mlsanityData to 7 Oct 2026

Learning Disentangled Representations of Negation and Uncertainty

arXiv 2204.00511 ↗First posted 1 Apr 2022cs.CL cs.LGcited by 13

Not on the map. Why?

Abstract (arXiv)

Negation and uncertainty modeling are long-standing tasks in natural language processing. Linguistic theory postulates that expressions of negation and uncertainty are semantically independent from each other and the content they modify. However, previous works on representation learning do not explicitly model this independence. We therefore attempt to disentangle the representations of negation, uncertainty, and content using a Variational Autoencoder. We find that simply supervising the latent representations results in good disentanglement, but auxiliary objectives based on adversarial learning and mutual information minimization can provide additional disentanglement gains.

Key facts. Cited by 13 papers in the map (data through 7 Oct 2026). Builds on 24 of its 63 references that are in the map. First posted on arXiv 1 Apr 2022.

Builds on

24 of 63 references.

References · 24

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2016Categorical Reparameterization with Gumbel-Softmaxcited by 2,708
  3. 2020Beyond Accuracy: Behavioral Testing of NLP models with CheckListcited by 979
  4. 2020On Faithfulness and Factuality in Abstractive Summarizationcited by 895
  5. 2015Generating Sentences from a Continuous Spacecited by 607
  6. 2017Toward Controlled Generation of Textcited by 271
  7. 2020CLUB: A Contrastive Log-ratio Upper Bound of Mutual Informationcited by 233
  8. 2018Isolating Sources of Disentanglement in Variational Autoencoderscited by 167
  9. 2017Style Transfer in Text: Exploration and Evaluationcited by 145
  10. 2018Disentangled Representation Learning for Non-Parallel Text Style Transfercited by 127
  11. 2018Learning Disentangled Joint Continuous and Discrete Representationscited by 83
  12. 2019Weakly Supervised Disentanglement with Guaranteescited by 82
12 more
  1. 2019Generating Sentences from Disentangled Syntactic and Semantic Spacescited by 59
  2. 2020Improving Disentangled Text Representation Learning with Information-Theoretic Guidancecited by 52
  3. 2018Content preserving text generation with attribute controlscited by 47
  4. 2021A Novel Estimator of Mutual Information for Learning to Disentangle Textual Representationscited by 37
  5. 2019NegBERT: A Transfer Learning Approach for Negation Detection and Scope Resolutioncited by 36
  6. 2019Weakly Supervised Disentanglement by Pairwise Similaritiescited by 22
  7. 2018A Qualitative Comparison of CoQA, SQuAD 2.0 and QuACcited by 21
  8. 2019Improving Sentiment Analysis with Multi-task Learning of Negationcited by 8
  9. 2016Exploring Different Dimensions of Attention for Uncertainty Detectioncited by 7
  10. 2020Polarized-VAE: Proximity Based Disentangled Representation Learning for Text Generationcited by 7
  11. 2020Do sequence-to-sequence VAEs learn global features of sentences?cited by 6
  12. 2018Seeing Through Misinformation: A Framework for Identifying Fake Online Newscited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 1; 2023: 6; 2024: 2; 2025: 3; 2026: 1.

13 papers.

Sort:

By area:

  1. 2023Learning Disentangled Semantic Spaces of Explanations via Invertible Neural Networkscited by 6
  2. 2023Counterfactuals of Counterfactuals: a back-translation-inspired approach to analyse counterfactual editorscited by 6
  3. 2024Improving Semantic Control in Discrete Latent Spaces with Transformer Quantized Variational Autoencoderscited by 6
  4. 2022Quasi-symbolic Semantic Geometry over Transformer-based Variational AutoEncodercited by 5
  5. 2023Disentangled Variational Autoencoder for Emotion Recognition in Conversationscited by 5
  6. 2025LangVAE and LangSpace: Building and Probing for Language Model VAEscited by 3
  7. 2025Characterizing Mamba's Selective Memory using Auto-Encoderscited by 3
  8. 2023Object Recognition from Scientific Document based on Compartment Refinement Frameworkcited by 1
  9. 2024Logical Negation Augmenting and Debiasing for Prompt-based Methodscited by 1
  10. 2023CausalAPM: Generalizable Literal Disentanglement for NLU Debiasingcited by 0
  11. 2023Factuality Detection using Machine Translation -- a Use Case for German Clinical Textcited by 0
  12. 2025Bridging Compositional and Distributional Semantics: A Survey on Latent Semantic Geometry via AutoEncodercited by 0
1 more
  1. 2026Uncovering Latent Reasoning Strategies in Language Modelscited by 0