mlsanityData to 13 Oct 2026

Unpaired Sentiment-to-Sentiment Translation: A Cycled Reinforcement Learning Approach

arXiv 1805.05181 ↗First posted 14 May 2018cs.CLcited by 55

Not on the map. Why?

Abstract (arXiv)

The goal of sentiment-to-sentiment "translation" is to change the underlying sentiment of a sentence while keeping its content. The main challenge is the lack of parallel data. To solve this problem, we propose a cycled reinforcement learning method that enables training on unpaired data by collaboration between a neutralization module and an emotionalization module. We evaluate our approach on two review datasets, Yelp and Amazon. Experimental results show that our approach significantly outperforms the state-of-the-art systems. Especially, the proposed method substantially improves the content preservation performance. The BLEU score is improved from 1.64 to 22.46 and from 0.56 to 14.06 on the two datasets, respectively.

Key facts. Cited by 55 papers in the map (data through 13 Oct 2026). First posted on arXiv 14 May 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 13 Oct)

Citing papers per year: 2021: 17; 2022: 13; 2023: 15; 2024: 8; 2025: 1; 2026: 1.

55 papers.

Sort:

By area:

  1. 2021Mind the Style of Text! Adversarial and Backdoor Attacks Based on Text Style Transfercited by 158
  2. 2021A Recipe For Arbitrary Text Style Transfer with Large Language Modelscited by 107
  3. 2023Controlled Text Generation with Natural Language Instructionscited by 87
  4. 2021XFORMAL: A Benchmark for Multilingual Formality Style Transfercited by 51
  5. 2022Prompt-and-Rerank: A Method for Zero-Shot and Few-Shot Arbitrary Textual Style Transfer with Small Language Modelscited by 49
  6. 2021Civil Rephrases Of Toxic Texts With Self-Supervised Transformerscited by 32
  7. 2021Parallel Refinements for Lexically Constrained Text Generation with BARTcited by 24
  8. 2021Enhancing Content Preservation in Text Style Transfer Using Reverse Attention and Conditional Layer Normalizationcited by 20
  9. 2024StyleRemix: Interpretable Authorship Obfuscation via Distillation and Perturbation of Style Elementscited by 18
  10. 2022Text Revision by On-the-Fly Representation Optimizationcited by 17
  11. 2022Proactively Reducing the Hate Intensity of Online Posts via Hate Speech Normalizationcited by 17
  12. 2023Think Twice: A Human-like Two-stage Conversational Agent for Emotional Response Generationcited by 14
38 more
  1. 2023A Call for Standardization and Validation of Text Style Transfer Evaluationcited by 14
  2. 2023STEER: Unified Style Transfer with Expert Reinforcementcited by 14
  3. 2021A Survey of Natural Language Generationcited by 13
  4. 2021Transductive Learning for Unsupervised Text Style Transfercited by 12
  5. 2022Human Judgement as a Compass to Navigate Automatic Metrics for Formality Transfercited by 12
  6. 2021Generic resources are what you need: Style transfer tasks without task-specific parallel training datacited by 10
  7. 2023Diversify Question Generation with Retrieval-Augmented Style Transfercited by 10
  8. 2021Political Depolarization of News Articles Using Attribute-aware Word Embeddingscited by 9
  9. 2022On The Robustness of Offensive Language Classifierscited by 8
  10. 2022StoryTrans: Non-Parallel Story Author-Style Transfer with Discourse Representations and Content Enhancingcited by 8
  11. 2022Efficient Reinforcement Learning for Unsupervised Controlled Text Generationcited by 7
  12. 2024Unsupervised Text Style Transfer via LLMs and Attention Masking with Multi-way Interactionscited by 7
  13. 2024LLM-based Rewriting of Inappropriate Argumentation using Reinforcement Learning from Machine Feedbackcited by 7
  14. 2022T-STAR: Truthful Style Transfer using AMR Graph as Intermediate Representationcited by 6
  15. 2023Don't Take This Out of Context! On the Need for Contextual Models and Evaluations for Stylistic Rewritingcited by 6
  16. 2021From Solving a Problem Boldly to Cutting the Gordian Knot: Idiomatic Text Generationcited by 5
  17. 2021From Theories on Styles to their Transfer in Text: Bridging the Gap with a Hierarchical Surveycited by 5
  18. 2023Translating away Translationese without Parallel Datacited by 5
  19. 2024LMStyle Benchmark: Evaluating Text Style Transfer for Chatbotscited by 5
  20. 2024Text Style Transfer: An Introductory Overviewcited by 5
  21. 2022StyleFlow: Disentangle Latent Representations via Normalizing Flow for Unsupervised Text Style Transfercited by 4
  22. 2021GTAE: Graph-Transformer based Auto-Encoders for Linguistic-Constrained Text Style Transfercited by 3
  23. 2023Active Learning for Natural Language Generationcited by 3
  24. 2024Continuous Language Model Interpolation for Dynamic and Controllable Text Generationcited by 3
  25. 2021Stylistic Retrieval-based Dialogue System with Unparallel Training Datacited by 2
  26. 2023Specializing Small Language Models towards Complex Style Transfer via Latent Attribute Pre-Trainingcited by 2
  27. 2021SE-DAE: Style-Enhanced Denoising Auto-Encoder for Unsupervised Text Style Transfercited by 1
  28. 2021Bag-of-Vectors Autoencoders for Unsupervised Conditional Text Generationcited by 1
  29. 2022Russian Texts Detoxification with Levenshtein Editingcited by 1
  30. 2023"When Words Fail, Emojis Prevail": Generating Sarcastic Utterances with Emoji Using Valence Reversal and Semantic Incongruitycited by 1
  31. 2024Analyzing Sentiment Polarity Reduction in News Presentation through Contextual Perturbation and Large Language Modelscited by 1
  32. 2021Topical Language Generation using Transformerscited by 0
  33. 2022Learning from Bootstrapping and Stepwise Reinforcement Reward: A Semi-Supervised Framework for Text Style Transfercited by 0
  34. 2022On Text Style Transfer via Style Masked Language Modelscited by 0
  35. 2022SimpleStyle: An Adaptable Style Transfer Approachcited by 0
  36. 2023Generative Sentiment Transfer via Adaptive Maskingcited by 0
  37. 2023MSSRNet: Manipulating Sequential Style Representation for Unsupervised Text Style Transfercited by 0
  38. 2023Tweet Sentiment Extraction using Viterbi Algorithm with Transfer Learningcited by 0

50 most cited of 55 All 55 (JSON)