The 'News Engine Web Services' (NEWS) project platform comprises a classification and ontology-based annotation system which allows computers to 'read' web news content across many languages and analyse the content, coming up with a set of results which best matches a user's needs.
The unknowing user may suspect that this is what a computer does now when we do an online search. However, a computer cannot accomplish the same tasks without our intervention because web pages are designed to be read by people, not machines. Semantic Web technologies aim to change all that by making web pages understandable by computers, so that they can search websites and perform actions in a standardised way.
The semantic web-based annotation system developed by the NEWS project allow news agencies to better classify information, resulting in more personalised online news delivery.
"News classifications up to now typically consisted of about 12 terms, like sport, world news, finance, that a journalist knew off by heart," says Dr Ansgar Bernardi, deputy head of the Knowledge Management Group at DFKI, the German Research Centre for Artificial Intelligence, and coordinator of the NEWS project.
"That's not very precise. Our system can automatically analyse a story and access 1,300 classification terms to define it," says Dr Bernardi.
A feature of the new classification and annotation system is its ability to distinguish between people or places with the same name to avoid 'false positives'. This is achieved using an adaptive algorithm called 'IdentityRank'. "It really started out as a by-product of our main work, but it works well and I think it may generate quite a bit of scientific interest," says Dr Bernardi.
By combining their system with an existing commercial voice recognition programme, the project partners also developed a 'proof-of-concept' to analyse audio news files.
The projects' system has attracted some interest from news agencies and plans are afoot for commercialisation.
For further information, please visit:
Copyright Â©European Communities, 2006
Neither the Office for Official Publications of the European Communities, nor any person acting on its behalf, is responsible for the use, which might be made of the attached information. The attached information is drawn from the Community R&D Information Service (CORDIS). The CORDIS services are carried on the CORDIS Host in Luxembourg â http://cordis.europa.eu.int. Access to CORDIS is currently available free-of-charge.