no code implementations • 2 Jun 2023 • Stefan Arnold, Dilara Yesilbas, Sven Weinzierl
Lacking the capability to produce surrogate texts that correlate with the structure of the sensitive texts, we encompass our analysis by transforming the privatization step into a candidate selection problem in which substitutions are directed to words with matching grammatical properties.
no code implementations • 2 Jun 2023 • 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.
2 code implementations • 19 Apr 2022 • Patrick Zschech, Sven Weinzierl, Nico Hambauer, Sandra Zilker, Mathias Kraus
The number of information systems (IS) studies dealing with explainable artificial intelligence (XAI) is currently exploding as the field demands more transparency about the internal decision logic of machine learning (ML) models.
1 code implementation • 2 Oct 2020 • An Nguyen, Srijeet Chatterjee, Sven Weinzierl, Leo Schwinn, Martin Matzner, Bjoern Eskofier
To better model the time dependencies between events, we propose a new PBPM technique based on time-aware LSTM (T-LSTM) cells.
1 code implementation • 19 Aug 2020 • Sven Weinzierl, Sebastian Dunzer, Sandra Zilker, Martin Matzner
We present a PrBPM technique that transforms the next most likely activities into the next best actions regarding a given KPI.
1 code implementation • 18 Aug 2020 • Sven Weinzierl, Sandra Zilker, Jens Brunk, Kate Revoredo, Martin Matzner, Jörg Becker
PBPM techniques aim to improve process performance by providing predictions to process analysts, supporting them in their decision making.
1 code implementation • 7 Aug 2020 • Matthias Stierle, Sven Weinzierl, Maximilian Harl, Martin Matzner
Through annotations with metrics such as the frequency or duration of activities, these models provide generic information to the process analyst.