Reasoning about Ambiguous Definite Descriptions in EMNLP 2023 Findings
Abstract Natural language reasoning plays an increasingly important role in improving language models’ ability to solve complex language understanding tasks....
Cross-Domain Toxic Spans Detection @ NLDB 2023
Abstract Given the dynamic nature of toxic language use, automated methods for detecting toxic spans are likely to encounter distributional shift. To explore...
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.
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...
Order in the Court: Explainable AI Methods Prone to Disagreement
Our paper which was presentation at the ICML Workshop on Theoretic Foundation, Criticism, and Application Trend of Explainable AI.
Sparse attention might be explanation.
Last January I participated in the Fairness, Accountability, Confidentiality, and Transparency course. We were tasked with replicating a recent paper on one...
Care2Report: Automated Medical Reporting
During my bachelor thesis project I worked in a team that developed a prototype for a research program called Care2Report at Utrecht University. The project ...