mlsanityData to 7 Oct 2026

Replacing Language Model for Style Transfer

arXiv 2211.07343 ↗First posted 14 Nov 2022cs.CL cs.LGcited by 3

Not on the map. Why?

Abstract (arXiv)

We introduce replacing language model (RLM), a sequence-to-sequence language modeling framework for text style transfer (TST). Our method autoregressively replaces each token of the source sentence with a text span that has a similar meaning but in the target style. The new span is generated via a non-autoregressive masked language model, which can better preserve the local-contextual meaning of the replaced token. This RLM generation scheme gathers the flexibility of autoregressive models and the accuracy of non-autoregressive models, which bridges the gap between sentence-level and word-level style transfer methods. To control the generation style more precisely, we conduct a token-level style-content disentanglement on the hidden representations of RLM. Empirical results on real-world text datasets demonstrate the effectiveness of RLM compared with other TST baselines. The code is at https://github.com/Linear95/RLM.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 35 of its 53 references that are in the map. First posted on arXiv 14 Nov 2022.

Builds on

35 of 53 references.

References · 35

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  3. 2020Language Models are Few-Shot Learnerscited by 32,199
  4. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,266
  5. 2013Auto-Encoding Variational Bayescited by 3,980
  6. 2020Making Pre-trained Language Models Better Few-shot Learnerscited by 1,255
  7. 2018Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representationscited by 929
  8. 2016Deep Variational Information Bottleneckcited by 915
  9. 2018Personalizing Dialogue Agents: I have a dog, do you have pets too?cited by 820
  10. 2019On Variational Bounds of Mutual Informationcited by 550
  11. 2018Diverse Image-to-Image Translation via Disentangled Representationscited by 296
  12. 2017Toward Controlled Generation of Textcited by 271
23 more
  1. 2017Style Transfer from Non-Parallel Text by Cross-Alignmentcited by 246
  2. 2020CLUB: A Contrastive Log-ratio Upper Bound of Mutual Informationcited by 233
  3. 2018Dear Sir or Madam, May I introduce the GYAFC Dataset: Corpus, Benchmarks and Metrics for Formality Style Transfercited by 209
  4. 2018Delete, Retrieve, Generate: A Simple Approach to Sentiment and Style Transfercited by 191
  5. 2018Disentangled Representation Learning for Non-Parallel Text Style Transfercited by 127
  6. 2018Learning to Write with Cooperative Discriminatorscited by 119
  7. 2022Why Exposure Bias Matters: An Imitation Learning Perspective of Error Accumulation in Language Generationcited by 106
  8. 2019Style Transformer: Unpaired Text Style Transfer without Disentangled Latent Representationcited by 84
  9. 2019Transforming Delete, Retrieve, Generate Approach for Controlled Text Style Transfercited by 81
  10. 2020Politeness Transfer: A Tag and Generate Approachcited by 78
  11. 2018Unsupervised Text Style Transfer using Language Models as Discriminatorscited by 70
  12. 2020A Probabilistic Formulation of Unsupervised Text Style Transfercited by 70
  13. 2020Improving Disentangled Text Representation Learning with Information-Theoretic Guidancecited by 52
  14. 2019"Mask and Infill" : Applying Masked Language Model to Sentiment Transfercited by 48
  15. 2020Blank Language Modelscited by 43
  16. 2021LEWIS: Levenshtein Editing for Unsupervised Text Style Transfercited by 40
  17. 2020BANG: Bridging Autoregressive and Non-autoregressive Generation with Large Scale Pretrainingcited by 33
  18. 2021Improving Zero-shot Voice Style Transfer via Disentangled Representation Learningcited by 32
  19. 2021Thank you BART! Rewarding Pre-Trained Models Improves Formality Style Transfercited by 28
  20. 2021Enhancing Content Preservation in Text Style Transfer Using Reverse Attention and Conditional Layer Normalizationcited by 20
  21. 2022Text Revision by On-the-Fly Representation Optimizationcited by 17
  22. 2021Transferable Persona-Grounded Dialogues via Grounded Minimal Editscited by 10
  23. 2021NAST: A Non-Autoregressive Generator with Word Alignment for Unsupervised Text Style Transfercited by 7

Built on by

Cited by year

Citing papers per year: 2023: 2; 2024: 0; 2025: 1.

3 papers.

  1. 2023FollowBench: A Multi-level Fine-grained Constraints Following Benchmark for Large Language Modelscited by 112
  2. 2023Chunk, Align, Select: A Simple Long-sequence Processing Method for Transformerscited by 9
  3. 2025Towards Efficient and Effective Alignment of Large Language Modelscited by 0