Search Results for author: Marlene Lutz

Found 2 papers, 1 papers with code

SensePOLAR: Word sense aware interpretability for pre-trained contextual word embeddings

1 code implementation11 Jan 2023 Jan Engler, Sandipan Sikdar, Marlene Lutz, Markus Strohmaier

To address this limitation, we present SensePOLAR, an extension of the original POLAR framework that enables word-sense aware interpretability for pre-trained contextual word embeddings.

Word Embeddings

Properties of Group Fairness Metrics for Rankings

no code implementations29 Dec 2022 Tobias Schumacher, Marlene Lutz, Sandipan Sikdar, Markus Strohmaier

By virtue of their diverse application contexts, we argue that such a comparative analysis is not straightforward.

Fairness

Cannot find the paper you are looking for? You can Submit a new open access paper.