English
Related papers

Related papers: The Text Anonymization Benchmark (TAB): A Dedicate…

200 papers

The language models, especially the basic text classification models, have been shown to be susceptible to textual adversarial attacks such as synonym substitution and word insertion attacks. To defend against such attacks, a growing body…

Cryptography and Security · Computer Science 2024-06-12 Xinyu Zhang , Hanbin Hong , Yuan Hong , Peng Huang , Binghui Wang , Zhongjie Ba , Kui Ren

Voice anonymization aims to conceal speaker identity and attributes while preserving intelligibility, but current evaluations rely almost exclusively on Equal Error Rate (EER) that obscures whether adversaries can mount high-precision…

Cryptography and Security · Computer Science 2026-01-27 Efthymios Tsaprazlis , Thanathai Lertpetchpun , Tiantian Feng , Sai Praneeth Karimireddy , Shrikanth Narayanan

Deep neural networks trained via empirical risk minimisation often exhibit significant performance disparities across groups, particularly when group and task labels are spuriously correlated (e.g., "grassy background" and "cows"). Existing…

Being able to understand information is a key factor for a self-determined life and society. It is also very important for participating in democratic processes. The study of automatic text simplification is often limited by the…

Computation and Language · Computer Science 2026-03-17 Stefan Bott , Verena Riegler , Horacio Saggion , Almudena Rascón Alcaina , Nouran Khallaf

Tokenisation - "the process of splitting text into atomic parts" (Brezina & Timperley, 2017: 1) - is a crucial step for corpus linguistics, as it provides the basis for any applicable quantitative method (e.g. collocations) while ensuring…

Computation and Language · Computer Science 2025-07-03 Matteo Di Cristofaro

Topic modelling is a text mining technique for identifying salient themes from a number of documents. The output is commonly a set of topics consisting of isolated tokens that often co-occur in such documents. Manual effort is often…

Computation and Language · Computer Science 2024-04-26 Lowri Williams , Eirini Anthi , Laura Arman , Pete Burnap

Rather than anonymizing social graphs by generalizing them to super nodes/edges or adding/removing nodes and edges to satisfy given privacy parameters, recent methods exploit the semantics of uncertain graphs to achieve privacy protection…

Social and Information Networks · Computer Science 2014-08-07 Hiep H. Nguyen , Abdessamad Imine , Michaël Rusinowitch

Authorship verification is the task of determining if two distinct writing samples share the same author and is typically concerned with the attribution of written text. In this paper, we explore the attribution of transcribed speech, which…

Computation and Language · Computer Science 2025-05-19 Cristina Aggazzotti , Nicholas Andrews , Elizabeth Allyn Smith

In speaker anonymization, speech recordings are modified in a way that the identity of the speaker remains hidden. While this technology could help to protect the privacy of individuals around the globe, current research restricts this by…

Computation and Language · Computer Science 2024-10-08 Sarina Meyer , Florian Lux , Ngoc Thang Vu

Legal documents are often long, dense, and difficult to comprehend, not only for laypeople but also for legal experts. While automated document summarization has great potential to improve access to legal knowledge, prevailing task-based…

Computation and Language · Computer Science 2026-03-24 Tsz Fung Pang , Maryam Berijanian , Thomas Orth , Breanna Shi , Charlotte S. Alexander

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 perturbed text.…

Computation and Language · Computer Science 2023-10-18 Stefan Arnold , Nils Kemmerzell , Annika Schreiner

Sharing sensitive texts for scientific purposes requires appropriate techniques to protect the privacy of patients and healthcare personnel. Anonymizing textual data is particularly challenging due to the presence of diverse unstructured…

Computation and Language · Computer Science 2025-02-20 Ibrahim Baroud , Lisa Raithel , Sebastian Möller , Roland Roller

Existing topic modeling and text segmentation methodologies generally require large datasets for training, limiting their capabilities when only small collections of text are available. In this work, we reexamine the inter-related problems…

Information Retrieval · Computer Science 2021-05-26 Qiong Wu , Adam Hare , Sirui Wang , Yuwei Tu , Zhenming Liu , Christopher G. Brinton , Yanhua Li

The increasing use of cloud-based speech assistants has heightened the need for effective speech anonymization, which aims to obscure a speaker's identity while retaining critical information for subsequent tasks. One approach to achieving…

Artificial Intelligence · Computer Science 2024-10-22 Suhita Ghosh , Tim Thiele , Frederic Lorbeer , Frank Dreyer , Sebastian Stober

Measuring similarity between texts is an important task for several applications. Available approaches to measure document similarity are inadequate for document pairs that have non-comparable lengths, such as a long document and its…

Computation and Language · Computer Science 2019-03-27 Hongyu Gong , Tarek Sakakini , Suma Bhat , Jinjun Xiong

Text style can reveal sensitive attributes of the author (e.g. race or age) to the reader, which can, in turn, lead to privacy violations and bias in both human and algorithmic decisions based on text. For example, the style of writing in…

Machine Learning · Computer Science 2021-09-13 Fatemehsadat Mireshghallah , Taylor Berg-Kirkpatrick

We show that while anonymization effectively obscures firm identity, it significantly reduces the power of textual understanding, thereby diminishing models' ability to extract meaningful economic signals from financial texts. This…

General Finance · Quantitative Finance 2025-11-20 Ke Wu , Baozhong Yang , Zhenkun Ying , Dexin Zhou

This work investigates the effectiveness of different pseudonymization techniques, ranging from rule-based substitutions to using pre-trained Large Language Models (LLMs), on a variety of datasets and models used for two widely used NLP…

Computation and Language · Computer Science 2023-06-12 Oleksandr Yermilov , Vipul Raheja , Artem Chernodub

System logs constitute valuable information for analysis and diagnosis of system behavior. The size of parallel computing systems and the number of their components steadily increase. The volume of generated logs by the system is in…

Distributed, Parallel, and Cluster Computing · Computer Science 2019-01-23 Siavash Ghiasvand , Florina M. Ciorba

Authorship identification has proven unsettlingly effective in inferring the identity of the author of an unsigned document, even when sensitive personal information has been carefully omitted. In the digital era, individuals leave a…

Computation and Language · Computer Science 2023-10-04 Haining Wang
‹ Prev 1 8 9 10 Next ›