no code implementations • 30 Nov 2022 • Kishaloy Halder, Josip Krapac, Alan Akbik, Anthony Brew, Matti Lyra
In a series of experiments, we show that this yields a number of interesting benefits: (1) The resulting order induced by distances in the embedding space can be used to directly explain classification decisions.
no code implementations • 25 Oct 2022 • Kishaloy Halder, Josip Krapac, Dmitry Goryunov, Anthony Brew, Matti Lyra, Alsida Dizdari, William Gillett, Adrien Renahy, Sinan Tang
Ensuring safety of the products offered to the customers is of paramount importance to any e- commerce platform.
1 code implementation • COLING 2020 • Kishaloy Halder, Alan Akbik, Josip Krapac, Roland Vollgraf
State-of-the-art approaches for text classification leverage a transformer architecture with a linear layer on top that outputs a class distribution for a given prediction problem.
3 code implementations • 14 May 2019 • Ivan Krešo, Josip Krapac, Siniša Šegvić
Recent progress of deep image classification models has provided great potential to improve state-of-the-art performance in related computer vision tasks.
no code implementations • 23 Apr 2019 • Tomislav Šebrek, Jan Tomljanović, Josip Krapac, Mile Šikić
In this paper, we propose a semi-supervised deep learning method for detecting the specific types of reads that impede the de novo genome assembly process.