ALTA is pleased to announce that two presenters have offered to deliver a tutorial session on the afternoon of the 4th of December.
CSIRO | Data61
CSIRO | Data61
NLP for Healthcare in the Absence of a Healthcare Dataset
Epidemic intelligence deals with the detection of outbreaks using formal (such as hospital records) and informal (such as user-generated text on the web) sources of information. However, official records may not always be available for healthcare research. In this tutorial, we discuss approaches for epidemic intelligence that use unofficial and open datasets. We view past work in terms of two broad categories: health mention classification (selecting relevant text from a large volume) and health event detection (predicting epidemic events from a collection of relevant text). The focus of our discussion is the underlying computational linguistic techniques in the two categories. We also discuss the state-of-the-art in annotation techniques, resources and evaluation strategies when applying NLP for healthcare.
Sarvnaz is a senior researcher at CSIRO’s Data61 in Sydney, with expertise in Information Retrieval, Natural Language Processing (NLP), and Machine Learning. She has over 10 years of experience of research in biomedical NLP. She has led a number of different projects, such as Adverse Drug Reaction Discovery from patient reports (information extraction from social media), and Medical decision support within precision health future science platform. Before CSIRO, Sarvnaz was a researcher at NICTA (2008-2012) working on search and information retrieval in the medical domain (BioTALA project).
Aditya Joshi is a Postdoctoral Fellow at CSIRO's Data61 in Sydney. He was awarded a joint PhD degree by Indian Institute of Technology Bombay, India and Monash University, Australia, in 2018. His research interests are sentiment analysis and health informatics. He currently works on early detection of epidemics using social media streams: a work that combines natural language processing with statistical time series monitoring. Based on his PhD thesis on computational sarcasm, Aditya presented a tutorial on ‘Computational Sarcasm’ at EMNLP 2017, and a TEDx talk titled ‘Detecting sarcasm, combating hate’ that interleaved his PhD research with his experiences as an out LGBTQ student in an Indian university.