mlsanityData to 14 Oct 2026

Learning Disentangled Representations for Natural Language Definitions

arXiv 2210.02898 ↗First posted 22 Sep 2022cs.CL cs.AIcited by 12

Not on the map. Why?

Abstract (arXiv)

Disentangling the encodings of neural models is a fundamental aspect for improving interpretability, semantic control and downstream task performance in Natural Language Processing. Currently, most disentanglement methods are unsupervised or rely on synthetic datasets with known generative factors. We argue that recurrent syntactic and semantic regularities in textual data can be used to provide the models with both structural biases and generative factors. We leverage the semantic structures present in a representative and semantically dense category of sentence types, definitional sentences, for training a Variational Autoencoder to learn disentangled representations. Our experimental results show that the proposed model outperforms unsupervised baselines on several qualitative and quantitative benchmarks for disentanglement, and it also improves the results in the downstream task of definition modeling.

Key facts. Cited by 12 papers in the map (data through 14 Oct 2026). Builds on 26 of its 41 references that are in the map. First posted on arXiv 22 Sep 2022.

Builds on

26 of 41 references.

References · 26

  1. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,599
  2. 2016Pointer Sentinel Mixture Modelscited by 3,096
  3. 2018UMAP: Uniform Manifold Approximation and Projection for Dimension Reductioncited by 2,898
  4. 2018Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representationscited by 941
  5. 2018Disentangling by Factorisingcited by 616
  6. 2015Generating Sentences from a Continuous Spacecited by 612
  7. 2017Toward Controlled Generation of Textcited by 272
  8. 2017Learning Discourse-level Diversity for Neural Dialog Models using Conditional Variational Autoencoderscited by 222
  9. 2018Isolating Sources of Disentanglement in Variational Autoencoderscited by 167
  10. 2018Disentangled Representation Learning for Non-Parallel Text Style Transfercited by 127
  11. 2020Optimus: Organizing Sentences via Pre-trained Modeling of a Latent Spacecited by 114
  12. 2018Learning Deep Disentangled Embeddings with the F-Statistic Losscited by 101
14 more
  1. 2018Learning Disentangled Joint Continuous and Discrete Representationscited by 83
  2. 2020Measuring Disentanglement: A Review of Metricscited by 70
  3. 2019Generating Sentences from Disentangled Syntactic and Semantic Spacescited by 59
  4. 2020Improving Disentangled Text Representation Learning with Information-Theoretic Guidancecited by 52
  5. 2016Definition Modeling: Learning to define word embeddings in natural languagecited by 46
  6. 2019A Multi-Task Approach for Disentangling Syntax and Semantics in Sentence Representationscited by 37
  7. 2021A Novel Estimator of Mutual Information for Learning to Disentangle Textual Representationscited by 37
  8. 2018Conditional Generators of Words Definitionscited by 35
  9. 2015Learning to Understand Phrases by Embedding the Dictionarycited by 33
  10. 2021DefSent: Sentence Embeddings using Definition Sentencescited by 20
  11. 2021Disentangling Generative Factors in Natural Language with Discrete Variational Autoencoderscited by 19
  12. 2017Learning to Compute Word Embeddings On the Flycited by 12
  13. 2018Categorization of Semantic Roles for Dictionary Definitionscited by 3
  14. 2021Unsupervised Representation Disentanglement of Text: An Evaluation on Synthetic Datasetscited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 1; 2023: 4; 2024: 2; 2025: 4; 2026: 1.

12 papers.

  1. 2023Learning Disentangled Semantic Spaces of Explanations via Invertible Neural Networkscited by 6
  2. 2024Improving Semantic Control in Discrete Latent Spaces with Transformer Quantized Variational Autoencoderscited by 6
  3. 2024Are there identifiable structural parts in the sentence embedding whole?cited by 6
  4. 2022Quasi-symbolic Semantic Geometry over Transformer-based Variational AutoEncodercited by 5
  5. 2023Multi-Relational Hyperbolic Word Embeddings from Natural Language Definitionscited by 4
  6. 2023LlaMaVAE: Guiding Large Language Model Generation via Continuous Latent Sentence Spacescited by 3
  7. 2025LangVAE and LangSpace: Building and Probing for Language Model VAEscited by 3
  8. 2025Testing the assumptions about the geometry of sentence embedding spaces: the cosine measure need not applycited by 2
  9. 2023Towards Controllable Natural Language Inference through Lexical Inference Typescited by 1
  10. 2025Discovering Semantic Subdimensions through Disentangled Conceptual Representationscited by 1
  11. 2025Bridging Compositional and Distributional Semantics: A Survey on Latent Semantic Geometry via AutoEncodercited by 0
  12. 2026Principles of Concept Representation in Sentence Encoderscited by 0