I am a 3rd (and final) year PhD student in Machine Learning at the School of Informatics, University of Edinburgh, supervised by Tim Hospedales and Ivan Titov. I am a member of the Centre for Doctoral Training in Data Science. Majority of my PhD research is centered around representation learning for knowledge graphs. More broadly, I am interested in 1) understanding how semantics is encoded in the geometry of representations; and 2) learning to better represent objects in the real world, ranging from words to objects in images.
From November 2019 to June 2020, I interned at the Samsung AI Center in Cambridge.
Before starting my PhD, I received a BSc in Computer Science at the Faculty of Electrical Engineering and Computing, University of Zagreb, an MSc in Computer Science at the Technische Universität Berlin and an MSc in Data Science at the University of Edinburgh.
Interpreting Knowledge Graph Relation Representation from Word Embeddings
Carl Allen*, Ivana Balažević*, Timothy Hospedales, ICLR, 2021
What the Vec? Towards Probabilistically Grounded Embeddings
Carl Allen, Ivana Balažević, Timothy Hospedales, NeurIPS, 2019
A Probabilistic Framework for Discriminative and Neuro-Symbolic Semi-Supervised Learning
Carl Allen, Ivana Balažević, Timothy Hospedales, arXiv:2006.05896, 2020
Benchmark and Best Practices for Biomedical Knowledge Graph Embeddings
David Chang, Ivana Balažević, Carl Allen, Daniel Chawla, Cynthia Brandt, Andrew Taylor
ACL BioNLP Workshop, 2020
TuckER: Tensor Factorization for Knowledge Graph Completion
Ivana Balažević, Carl Allen, Timothy Hospedales, ICML AMTL Workshop, 2019
Office: Room 3.50, Informatics Forum, 10 Crichton Street, Edinburgh, EH8 9AB