no code implementations • 24 Nov 2022 • Oskar van der Wal, Dominik Bachmann, Alina Leidinger, Leendert van Maanen, Willem Zuidema, Katrin Schulz
In particular, we will explore two central notions from psychometrics, the construct validity and the reliability of measurement tools, and discuss how they can be applied in the context of measuring model bias.
1 code implementation • NAACL (GeBNLP) 2022 • Oskar van der Wal, Jaap Jumelet, Katrin Schulz, Willem Zuidema
With full access to the data and to the model parameters as they change during every step while training, we can map in detail how the representation of gender develops, what patterns in the dataset drive this, and how the model's internal state relates to the bias in a downstream task (semantic textual similarity).
no code implementations • 25 Nov 2021 • Fausto Barbero, Katrin Schulz, Fernando R. Velázquez-Quesada, Kaibo Xie
Therefore, in a second step, we implement a more complex notion of knowledge that allows an agent to observe (measure) certain variables when an experiment is carried out.
no code implementations • 30 Oct 2020 • Fausto Barbero, Katrin Schulz, Sonja Smets, Fernando R. Velázquez-Quesada, Kaibo Xie
To this purpose, we extend the notion of a causal model with a representation of the epistemic state of an agent.