Hi! I’m a PhD student at the University of Edinburgh in the Centre for Doctoral Training in Natural Language Processing. My supervisors are Ivan Titov (primary) and Alexander Koller (secondary).

I work on compositional generalisation in semantic parsing but I’m interested more generally in structured prediction, latent variable models in NLP and in introducing (structural) inductive biases into deep learning models.

Before I came to Edinburgh, I got my Bachelor’s and Master’s in computational linguistics from Saarland University, where I worked on semantic graph parsing with amazing people like Jonas Groschwitz, Meaghan Fowlie, Lucia Donatelli, Pia Weißenhorn and Alexander Koller.

News

• Talk on Structural Inductive Biases for Seq2Seq Models at the CL Seminar at the University of Amsterdam.
• New preprint Injecting a Structural Inductive Bias into a Seq2Seq Model by Simulation.
• Got an Outstanding Paper Award at ACL 2023 for Compositional Generalization without Trees using Multiset Tagging and Latent Permutations 🏅
• Compositional Generalisation with Structured Reordering and Fertility Layers has been accepted to EACL 2023.