3 citations · 4 across the 5 of their papers we have counts for
5 papers
FindMyText: Robust, Scalable Detection of Text Containment in Large Web-Crawled Corpora
Lars Henry Berge Olsen, Pierre Lison, Martin Jullum +1
We present FindMyText, an open-source Python package designed to efficiently assess whether a given text appears, in part or in full, within a text corpus. The tool builds on prior…
Protecting De-identified Documents from Search-based Linkage Attacks
Pierre Lison, Mark Anderson
While de-identification models can help conceal the identity of the individuals mentioned in a document, they fail to address linkage risks, defined as the potential to map the de-…
Fairness-Aware Low-Rank Representation Fine-Tuning
Parameswaran Kamalaruban, Mark Anderson, Stuart Burrell +3
Pre-trained foundation models can be efficiently adapted for specific tasks using Low-Rank Adaptation (LoRA), but the fairness properties of these adapted classifiers remain undere…
Neural Text Sanitization with Privacy Risk Indicators: An Empirical Analysis
Anthi Papadopoulou, Pierre Lison, Mark Anderson +2
Text sanitization is the task of redacting a document to mask all occurrences of (direct or indirect) personal identifiers, with the goal of concealing the identity of the individu…
Learning from learning machines: a new generation of AI technology to meet the needs of science
Luca Pion-Tonachini, Kristofer Bouchard, Hector Garcia Martin +33
We outline emerging opportunities and challenges to enhance the utility of AI for scientific discovery. The distinct goals of AI for industry versus the goals of AI for science cre…