Challenges of Unstructured Information Management

Abstract:

The bulk of online business information is unstructured -- mainly text. The work on unstructured information in IBM is focussed on ways of making large volumes of textual information more useful, both by helping people to deal with it, and by treating it as a source of information that can be analyzed by IT. In this talk, I will review some of the trends in this area, and illustrate them with work underway in IBM's Research Division. Among the topics I will discuss are new approaches to document classification and taxonomy building, question answering, applications of text analytics, and prospects for semantic annotation and search. Underlying technologies include shallow parsing, vector space models, and ontologies. I will conclude with a brief review of other focus areas in IBM's worldwide research labs.

About the speaker:

Alan Marwick manages the Knowledge Management Technology department of the IBM Thomas J. Watson Research Center in Yorktown, New York. The department develops new technologies and applications in natural language processing, information retrieval, text analysis, and text mining. These technologies are helpful in connecting people to information and to other people who can help with some task.

Alan received a D.Phil. in Physics from the University of Sussex in Britain, and joined the IBM Research Division in 1985. His former research was on applications of nuclear methods in materials science. Since 1992 he has worked on a number of projects related to the dissemination and use of online information. His current interests include technology transfer in industrial R&D, and the development of technologies useful for unstructured information management and knowledge management.

Parking: Visitors requiring a parking pass are asked to contact us at least one working day before the seminar.

Enquiries: sals@ics.mq.edu.au