PDF version of this document
Given all the data that is contained in our E-mail box(es), our files (photos, documents and sounds to name a few), would inference not be one natural direction to follow? Extracting the semantics from our data and forming a network of knowledge will enable us to search for answers rather than arbitrary pages that approximately resemble our query text. Taking personal search (limited scope due to privacy) as an instance, the implications can be particularly revolutionary. Having got large lumps of data, we should be able to perform a query, using natural language, to receive plenty of information about a person (or place) including relationships, photos, etc. See the short discussion on privacy controversies in §B.