I am a DECRA Research Fellow at The University of Sydney. My focus is in computational linguistics, in particular systems for automatically extracting, aggregating and summarizing information from massive text data. I am currently working on techniques to streamline enterprise identity management. This includes bootstrapped linking from flat entity authorities, wide-scope fact extraction using distant supervision, and fact-driven text generation.
I maintain cloes ties to the Thomson Reuters R&D Lab in Minnesota. As a Senior Research Scientist there from 2011-2013, I led several exciting projects with professional content, including extended entity recognition for legal documents, keyword taxonomy extraction for risk mining, crowdsourced linguistic annotation, authority-driven company linking for news, and exploiting historical/web text for authority integration.
Previously, I developed approaches to named entity linking, natural language processing with social/collaborative media, and web-scale information extraction as part of the Computable News project. This was part of the financial text analytics programme at the Capital Markets Cooperative Research Centre. I was affiliated with Macquarie University's Centre for Language Technology and the University of Sydney's Schwa Lab.
My PhD (2008) is from the University of Edinburgh, where I also worked as a Research Associate from 2002-2004.
Room 453, Building J12
School of Information Technologies
University of Sydney