Overview
Duration
Financial Support
Overview
Although the general problem of Natural Language Generation (NLG) remains far from completely understood, the field is starting to produce systems which achieve successful practical deployment. However, a significant barrier to wider exploitation is the lack of a standard view of the generation process as a whole, within which more specialised research can be embedded and against which whole systems can be compared. This project aimed to provide such a view: a `reference architecture' for natural language generation systems based on an emerging consensus on what such systems should be like. The work aimed to refine this consensus into a more explicit reference architecture specification, identifying principal components and data representations. It has produced example data interfaces and sample implementations of processing modules. Although the resulting architecture may not be a perfect fit for all NLG applications, the intention is that it will be sufficiently general to facilitate sharing of resources and comparative evaluation of different approaches.
RAGS was a joint project between the Information Technology Research Institute at the University of Brighton and the Informatics Division (formerly the Department of Artificial Intelligence) at the University of Edinburgh. However, the success of the project (in terms of the general utility of the final architecture to the range of interests of the NLG community) depended on the involvement of other NLG researchers from other sites. Below is a list of people who agreed to participate as "consultants" on the project, providing us with feedback on the deliverables of the project and data relating to their own work.
In addition to the technical work, we
ran a series of specialist workshops on the topic of NLG architectures
to which members of the NLG community and other interested parties were
invited. We are still in the process of making
our deliverables available at this site.
Duration
March 1998 to April 2001.
Financial
support
This project is funded by the Engineering and Physical Sciences Research Council under grants GR/L77041 to Chris Mellish (Edinburgh) and GR/L77102 to Donia Scott (Brighton).
Contact
You can reach us by email at rags@itri.bton.ac.uk
© Information Technology Research Institute