Medical knowledge is increasing exponentially, and it is the job of the clinician to continually stay abreast of the latest medical findings. Clinicians make use of the most recent diagnostic tools and use these to optimise a treatment plan based on the best medical knowledge available. However, it is unrealistic to expect a clinician to have perfect knowledge of all medical literature. A better approach is to develop NLP solutions that are able to automatically extract clinical guidelines from medical literature, and identify the recommended approaches to preventing or treating a given disease in a specific clinical situation. In this project the key focuses include: (1) abstractive summarisation of medical literature (single- and multi-document, and document- and subdocument-level), based on deep learning; (2) inferring new relations for entities, based on using deep learning to project textual relations and entities into a dense latent representation, extending work that has been done on more general knowledge base population tasks; and (3) hybrid text and image analytics over medical textbooks and full-text articles, integrating text and explanatory figures using deep learning and adversarial training methods.



Professor Karin Verspoor

Deputy Director
ARC Training Centre in Cognitive Computing for Medical Technologies, The University of Melbourne
Karin Verspoor is a Professor in the School of Computing and Information Systems and Deputy Director of the Health and Biomedical Informatics Centre at The University of Melbourne. Trained as a computational linguist, Karin’s research primarily focuses on extracting information from clinical texts and the biomedical literature using machine learning methods to enable biological discovery and clinical decision support. Karin held previous posts as the Scientific Director of Health and Life Sciences at NICTA Victoria Research Laboratory, at the University of Colorado School of Medicine, and Los Alamos National Laboratory. She also spent 5 years in start-ups during the US Tech bubble, where she helped design an early artificial intelligence system.


Dr Chris Butler

Manager of Cognitive Analytics
IBM Research - Australia

Chris Butler is the Manager of Cognitive Analytics at IBM Research – Australia in Melbourne. He is part of IBM Research’s global Financial Service leadership team and has been working with AI technologies, such as natural language processing, across Government, Financial Services sectors. His team is responsible for IBM Research – Australia’s engagements with Watson technologies including a number of projects delivered in conjunction with IBM Watson. Throughout his tenure he has been engaging with clients across a wide variety of industries including Federal Government, Education, Insurance and Banking.

Chris joined IBM first at the IBM Research Collaboratory for Life sciences in November 2010. In May 2011 he joined IBM Research – Australia as a research intern and in 2012 he joined IBM Research as a research scientist full time. Throughout his tenure at IBM Research Chris has worked on a diverse set of projects from numerical modelling of cardiac electrophysiology to the analysis of social media for disaster management.

His PhD on utilising numerical modelling to understand in vitro blood flow experiments and his undergraduate degree (BE(Mech) / BTech (Aero) Hons.) were received from Monash University.