no code implementations • EMNLP (sdp) 2020 • Alaa El-Ebshihy, Annisa Maulida Ningtyas, Linda Andersson, Florina Piroi, Andreas Rauber
In this paper, we present our approach to solve the LongSumm 2020 Shared Task, at the 1st Workshop on Scholarly Document Processing.
no code implementations • 21 Sep 2023 • Anahid Jalali, Bernhard Haslhofer, Simone Kriglstein, Andreas Rauber
Furthermore, we find that counterfactual explanations and misclassifications can significantly increase the users understanding of how a machine learning model is making decisions.
no code implementations • 22 Apr 2023 • Isabell Lederer, Rudolf Mayer, Andreas Rauber
The commercial use of Machine Learning (ML) is spreading; at the same time, ML models are becoming more complex and more expensive to train, which makes Intellectual Property Protection (IPP) of trained models a pressing issue.
no code implementations • 16 Jun 2022 • Daryna Oliynyk, Rudolf Mayer, Andreas Rauber
We address this by categorising and comparing model stealing attacks, assessing their performance, and exploring corresponding defence techniques in different settings.
no code implementations • WS 2020 • Girma Neshir Alemneh, Andreas Rauber, Solomon Atnafu
Due to the advancement of World Wide Web technology, users are not only consumer of web contents but also they are producers of contents in the form of text, audio, video and picture.
no code implementations • WS 2020 • Girma Neshir Alemneh, Andreas Rauber, Solomon Atnafu
To bypass manual development time and costs, we tried to build Amharic Sentiment Lexicons relying on corpus based approach.
no code implementations • 11 Nov 2018 • Botond Fazeka, Alexander Schindler, Thomas Lidy, Andreas Rauber
The audio is fed into a Convolutional Neural Network (CNN) using four convolutional layers.
Sound Audio and Speech Processing