mlsanityData to 14 Oct 2026

Unsupervised Text Style Transfer with Deep Generative Models

arXiv 2308.16584 ↗First posted 31 Aug 2023cs.CLcited by 0

Not on the map. Why?

Abstract (arXiv)

We present a general framework for unsupervised text style transfer with deep generative models. The framework models each sentence-label pair in the non-parallel corpus as partially observed from a complete quadruplet which additionally contains two latent codes representing the content and style, respectively. These codes are learned by exploiting dependencies inside the observed data. Then a sentence is transferred by manipulating them. Our framework is able to unify previous embedding and prototype methods as two special forms. It also provides a principled perspective to explain previously proposed techniques in the field such as aligned encoder and adversarial training. We further conduct experiments on three benchmarks. Both automatic and human evaluation results show that our methods achieve better or competitive results compared to several strong baselines.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 50 of its 68 references that are in the map. First posted on arXiv 31 Aug 2023.

Builds on

50 of 68 references.

References · 50

  1. 2017Attention Is All You Needcited by 60,361
  2. 2020Language Models are Few-Shot Learnerscited by 32,419
  3. 2019BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehensioncited by 5,893
  4. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,070
  5. 2014Neural Machine Translation by Jointly Learning to Align and Translatecited by 4,548
  6. 2014Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translationcited by 4,057
  7. 2017Axiomatic Attribution for Deep Networkscited by 3,384
  8. 2013Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Mapscited by 2,371
  9. 2013Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computationcited by 2,079
  10. 2016Variational Inference: A Review for Statisticianscited by 1,472
  11. 2019Attention is not Explanationcited by 929
  12. 2015Cyclical Learning Rates for Training Neural Networkscited by 629
38 more
  1. 2015Generating Sentences from a Continuous Spacecited by 612
  2. 2016f-GAN: Training Generative Neural Samplers using Variational Divergence Minimizationcited by 506
  3. 2014Semi-Supervised Learning with Deep Generative Modelscited by 496
  4. 2015Adversarial Autoencoderscited by 364
  5. 2016Rationalizing Neural Predictionscited by 281
  6. 2017Toward Controlled Generation of Textcited by 272
  7. 2017VAE with a VampPriorcited by 248
  8. 2017Style Transfer from Non-Parallel Text by Cross-Alignmentcited by 248
  9. 2015Building End-To-End Dialogue Systems Using Generative Hierarchical Neural Network Modelscited by 207
  10. 2018Delete, Retrieve, Generate: A Simple Approach to Sentiment and Style Transfercited by 191
  11. 2016A Hierarchical Latent Variable Encoder-Decoder Model for Generating Dialoguescited by 174
  12. 2020Deep Learning for Text Style Transfer: A Surveycited by 162
  13. 2017Style Transfer in Text: Exploration and Evaluationcited by 146
  14. 2018Disentangled Representation Learning for Non-Parallel Text Style Transfercited by 127
  15. 2019Interpretable Neural Predictions with Differentiable Binary Variablescited by 126
  16. 2016Learning in Implicit Generative Modelscited by 125
  17. 2018Style Transfer Through Back-Translationcited by 124
  18. 2020The elephant in the interpretability room: Why use attention as explanation when we have saliency methods?cited by 122
  19. 2017Adversarial Variational Bayes: Unifying Variational Autoencoders and Generative Adversarial Networkscited by 107
  20. 2019Transforming Delete, Retrieve, Generate Approach for Controlled Text Style Transfercited by 81
  21. 2020Politeness Transfer: A Tag and Generate Approachcited by 78
  22. 2016Auxiliary Deep Generative Modelscited by 72
  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. 2020How do Decisions Emerge across Layers in Neural Models? Interpretation with Differentiable Maskingcited by 63
  27. 2019Generating Sentences from Disentangled Syntactic and Semantic Spacescited by 59
  28. 2018Unpaired Sentiment-to-Sentiment Translation: A Cycled Reinforcement Learning Approachcited by 55
  29. 2018Avoiding Latent Variable Collapse With Generative Skip Modelscited by 47
  30. 2018Content preserving text generation with attribute controlscited by 47
  31. 2020Blank Language Modelscited by 43
  32. 2018Regularizing Neural Machine Translation by Target-bidirectional Agreementcited by 40
  33. 2020Learning Variational Word Masks to Improve the Interpretability of Neural Text Classifierscited by 35
  34. 2019Controllable Unsupervised Text Attribute Transfer via Editing Entangled Latent Representationcited by 34
  35. 2014Stochastic Backpropagation and Approximate Inference in Deep Generative Modelscited by 31
  36. 2019Semi-supervised Text Style Transfer: Cross Projection in Latent Spacecited by 21
  37. 2018Adversarial Decomposition of Text Representationcited by 18
  38. 2018Learning Sentiment Memories for Sentiment Modification without Parallel Datacited by 10

Built on by

Not cited yet.