This paper discusses aspects of multi-medium document bases and how
access to documents held on a computer based system can be achieved.
It discusses current access methods for multi-medium document bases and
in particular hypermedia and probabilistic retrieval systems. It then
goes on to propose a hybrid between these two traditional fields of
information retrieval in an attempt to improves access to information
held on document bases and in particular non-textual information. A user
interface is also proposed which would take advantage of the hybrid model.
Mark Dunlop's Publications