In this paper we address the task of extracting risk events and probabilities from free text, focusing in particular on the biomedical domain. While our initial motivation is to enable the determination of the parameters of a Bayesian belief network, our approach is not specific to that use case. We are the first to investigate this task as a sequence tagging problem where we label spans of text as events A or B that are then used to construct probability statements of the form P(A B) x. We show that our approach significantly outperforms an entity extraction baseline on a new annotated medical risk event corpus. We also explore semi-supervised methods that lead to modest improvement, encouraging further work in this direction.

Have you ever pictured a robot and an art easel in the same room? A new gallery is bringing that to reality by linking artists with machines. The Cueva Gallery – described as the first of its kind in Ireland – is a gallery entirely devoted to artwork made or inspired by artificial intelligence (AI). It was set up by three people with "a passion for art and technology" – Dr Ernesto Diaz-Aviles, Dr Claudia Orellana-Rodriguez and Beth Jochim. We spoke to Jochim – the director of Dublin-based Cueva – about her vision for the gallery and why she and her colleagues – who have experience across machine learning (ML), creative AI, arts and humanities research and innovation – came together to bring this project to life.