Probing the representations of named entities in Transformer-based Language Models @ BlackboxNLP 2022
On December 8th I will be presenting my poster of the following work. This work is a collaboration with my supervisors Peter Bloem and Piek Vossen.
About me
I'm a PhD candidate at the Vrije Universiteit Amsterdam (CLTL), supervised by Piek Vossen and Peter Bloem.
One of my main interests is the integration of knowledge and machine learning. Particularly topics such as: incorporating semantics in knowledge graph embeddings; the use of deep learned models for ontology population; or direct integration of reasoning in neural networks (Neurosymbolic AI). I am also interested in the creation of more eXplainable AI. Particularly where this also involves the topics above. Solutions that involve the use of probabilistic deep learning are especially exciting to me.
I obtained a BSc in Computer Science from Utrecht University, and a MSc in Artificial Intelligence from the University of Amsterdam.
Recent Posts
Project AI: Do Feature-Additive Explanation Methods Agree?
Report written for the ‘Project AI’ course Michael Neely and I did on eXplainable AI. This course was done during our time in the MSc AI program at the Unive...
Plotting on the Simplex - Visualizing (rank) correlations and losses.
[Mirror of post on Medium.] For the past year or so I have been involved in a project systematically comparing feature-additive eXplainable AI (XAI) methods...