This paper describes the complete process and a tool for the automatic
construction of a multimedia hypertext starting from a large collecti
on of multimedia documents. Through the use of an authoring methodolog
y, the document collection is automatically authored, and the result i
s a multimedia hypertext, also called a hypermedia, written in hyperte
xt markup language (HTML), almost a standard among hypermedia mark-up
languages. The resulting hypermedia can be browsed and queried with Mo
saic, an interface developed in the framework of the World Wide Web Pr
oject. In particular, the set of methods and techniques used for the a
utomatic construction of hypermedia is described in this paper, and th
eir relevance in the context of multimedia information retrieval is hi
ghlighted.