paper-with-me

홈 › Papers

Driving Context into Text-to-Text Privatization

2023-06-02 · Stefan Arnold, Dilara Yesilbas, Sven Weinzierl

\textit{Metric 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 \textit{Words in Context} dataset, we demonstrate a substantial increase in classification accuracy by $6.05\%$.

📄 PDF Abstract BibTeX arXiv:2306.01457

Code (0)

등록된 구현이 없습니다.

Tasks

Word Sense Disambiguation

Similar Papers 제목 키워드 기반

Guiding Text-to-Text Privatization by Syntax

2023-06-02 · Stefan Arnold, Dilara Yesilbas, Sven Weinzierl

Metric Differential Privacy is a generalization of differential privacy tailored to address the unique challenges of text-to-text privatization. By adding noise to the representation of words in the geometric space of em…

Disentangling the Linguistic Competence of Privacy-Preserving BERT

2023-10-17 · Stefan Arnold, Nils Kemmerzell, Annika Schreiner

Differential Privacy (DP) has been tailored to address the unique challenges of text-to-text privatization. However, text-to-text privatization is known for degrading the performance of language models when trained on pe…

Privacy Preserving

Characterizing Stereotypical Bias from Privacy-preserving Pre-Training

2024-06-30 · Stefan Arnold, Rene Gröbner, Annika Schreiner

Differential Privacy (DP) can be applied to raw text by exploiting the spatial arrangement of words in an embedding space. We investigate the implications of such text privatization on Language Models (LMs) and their ten…

Language ModelingLanguage ModellingPrivacy Preserving

When does privatization spur entrepreneurial performance? The moderating effect of institutional quality in an emerging market

2019-01-10

We explore how institutional quality moderates the effectiveness of privatization on entrepreneurs sales performance. To do this, we blend agency theory and entrepreneurial cognition theory with insights from institution…

Investigating User Perspectives on Differentially Private Text Privatization

2025-03-12 · Stephen Meisenbacher, Alexandra Klymenko, Alexander Karpp, Florian Matthes

Recent literature has seen a considerable uptick in $\textit{Differentially Private Natural Language Processing}$ (DP NLP). This includes DP text privatization, where potentially sensitive input texts are transformed und…