Our approach is not the traditional Semantic Web approach with coded or semi-automatically extracted metadata, but rather an engine that can build on content through automatic analysis of free text. Linguistic processing will be inside the search engine and a probabilistic document model will provide a principled evaluation of relevance to complement existing standard authority scores. This will facilitate semantic retrieval and incorporate pre-existing domain ontologies using facilities for import and maintenance.

The distributed design will be based on exposing search objects as resources, and on using implicit and automatically generated semantics (not ontologies) to distribute queries and merge results. Because semantic expressivity and interoperability are competing goals, developing a system that is both distributed and semantic-based is the key challenge: research will involve both the statistical and linguistic format of semantic internals, and determining the extent to which the semantic internals are exposed at the interface. The consortium assembles a team of leading international researchers from the areas of peer-to-peer computing (P2P), information extraction and search, and probabilistic modeling together with some of Europe's leading SMEs.

(i) reducing costs for content production and management by applying Artificial Intelligence techniques to content creation, representation (format) and workflow;