mlsanityData to 7 Oct 2026

T-STAR: Truthful Style Transfer using AMR Graph as Intermediate Representation

arXiv 2212.01667 ↗First posted 3 Dec 2022cs.CLcited by 6

Not on the map. Why?

Abstract (arXiv)

Unavailability of parallel corpora for training text style transfer (TST) models is a very challenging yet common scenario. Also, TST models implicitly need to preserve the content while transforming a source sentence into the target style. To tackle these problems, an intermediate representation is often constructed that is devoid of style while still preserving the meaning of the source sentence. In this work, we study the usefulness of Abstract Meaning Representation (AMR) graph as the intermediate style agnostic representation. We posit that semantic notations like AMR are a natural choice for an intermediate representation. Hence, we propose T-STAR: a model comprising of two components, text-to-AMR encoder and a AMR-to-text decoder. We propose several modeling improvements to enhance the style agnosticity of the generated AMR. To the best of our knowledge, T-STAR is the first work that uses AMR as an intermediate representation for TST. With thorough experimental evaluation we show T-STAR significantly outperforms state of the art techniques by achieving on an average 15.2% higher content preservation with negligible loss (3% approx.) in style accuracy. Through detailed human evaluation with 90,000 ratings, we also show that T-STAR has up to 50% lesser hallucinations compared to state of the art TST models.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 48 of its 75 references that are in the map. First posted on arXiv 3 Dec 2022.

Builds on

48 of 75 references.

References · 48

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
  3. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,266
  4. 2019BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehensioncited by 5,874
  5. 2019DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lightercited by 4,243
  6. 2019The Curious Case of Neural Text Degenerationcited by 2,881
  7. 2018Adafactor: Adaptive Learning Rates with Sublinear Memory Costcited by 896
  8. 2022RLPrompt: Optimizing Discrete Text Prompts with Reinforcement Learningcited by 361
  9. 2017Style Transfer from Non-Parallel Text by Cross-Alignmentcited by 246
  10. 2018Delete, Retrieve, Generate: A Simple Approach to Sentiment and Style Transfercited by 191
  11. 2020Reformulating Unsupervised Style Transfer as Paraphrase Generationcited by 181
  12. 2020Deep Learning for Text Style Transfer: A Surveycited by 161
36 more
  1. 2017Style Transfer in Text: Exploration and Evaluationcited by 145
  2. 2018Disentangled Representation Learning for Non-Parallel Text Style Transfercited by 127
  3. 2018Style Transfer Through Back-Translationcited by 124
  4. 2019Beyond BLEU: Training Neural Machine Translation with Semantic Similaritycited by 84
  5. 2019Transforming Delete, Retrieve, Generate Approach for Controlled Text Style Transfercited by 81
  6. 2020Politeness Transfer: A Tag and Generate Approachcited by 78
  7. 2020A Probabilistic Formulation of Unsupervised Text Style Transfercited by 70
  8. 2019A Dual Reinforcement Learning Framework for Unsupervised Text Style Transfercited by 65
  9. 2020PowerTransformer: Unsupervised Controllable Revision for Biased Language Correctioncited by 59
  10. 2018Polite Dialogue Generation Without Parallel Datacited by 57
  11. 2018A Graph-to-Sequence Model for AMR-to-Text Generationcited by 56
  12. 2018Unpaired Sentiment-to-Sentiment Translation: A Cycled Reinforcement Learning Approachcited by 55
  13. 2022Graph Pre-training for AMR Parsing and Generationcited by 55
  14. 2019AMR Parsing as Sequence-to-Graph Transductioncited by 50
  15. 2018Content preserving text generation with attribute controlscited by 47
  16. 2020AMR Parsing via Graph-Sequence Iterative Inferencecited by 47
  17. 2019Semantic Neural Machine Translation using AMRcited by 37
  18. 2018Abstract Meaning Representation for Multi-Document Summarizationcited by 35
  19. 2019Controllable Unsupervised Text Attribute Transfer via Editing Entangled Latent Representationcited by 34
  20. 2020Improving AMR Parsing with Sequence-to-Sequence Pre-trainingcited by 30
  21. 2019Simple and Effective Paraphrastic Similarity from Parallel Translationscited by 25
  22. 2018Guided Neural Language Generation for Abstractive Summarization using Abstract Meaning Representationcited by 24
  23. 2020On Learning Text Style Transfer with Direct Rewardscited by 24
  24. 2020Style-transfer and Paraphrase: Looking for a Sensible Semantic Similarity Metriccited by 23
  25. 2018Multiple-Attribute Text Style Transfercited by 20
  26. 2019Style Transfer for Texts: Retrain, Report Errors, Compare with Rewritescited by 19
  27. 2020Contextual Text Style Transfercited by 16
  28. 2020Multilingual AMR-to-Text Generationcited by 12
  29. 2022Interpretable AMR-Based Question Decomposition for Multi-hop Question Answeringcited by 12
  30. 2017Addressing the Data Sparsity Issue in Neural AMR Parsingcited by 11
  31. 2020Online Back-Parsing for AMR-to-Text Generationcited by 9
  32. 2019Improved Sentiment Detection via Label Transfer from Monolingual to Synthetic Code-Switched Textcited by 8
  33. 2018Sentiment Transfer using Seq2Seq Adversarial Autoencoderscited by 4
  34. 2019Decomposing Textual Information For Style Transfercited by 3
  35. 2021GTAE: Graph-Transformer based Auto-Encoders for Linguistic-Constrained Text Style Transfercited by 3
  36. 2020Incorporate Semantic Structures into Machine Translation Evaluation via UCCAcited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 1; 2024: 2; 2025: 2; 2026: 1.

6 papers.

  1. 2024Compressing Long Context for Enhancing RAG with AMR-based Concept Distillationcited by 16
  2. 2024TinyStyler: Efficient Few-Shot Text Style Transfer with Authorship Embeddingscited by 16
  3. 2023Lost in Translationese? Reducing Translation Effect Using Abstract Meaning Representationcited by 10
  4. 2025Sentence Smith: Controllable Edits for Evaluating Text Embeddingscited by 4
  5. 2025Evaluating Style-Personalized Text Generation: Challenges and Directionscited by 2
  6. 2026RT-SFT: Text Style Transfer from Non-Parallel Corpora by Roundtrip Translationcited by 0