness Against Natural Language Attacks by Causal Interventioncited by 24
  37. 2023Generating Summaries with Controllable Readability Levelscited by 24
  38. 2024Style-Specific Neurons for Steering LLMs in Text Style Transfercited by 24

50 most cited of 248 All 248 (JSON)