mlsanityData to 7 Oct 2026

Generating Sentences from Disentangled Syntactic and Semantic Spaces

arXiv 1907.05789 ↗First posted 6 Jul 2019cs.CLcited by 59

Not on the map. Why?

Abstract (arXiv)

Variational auto-encoders (VAEs) are widely used in natural language generation due to the regularization of the latent space. However, generating sentences from the continuous latent space does not explicitly model the syntactic information. In this paper, we propose to generate sentences from disentangled syntactic and semantic spaces. Our proposed method explicitly models syntactic information in the VAE's latent space by using the linearized tree sequence, leading to better performance of language generation. Additionally, the advantage of sampling in the disentangled syntactic and semantic latent spaces enables us to perform novel applications, such as the unsupervised paraphrase generation and syntax-transfer generation. Experimental results show that our proposed model achieves similar or better performance in various tasks, compared with state-of-the-art related work.

Key facts. Cited by 59 papers in the map (data through 7 Oct 2026). First posted on arXiv 6 Jul 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 16; 2022: 16; 2023: 10; 2024: 6; 2025: 8; 2026: 3.

59 papers.

Sort:

By area:

  1. 2022Disentangled Representation Learningcited by 111
  2. 2021Continual Learning for Text Classification with Information Disentanglement Based Regularizationcited by 86
  3. 2021Tailor: Generating and Perturbing Text with Semantic Controlscited by 67
  4. 2021Generating Syntactically Controlled Paraphrases without Using Annotated Parallel Pairscited by 45
  5. 2021Transformer-based Conditional Variational Autoencoder for Controllable Story Generationcited by 44
  6. 2021A Novel Estimator of Mutual Information for Learning to Disentangle Textual Representationscited by 37
  7. 2022Quality Controlled Paraphrase Generationcited by 31
  8. 2021Disentangling Semantics and Syntax in Sentence Embeddings with Pre-trained Language Modelscited by 22
  9. 2021Factorising Meaning and Form for Intent-Preserving Paraphrasingcited by 22
  10. 2021Convex Aggregation for Opinion Summarizationcited by 21
  11. 2022Hierarchical Sketch Induction for Paraphrase Generationcited by 21
  12. 2022Why is constrained neural language generation particularly challenging?cited by 19
38 more
  1. 2023Prompt-Based Editing for Text Style Transfercited by 16
  2. 2021Improving Formality Style Transfer with Context-Aware Rule Injectioncited by 13
  3. 2021ConRPG: Paraphrase Generation using Contexts as Regularizercited by 13
  4. 2022Learning Disentangled Representations of Negation and Uncertaintycited by 13
  5. 2023Disentangled Counterfactual Learning for Physical Audiovisual Commonsense Reasoningcited by 13
  6. 2022Learning Disentangled Representations for Natural Language Definitionscited by 12
  7. 2021Transferable Persona-Grounded Dialogues via Grounded Minimal Editscited by 10
  8. 2022Towards Robust and Semantically Organised Latent Representations for Unsupervised Text Style Transfercited by 7
  9. 2023Learning Disentangled Semantic Spaces of Explanations via Invertible Neural Networkscited by 6
  10. 2023Graph-Induced Syntactic-Semantic Spaces in Transformer-Based Variational AutoEncoderscited by 6
  11. 2024Improving Semantic Control in Discrete Latent Spaces with Transformer Quantized Variational Autoencoderscited by 6
  12. 2024Are there identifiable structural parts in the sentence embedding whole?cited by 6
  13. 2025Decoupling Content and Expression: Two-Dimensional Detection of AI-Generated Textcited 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. 2022Towards Unsupervised Content Disentanglement in Sentence Representations via Syntactic Rolescited by 5
  17. 2022Quasi-symbolic Semantic Geometry over Transformer-based Variational AutoEncodercited by 5
  18. 2023Disentangled Variational Autoencoder for Emotion Recognition in Conversationscited by 5
  19. 2022Unsupervised Syntactically Controlled Paraphrase Generation with Abstract Meaning Representationscited by 4
  20. 2022StyleFlow: Disentangle Latent Representations via Normalizing Flow for Unsupervised Text Style Transfercited by 4
  21. 2024Enhanced Coherence-Aware Network with Hierarchical Disentanglement for Aspect-Category Sentiment Analysiscited by 4
  22. 2024P-TA: Using Proximal Policy Optimization to Enhance Tabular Data Augmentation via Large Language Modelscited by 4
  23. 2021Learning to Selectively Learn for Weakly-supervised Paraphrase Generationcited by 3
  24. 2021VIRT: Improving Representation-based Models for Text Matching through Virtual Interactioncited by 3
  25. 2022Exploiting Inductive Bias in Transformers for Unsupervised Disentanglement of Syntax and Semantics with VAEscited by 3
  26. 2023LlaMaVAE: Guiding Large Language Model Generation via Continuous Latent Sentence Spacescited by 3
  27. 2024Dual-disentangled Deep Multiple Clusteringcited by 3
  28. 2025Disentangling Feature Structure: A Mathematically Provable Two-Stage Training Dynamics in Transformerscited by 3
  29. 2025LangVAE and LangSpace: Building and Probing for Language Model VAEscited by 3
  30. 2022Unsupervised Opinion Summarisation in the Wasserstein Spacecited by 2
  31. 2025Testing the assumptions about the geometry of sentence embedding spaces: the cosine measure need not applycited by 2
  32. 2021Unsupervised Representation Disentanglement of Text: An Evaluation on Synthetic Datasetscited by 1
  33. 2022An Overview on Controllable Text Generation via Variational Auto-Encoderscited by 1
  34. 2022Accelerating Antimicrobial Peptide Discovery with Latent Structurecited by 1
  35. 2023Towards Controllable Natural Language Inference through Lexical Inference Typescited by 1
  36. 2025Robust Drone-View Geo-Localization via Content-Viewpoint Disentanglementcited by 1
  37. 2026Enhancing Visual In-Context Learning by Multi-Faceted Fusioncited by 1
  38. 2022Noun2Verb: Probabilistic frame semantics for word class conversioncited by 0

50 most cited of 59 All 59 (JSON)