The NLP group at the Open University comprises 20 researchers located within the Centre for Research in Computing. The group has expanded during 2005 and will expand further in 2006 as new staff and students are recruited.

Within a wide variety of research areas, there is a strong central focus on documents (text and diagrams) and their relationship to data, and also on applications with an important social impact (e.g., projects in the medical domain and in e-learning and assessment).

The main areas are as follows.

• Ontologies and Semantic Web
Recent methods of corpus analysis are applied to electronic documents, with the aim of building ontologies or deriving metadata.
• Natural Language Generation
  High-quality texts in different languages and styles are generated automatically from data. The texts serve either as documents, or as interactive presentations in graphical user interfaces.
• Extracting information from text
  Analysis and data mining on corpora of electronic documents, applied to a range of phenomena, including recognising synonyms, profiling documents, assessing student assignments and retrieving information from a cognitively-inspired perspective.
• Diagrams
  Schematic diagrams such as entity-relationship graphs have formation and interpretation rules analogous to syntax and semantics for natural languages.
• Discourse and human cognition
  Here the emphasis is not on the relationship between text and data, but on how texts and electronic media are interpreted by people.

This Theme's Projects

Designing adaptive infOrmation exTraction from text for KnOwledge Management.

Diagrams in Electronic Assessment Project

European Learning Grid Infrastructure based on GRID technololgies

HALO

Natural Language Generation

Network for Euro-Mediterranean LAnguage Resources

Semantic Mining

Towards a Unified Algorithm for the Generation of Referring Expressions