mlsanityData to 14 Oct 2026

Driving Context into Text-to-Text Privatization

arXiv 2306.01457 ↗First posted 2 Jun 2023cs.CL cs.LGcited by 13

Not on the map. Why?

Abstract (arXiv)

textitMetric Differential Privacy enables text-to-text privatization by adding calibrated noise to the vector of a word derived from an embedding space and projecting this noisy vector back to a discrete vocabulary using a nearest neighbor search. Since words are substituted without context, this mechanism is expected to fall short at finding substitutes for words with ambiguous meanings, such as textit'bank'. To account for these ambiguous words, we leverage a sense embedding and incorporate a sense disambiguation step prior to noise injection. We encompass our modification to the privatization mechanism with an estimation of privacy and utility. For word sense disambiguation on the textitWords in Context dataset, we demonstrate a substantial increase in classification accuracy by 6.05%.

Key facts. Cited by 13 papers in the map (data through 14 Oct 2026). Builds on 28 of its 50 references that are in the map. First posted on arXiv 2 Jun 2023.

Builds on

28 of 50 references.

References · 28

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2018GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understandingcited by 4,899
  3. 2013Efficient Estimation of Word Representations in Vector Spacecited by 4,375
  4. 2016Pointer Sentinel Mixture Modelscited by 3,096
  5. 2018Deep contextualized word representationscited by 2,290
  6. 2020Extracting Training Data from Large Language Modelscited by 2,189
  7. 2018Neural Network Acceptability Judgmentscited by 958
  8. 2017Poincar'e Embeddings for Learning Hierarchical Representationscited by 684
  9. 2018WiC: the Word-in-Context Dataset for Evaluating Context-Sensitive Meaning Representationscited by 372
  10. 2019Knowledge Enhanced Contextual Word Representationscited by 296
  11. 2014SimLex-999: Evaluating Semantic Models with (Genuine) Similarity Estimationcited by 172
  12. 2019Privacy- and Utility-Preserving Textual Analysis via Calibrated Multivariate Perturbationscited by 119
16 more
  1. 2019GlossBERT: BERT for Word Sense Disambiguation with Gloss Knowledgecited by 79
  2. 2019SenseBERT: Driving Some Sense into BERTcited by 73
  3. 2019Leveraging Hierarchical Representations for Preserving Privacy and Utility in Textcited by 50
  4. 2021TEM: High Utility Metric Differential Privacy on Textcited by 43
  5. 2020A Differentially Private Text Perturbation Method Using a Regularized Mahalanobis Metriccited by 42
  6. 2015Efficient Non-parametric Estimation of Multiple Embeddings per Word in Vector Spacecited by 35
  7. 2015AutoExtend: Extending Word Embeddings to Embeddings for Synsets and Lexemescited by 19
  8. 2021On a Utilitarian Approach to Privacy Preserving Text Generationcited by 17
  9. 2016De-Conflated Semantic Representationscited by 12
  10. 2017A Mixture Model for Learning Multi-Sense Word Embeddingscited by 12
  11. 2017Making Sense of Word Embeddingscited by 12
  12. 2015Breaking Sticks and Ambiguities with Adaptive Skip-gramcited by 11
  13. 2021Multi-sense embeddings through a word sense disambiguation processcited by 7
  14. 2017MUSE: Modularizing Unsupervised Sense Embeddingscited by 6
  15. 2014A Simple and Efficient Method To Generate Word Sense Representationscited by 4
  16. 2020Differentially Private Adversarial Robustness Through Randomized Perturbationscited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 1; 2024: 3; 2025: 5; 2026: 4.

13 papers.

Sort:

  1. 2023Privacy-Preserving In-Context Learning with Differentially Private Few-Shot Generationcited by 96
  2. 2024Data-adaptive Differentially Private Prompt Synthesis for In-Context Learningcited by 10
  3. 2024Private Language Models via Truncated Laplacian Mechanismcited by 3
  4. 2025Inspecting the Representation Manifold of Differentially-Private Textcited by 2
  5. 2026STAMP: Selective Task-Aware Mechanism for Text Privacycited by 2
  6. 2025Investigating User Perspectives on Differentially Private Text Privatizationcited by 1
  7. 2025The Double-edged Sword of LLM-based Data Reconstruction: Understanding and Mitigating Contextual Vulnerability in Word-level Differential Privacy Text Sanitizationcited by 1
  8. 2026A Systematic Exploration of Text Decomposition and Budget Distribution in Differentially Private Text Obfuscationcited by 1
  9. 2024Characterizing Stereotypical Bias from Privacy-preserving Pre-Trainingcited by 0
  10. 2025Stereo-LiDAR Fusion by Semi-Global Matching With Discrete Disparity-Matching Cost and Semidensificationcited by 0
  11. 2025One Size Fits All? A Modular Adaptive Sanitization Kit (MASK) for Customizable Privacy-Preserving Phone Scam Detectioncited by 0
  12. 2026From Interpretability to Control: Insights from Six Years of the TrustNLP Workshopcited by 0
1 more
  1. 2026PrivBench: A Holistic and Modular Benchmarking Platform for Evaluating Text-to-Text Privatizationcited by 0