Tutorials at ALTA 2012

We are pleased to announce that ALTA2012 will include pre-workshop tutorials on 4 December 2012. Schedules for these tutorials are available in the programme.

Biomedical Natural Language Processing

David Martinez (NICTA), Hanna Suominen (NICTA), and Karin Verspoor (NICTA)

We will present a full-day combination tutorial and workshop in order to introduce participants to the topics and issues of Biomedical Natural Language Processing (BiomedNLP). We will address NLP of both the biomedical literature and health texts such as medical records, nursing notes, and radiology reports. In the morning, we will provide a tutorial exploring language processing issues and tasks in the biomedical domain, including an overview of existing resources and tools for BiomedNLP, shared tasks for which data is available, and initiatives towards systematic R&D platforms which combine these data, resources, and tools. In the afternoon, we will present several talks on more specific application research that is currently underway in Australia, including for clinical handovers, biosurveillance, evidence-based medicine, and using text mining in molecular biology research. Participants will finish the day with a good appreciation for the range of issues in BiomedNLP, the language processing challenges the domain poses, the importance of the application area, and a toolkit for engaging in BiomedNLP.

A Crash Course in Statistical Natural Language Processing

James Curran (School of Information Technologies, University of Sydney)

In this course, we'll crash headlong into some of the major breakthroughs in natural language processing over the past 30 years that have been enabled by statistical models and machine learning methods. We'll talk about the tasks we've (tried to) solve across syntax and semantics; the methodology, algorithms and data we use to solve them; and some of the challenges for future researchers.