no code implementations • 1 Sep 2023 • Karel Veldkamp, Mariya Hendriksen, Zoltán Szlávik, Alexander Keijser
To gain a better understanding of the reasons contrastive learning was not successful for music videos, we perform a qualitative analysis of the learned representations, revealing why contrastive learning might have difficulties uniting embeddings from two modalities.
no code implementations • 19 Oct 2021 • Edeline Contempré, Zoltán Szlávik, Majid Mohammadi, Erick Velazquez, Annette ten Teije, Ilaria Tiddi
In this paper, a model-agnostic explainable method is developed to provide users with further information regarding the reasons why a clinical trial is retrieved in response to a query.
no code implementations • 29 Jan 2021 • Tim Draws, Zoltán Szlávik, Benjamin Timmermans, Nava Tintarev, Kush R. Varshney, Michael Hind
Systems aiming to aid consumers in their decision-making (e. g., by implementing persuasive techniques) are more likely to be effective when consumers trust them.
Decision Making Fairness Human-Computer Interaction
no code implementations • 11 Nov 2020 • Evgeny Krivosheev, Burcu Sayin, Alessandro Bozzon, Zoltán Szlávik
In this paper, we explore how to efficiently combine crowdsourcing and machine intelligence for the problem of document screening, where we need to screen documents with a set of machine-learning filters.