The NewsTools Project




The NewsTools Project is an umbrella for various funded projects and collaborations. It is aimed at developing tools for analysing and merging news reports that are represented in the form of structured reports. An structured report is a set of semantic labels together with a word, phrase, sentence, null value, or a nested item of structured text, associated with each semantic label. As a simple example, a report on a corporate acquisition could use semantic labels such as "buyer", "seller", "acquisition", "value", and "date". It is assumed that reports may conflict with other reports and they may contain various kinds of uncertainty. We are investigating how inconsistencies can be identified, measured, and resolved. We are also investigating how arguments can be constructed from sets of reports to reflect conflicting perspectives.

The project is being developed using a number of ideas from artificial intelligence and data and knowledge engineering, and in particular, logic-based knowledge representation and reasoning techniques. The techniques being developed allow for a formal specification of the functionality of the tools, and also support a viable approach to managing the necessary domain knowledge required for the tool functionality. The domain knowledge is specialized knowledge about the information in news reports. Given the complexity in acquiring and maintaining this kind of knowledge, it is only possible to capture knowledge on very focussed domains. The coverage of the domain knowledge depends on the application area but includes context-sensitive lexical knowledge (eg. synonymous words and phrases, more general terms, more specialized terms, preferred terms, meronyms, etc) and context-sensitive world knowledge (eg. concept definitions, relationships between concepts, geographic knowledge, knowledge about calendars and time, knowledge about people and organizations, commonsense knowledge, etc).

The theoretical work has benefited from EPSRC, Royal Society, and ESPRIT funding. The work has also benefited from collaborative links with companies including Reuters, Factiva, and TFPL. Two EPSRC awards (320K pounds) are funding the development of prototype tools and evaluative studies. For more information about the NewsTools Project, see the publications listed on Tony Hunter's homepage or contact him at a.hunter@cs.ucl.ac.uk or +44 20 7679 7295.

  • People


  • A simple example of a structured news report


  • Potential application areas for NewsTools technology


  • Sourcing news for NewsTools applications


  • Analysing and acting on inconsistencies in news reports


  • Obtaining and using background domain knowledge