TEXT MINING FOR EVIDENCE BASED MEDICINE
Speaker: Diego Molla-Aliod (Macquarie University) Seminar Date: Tuesday March 14 12:00pm Brief abstract: In this talk I will present research we carried out on text mining for Evidence Based Medicine. I will focus on a summarisation framework to help medical doctors and researchers extract medical evidence from literature. Given a clinical question and a list of relevant documents, we use clustering methods to group the medical articles into the key components of the answer (e.g. possible treatments to a condition). We use statistical classifiers to appraise the quality of the evidence found in each cluster. And we have developed text summarisation systems that condense the specific contribution of each article. We are currently developing a proof-of-concept system that would eventually integrate all of this research into an end-to-end system. Short Bio: Dr. Diego Molla-Aliod is a senior lecturer at Macquarie University. His research focuses on text mining, with special emphasis on question answering, information extraction and text summarisation. He has developed question answering systems for technical documents, an open-domain question-answering system, and currently he is focusing on summarisation of medical texts to help the doctor find medical evidence. He is a founding member of the Australasian Language Technology Association (ALTA) and the Australasian Computational and Linguistics Olympiad (OzCLO).