mlsanityData to 7 Oct 2026

From Theories on Styles to their Transfer in Text: Bridging the Gap with a Hierarchical Survey

arXiv 2110.15871 ↗First posted 29 Oct 2021cs.CLcited by 5

Not on the map. Why?

Abstract (arXiv)

Humans are naturally endowed with the ability to write in a particular style. They can, for instance, re-phrase a formal letter in an informal way, convey a literal message with the use of figures of speech or edit a novel by mimicking the style of some well-known authors. Automating this form of creativity constitutes the goal of style transfer. As a natural language generation task, style transfer aims at rewriting existing texts, and specifically, it creates paraphrases that exhibit some desired stylistic attributes. From a practical perspective, it envisions beneficial applications, like chatbots that modulate their communicative style to appear empathetic, or systems that automatically simplify technical articles for a non-expert audience. Several style-aware paraphrasing methods have attempted to tackle style transfer. A handful of surveys give a methodological overview of the field, but they do not support researchers to focus on specific styles. With this paper, we aim at providing a comprehensive discussion of the styles that have received attention in the transfer task. We organize them in a hierarchy, highlighting the challenges for the definition of each of them, and pointing out gaps in the current research landscape. The hierarchy comprises two main groups. One encompasses styles that people modulate arbitrarily, along the lines of registers and genres. The other group corresponds to unintentionally expressed styles, due to an author's personal characteristics. Hence, our review shows how these groups relate to one another, and where specific styles, including some that have not yet been explored, belong in the hierarchy. Moreover, we summarize the methods employed for different stylistic families, hinting researchers towards those that would be the most fitting for future research.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 128 of its 340 references that are in the map. First posted on arXiv 29 Oct 2021.

Builds on

128 of 340 references.

References · 128

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
  3. 2019BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehensioncited by 5,874
  4. 2019BERTScore: Evaluating Text Generation with BERTcited by 5,462
  5. 2016Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddingscited by 1,304
  6. 2016ConceptNet 5.5: An Open Multilingual Graph of General Knowledgecited by 1,065
  7. 2017Automated Hate Speech Detection and the Problem of Offensive Languagecited by 724
  8. 2017DailyDialog: A Manually Labelled Multi-turn Dialogue Datasetcited by 649
  9. 2019COMET: Commonsense Transformers for Automatic Knowledge Graph Constructioncited by 450
  10. 2021FUDGE: Controlled Text Generation With Future Discriminatorscited by 374
  11. 2016How NOT To Evaluate Your Dialogue System: An Empirical Study of Unsupervised Evaluation Metrics for Dialogue Response Generationcited by 356
  12. 2017Toward Controlled Generation of Textcited by 271
38 more
  1. 2017Style Transfer from Non-Parallel Text by Cross-Alignmentcited by 246
  2. 2018Dear Sir or Madam, May I introduce the GYAFC Dataset: Corpus, Benchmarks and Metrics for Formality Style Transfercited by 209
  3. 2017Survey of the State of the Art in Natural Language Generation: Core tasks, applications and evaluationcited by 206
  4. 2016Demographic Dialectal Variation in Social Media: A Case Study of African-American Englishcited by 194
  5. 2018Delete, Retrieve, Generate: A Simple Approach to Sentiment and Style Transfercited by 191
  6. 2020Reformulating Unsupervised Style Transfer as Paraphrase Generationcited by 181
  7. 2018Learning Gender-Neutral Word Embeddingscited by 169
  8. 2020Deep Learning for Text Style Transfer: A Surveycited by 161
  9. 2017Style Transfer in Text: Exploration and Evaluationcited by 145
  10. 2017Encoding Sentences with Graph Convolutional Networks for Semantic Role Labelingcited by 137
  11. 2018Disentangled Representation Learning for Non-Parallel Text Style Transfercited by 127
  12. 2018Style Transfer Through Back-Translationcited by 124
  13. 2017Using millions of emoji occurrences to learn any-domain representations for detecting sentiment, emotion and sarcasmcited by 117
  14. 2017Understanding Abuse: A Typology of Abusive Language Detection Subtaskscited by 115
  15. 2017Sentence Simplification with Deep Reinforcement Learningcited by 107
  16. 2021A Recipe For Arbitrary Text Style Transfer with Large Language Modelscited by 107
  17. 2019Automatically Neutralizing Subjective Bias in Textcited by 105
  18. 2013A Computational Approach to Politeness with Application to Social Factorscited by 104
  19. 2017Generating Sentences by Editing Prototypescited by 88
  20. 2019Style Transformer: Unpaired Text Style Transfer without Disentangled Latent Representationcited by 84
  21. 2019Transforming Delete, Retrieve, Generate Approach for Controlled Text Style Transfercited by 81
  22. 2020Politeness Transfer: A Tag and Generate Approachcited by 78
  23. 2018Unsupervised Text Style Transfer using Language Models as Discriminatorscited by 70
  24. 2020A Probabilistic Formulation of Unsupervised Text Style Transfercited by 70
  25. 2019A Dual Reinforcement Learning Framework for Unsupervised Text Style Transfercited by 65
  26. 2017MojiTalk: Generating Emotional Responses at Scalecited by 64
  27. 2019Evaluating Style Transfer for Textcited by 59
  28. 2019Generating Sentences from Disentangled Syntactic and Semantic Spacescited by 59
  29. 2017Shakespearizing Modern Language Using Copy-Enriched Sequence-to-Sequence Modelscited by 57
  30. 2018Unpaired Sentiment-to-Sentiment Translation: A Cycled Reinforcement Learning Approachcited by 55
  31. 2018Fighting Offensive Language on Social Media with Unsupervised Text Style Transfercited by 55
  32. 2018Challenges for Toxic Comment Classification: An In-Depth Error Analysiscited by 55
  33. 2020Exploring Controllable Text Generation Techniquescited by 55
  34. 2015Gated Feedback Recurrent Neural Networkscited by 54
  35. 2020Improving Disentangled Text Representation Learning with Information-Theoretic Guidancecited by 52
  36. 2018Engaging Image Captioning Via Personalitycited by 51
  37. 2021XFORMAL: A Benchmark for Multilingual Formality Style Transfercited by 51
  38. 2017Affect-LM: A Neural Language Model for Customizable Affective Text Generationcited by 50

50 most cited of 128 All 128 (JSON)

Built on by

Cited by year

Citing papers per year: 2022: 1; 2023: 3; 2024: 0; 2025: 1.

5 papers.