Search Results for author:
Found 7 papers, 0 papers with code
ARTU / TU Wien and Artificial Researcher@ LongSumm 20
In this paper, we present our approach to solve the LongSumm 2020 Shared Task, at the 1st Workshop on Scholarly Document Processing.
Predictability and Comprehensibility in Post-Hoc XAI Methods: A User-Centered Analysis
Furthermore, we find that counterfactual explanations and misclassifications can significantly increase the users understanding of how a machine learning model is making decisions.
Identifying Appropriate Intellectual Property Protection Mechanisms for Machine Learning Models: A Systematization of Watermarking, Fingerprinting, Model Access, and Attacks
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.
I Know What You Trained Last Summer: A Survey on Stealing Machine Learning Models and Defences
We address this by categorising and comparing model stealing attacks, assessing their performance, and exploring corresponding defence techniques in different settings.
Negation handling for Amharic sentiment classification
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.
Corpus based Amharic sentiment lexicon generation
To bypass manual development time and costs, we tried to build Amharic Sentiment Lexicons relying on corpus based approach.
A Multi-modal Deep Neural Network approach to Bird-song identification
The audio is fed into a Convolutional Neural Network (CNN) using four convolutional layers.
Sound Audio and Speech Processing
