Some Thoughts on Failure Analysis for Noisy Data


John Tait

IRF, Austria

 

I examine the notion of noise and its application to Information Retrieval and urge the community to consider noise as an intrinsic property of information, not merely a problem to be eliminated.

 

About John Tait

John Tait obtained a Ph.D. from the University of Cambridge in 1983 for a thesis entitled “Automatic Summarising of English Text”. He subsequently followed a career in industry, mainly working on problems of large scale information retrieval and management, before taking up a post at the University of Sunderland in 1991, where he eventually became Professor of Intelligent Information Systems and Associate Dean of Computing And Technology, as well as leading the University of Sunderland Information Retrieval Group. In September 2007 he took up the post of Chief Scientific Officer of the Information Retrieval Facility, a not-for-profit foundation dedicated to promoting research in large scale information retrieval.  He has been joint programme committee chairs for two recent relevant workshops: “iNeWS  07 - Improving Non-English Web Searching”  at ACM SIGIR 2007 in Amsterdam; and the ACL/COLING 2006 Workshop “CLIIR: How can Computational Linguistics Improve Information Retrieval” in  Sydney, Australia.  John is a past Programme Committee chair of the ACM SIGIR conference (2005),  past General Chair of the European Conference on Information Retrieval (2004), an Associate Editor of ACM Transaction on Information Systems and has published over 90 refereed conference and journal papers. His current research focuses on problems of retrieving still and moving images and on patent retrieval.