My name is Arthur Bražinskas (pronounced Bra [zh] inskas), I’m a natural language processing Ph.D. researcher working on latent probabilistic models for abstractive opinion summarization. I’m part of the ILCC group at the University of Edinburgh and supervised by Ivan Titov and Mirella Lapata. Specifically, I focus on low-resource settings where annotated datasets are scarce yet large amounts of unannotated data are available. In these settings, the model learns the process of summarization without direct supervision or from a few examples.

I'm interested in Bayesian machine learning approaches that model data in terms of random variables - observable and hidden. These models have solid foundation in information theory and more recently have been fueled by neural networks. For training, my preference is amortized variational inference (i.e., VAE) combined with reinforcement learning.

I graduated (MSc. \w distinction) in artificial intelligence from the University of Amsterdam, Netherlands, where I specialized in theoretical machine learning and natural language processing. Before starting my Ph.D., I worked on machine learning modeling at Elsevier, Amazon, and Zalando.

Few-Shot Learning for Opinion Summarization
Arthur Bražinskas, Mirella Lapata, Ivan Titov In EMNLP 2020
Unsupervised Opinion Summarization as Copycat-Review Generation
Arthur Bražinskas, Mirella Lapata, Ivan Titov In ACL 2020
Embedding Words as Distributions with a Bayesian Skip-gram Model
Arthur Bražinskas, Serhii Havrylov, Ivan Titov In COLING 2018