mlsanityData to 14 Oct 2026

Content preserving text generation with attribute controls

arXiv 1811.01135 ↗First posted 3 Nov 2018cs.CL cs.LG stat.MLcited by 47

Not on the map. Why?

Abstract (arXiv)

In this work, we address the problem of modifying textual attributes of sentences. Given an input sentence and a set of attribute labels, we attempt to generate sentences that are compatible with the conditioning information. To ensure that the model generates content compatible sentences, we introduce a reconstruction loss which interpolates between auto-encoding and back-translation loss components. We propose an adversarial loss to enforce generated samples to be attribute compatible and realistic. Through quantitative, qualitative and human evaluations we demonstrate that our model is capable of generating fluent sentences that better reflect the conditioning information compared to prior methods. We further demonstrate that the model is capable of simultaneously controlling multiple attributes.

Key facts. Cited by 47 papers in the map (data through 14 Oct 2026). First posted on arXiv 3 Nov 2018.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 18; 2022: 10; 2023: 11; 2024: 4; 2025: 4.

47 papers.

Sort:

By area:

  1. 2023Large Language Model as Attributed Training Data Generator: A Tale of Diversity and Biascited by 232
  2. 2021Causal Inference in Natural Language Processing: Estimation, Prediction, Interpretation and Beyondcited by 178
  3. 2022A Survey of Controllable Text Generation using Transformer-based Pre-trained Language Modelscited by 129
  4. 2021NL-Augmenter: A Framework for Task-Sensitive Natural Language Augmentationcited by 73
  5. 2021Controlled Text Generation as Continuous Optimization with Multiple Constraintscited by 70
  6. 2021XFORMAL: A Benchmark for Multilingual Formality Style Transfercited by 52
  7. 2021Generating Syntactically Controlled Paraphrases without Using Annotated Parallel Pairscited by 45
  8. 2024Gradient-Based Language Model Red Teamingcited by 34
  9. 2021Civil Rephrases Of Toxic Texts With Self-Supervised Transformerscited by 32
  10. 2022Inducing Positive Perspectives with Text Reframingcited by 31
  11. 2024Personalized Text Generation with Fine-Grained Linguistic Controlcited by 20
  12. 2021Sentence Bottleneck Autoencoders from Transformer Language Modelscited by 19
35 more
  1. 2022Why is constrained neural language generation particularly challenging?cited by 19
  2. 2021A Review of Text Style Transfer using Deep Learningcited by 18
  3. 2024Abstractive Text Summarization: State of the Art, Challenges, and Improvementscited by 17
  4. 2023A Call for Standardization and Validation of Text Style Transfer Evaluationcited by 14
  5. 2022Learning Disentangled Representations of Negation and Uncertaintycited by 13
  6. 2021Political Depolarization of News Articles Using Attribute-aware Word Embeddingscited by 9
  7. 2024Boosting Reward Model with Preference-Conditional Multi-Aspect Synthetic Data Generationcited by 9
  8. 2022So Different Yet So Alike! Constrained Unsupervised Text Style Transfercited by 7
  9. 2023Advancements in Scientific Controllable Text Generation Methodscited by 7
  10. 2023Toward Unified Controllable Text Generation via Regular Expression Instructioncited by 7
  11. 2021Progressive Open-Domain Response Generation with Multiple Controllable Attributescited by 6
  12. 2022T-STAR: Truthful Style Transfer using AMR Graph as Intermediate Representationcited by 6
  13. 2023Evaluating Open-Domain Dialogues in Latent Space with Next Sentence Prediction and Mutual Informationcited by 6
  14. 2021StyleKQC: A Style-Variant Paraphrase Corpus for Korean Questions and Commandscited by 5
  15. 2021From Theories on Styles to their Transfer in Text: Bridging the Gap with a Hierarchical Surveycited by 5
  16. 2022AugCSE: Contrastive Sentence Embedding with Diverse Augmentationscited by 5
  17. 2025Steering Large Language Models with Register Analysis for Arbitrary Style Transfercited by 5
  18. 2025Attributes as Textual Genes: Leveraging LLMs as Genetic Algorithm Simulators for Conditional Synthetic Data Generationcited by 5
  19. 2022StyleFlow: Disentangle Latent Representations via Normalizing Flow for Unsupervised Text Style Transfercited by 4
  20. 2021GTAE: Graph-Transformer based Auto-Encoders for Linguistic-Constrained Text Style Transfercited by 3
  21. 2021Syntax Matters! Syntax-Controlled in Text Style Transfercited by 3
  22. 2022A Review of Affective Generation Modelscited by 3
  23. 2023Is it Possible to Modify Text to a Target Readability Level? An Initial Investigation Using Zero-Shot Large Language Modelscited by 3
  24. 2023Adapter-TST: A Parameter Efficient Method for Multiple-Attribute Text Style Transfercited by 2
  25. 2023Text Attribute Control via Closed-Loop Disentanglementcited by 2
  26. 2025Steering Language Models in Multi-Token Generation: A Case Study on Tense and Aspectcited by 2
  27. 2021Transforming Multi-Conditioned Generation from Meaning Representationcited by 1
  28. 2021A Simple Geometric Method for Cross-Lingual Linguistic Transformations with Pre-trained Autoencoderscited by 1
  29. 2021SE-DAE: Style-Enhanced Denoising Auto-Encoder for Unsupervised Text Style Transfercited by 1
  30. 2022An Overview on Controllable Text Generation via Variational Auto-Encoderscited by 1
  31. 2023Towards Controllable Natural Language Inference through Lexical Inference Typescited by 1
  32. 2021Empirical Evaluation of Supervision Signals for Style Transfer Modelscited by 0
  33. 2023Exposing the Functionalities of Neurons for Gated Recurrent Unit Based Sequence-to-Sequence Modelcited by 0
  34. 2023Unsupervised Text Style Transfer with Deep Generative Modelscited by 0
  35. 2025Generation, Evaluation, and Explanation of Novelists' Styles with Single-Token Promptscited by 0