mlsanityData to 14 Oct 2026

SimpleStyle: An Adaptable Style Transfer Approach

arXiv 2212.10498 ↗First posted 20 Dec 2022cs.CLcited by 0

Not on the map. Why?

Abstract (arXiv)

Attribute-controlled text rewriting, also known as text style-transfer, has a crucial role in regulating attributes and biases of textual training data and a machine generated text. In this work we present SimpleStyle, a minimalist yet effective approach for style-transfer composed of two simple ingredients: controlled denoising and output filtering. Despite the simplicity of our approach, which can be succinctly described with a few lines of code, it is competitive with previous state-of-the-art methods both in automatic and in human evaluation. To demonstrate the adaptability and practical value of our system beyond academic data, we apply SimpleStyle to transfer a wide range of text attributes appearing in real-world textual data from social networks. Additionally, we introduce a novel "soft noising" technique that further improves the performance of our system. We also show that teaching a student model to generate the output of SimpleStyle can result in a system that performs style transfer of equivalent quality with only a single greedy-decoded sample. Finally, we suggest our method as a remedy for the fundamental incompatible baseline issue that holds progress in the field. We offer our protocol as a simple yet strong baseline for works that wish to make incremental advancements in the field of attribute controlled text rewriting.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 35 of its 45 references that are in the map. First posted on arXiv 20 Dec 2022.

Builds on

35 of 45 references.

References · 35

  1. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,170
  2. 2019BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehensioncited by 5,893
  3. 2021SimCSE: Simple Contrastive Learning of Sentence Embeddingscited by 2,173
  4. 2021DeBERTaV3: Improving DeBERTa using ELECTRA-Style Pre-Training with Gradient-Disentangled Embedding Sharingcited by 1,254
  5. 2020TweetEval: Unified Benchmark and Comparative Evaluation for Tweet Classificationcited by 417
  6. 2017Unsupervised Machine Translation Using Monolingual Corpora Onlycited by 273
  7. 2017Toward Controlled Generation of Textcited by 272
  8. 2017Style Transfer from Non-Parallel Text by Cross-Alignmentcited by 248
  9. 2018Dear Sir or Madam, May I introduce the GYAFC Dataset: Corpus, Benchmarks and Metrics for Formality Style Transfercited by 211
  10. 2015Semi-supervised Sequence Learningcited by 198
  11. 2018Delete, Retrieve, Generate: A Simple Approach to Sentiment and Style Transfercited by 191
  12. 2020Reformulating Unsupervised Style Transfer as Paraphrase Generationcited by 183
23 more
  1. 2020Deep Learning for Text Style Transfer: A Surveycited by 162
  2. 2017Style Transfer in Text: Exploration and Evaluationcited by 146
  3. 2018Style Transfer Through Back-Translationcited by 124
  4. 2021A Recipe For Arbitrary Text Style Transfer with Large Language Modelscited by 107
  5. 2019Transforming Delete, Retrieve, Generate Approach for Controlled Text Style Transfercited by 81
  6. 2022Mix and Match: Learning-free Controllable Text Generation using Energy Language Modelscited by 66
  7. 2019A Dual Reinforcement Learning Framework for Unsupervised Text Style Transfercited by 65
  8. 2018Unpaired Sentiment-to-Sentiment Translation: A Cycled Reinforcement Learning Approachcited by 55
  9. 2019"Mask and Infill" : Applying Masked Language Model to Sentiment Transfercited by 48
  10. 2018Regularizing Neural Machine Translation by Target-bidirectional Agreementcited by 40
  11. 2020TextSETTR: Few-Shot Text Style Extraction and Tunable Targeted Restylingcited by 40
  12. 2020Parallel Data Augmentation for Formality Style Transfercited by 39
  13. 2019Reinforcement Learning Based Text Style Transfer without Parallel Training Corpuscited by 38
  14. 2020Unsupervised Text Generation by Learning from Searchcited by 36
  15. 2019IMaT: Unsupervised Text Attribute Transfer via Iterative Matching and Translationcited by 33
  16. 2022Quality Controlled Paraphrase Generationcited by 31
  17. 2019A Hierarchical Reinforced Sequence Operation Method for Unsupervised Text Style Transfercited by 20
  18. 2019Style Transfer for Texts: Retrain, Report Errors, Compare with Rewritescited by 20
  19. 2020Exploring Contextual Word-level Style Relevance for Unsupervised Style Transfercited by 15
  20. 2022Non-Parallel Text Style Transfer with Self-Parallel Supervisioncited by 11
  21. 2018Unsupervised Controllable Text Formalizationcited by 9
  22. 2022Efficient Reinforcement Learning for Unsupervised Controlled Text Generationcited by 7
  23. 2018Incorporating Discriminator in Sentence Generation: a Gibbs Sampling Methodcited by 5

Built on by

Not cited yet.