The COGENT Project at ITRI

COGENT COntrolled GENeration of Text
COGENT Team at ITRI Roger Evans, Kees van Deemter and Anja Belz
Duration 2003 - 2006
Funding EPSRC grants GR/S24480/01 (Brighton) and GR/S24497/01 (Sussex)
Project Partners University of Brighton, University of Sussex
Summary Natural Language Generation (NLG) technology has reached a level of maturity where applied systems exist in a range of specialised real-world domains (such as weather bulletins, software documentation, health and legal advice and stock market movements). However, developing such systems currently involves hand-crafting and special-purpose tuning by NLG experts which is non-portable, non-scaleable, time-consuming and expensive. Wider deployment of language generation requires more generally applicable and reusable NLG components based on wide-coverage grammars, but at present, effective techniques for such wide-coverage generation are not well understood. This three year project will investigate systematically the characteristics of wide-coverage generation and to develop reflective techniques for controlling it effectively. As well as furthering our understanding of wide-coverage generation, the project will deliver a substantial and novel resource to support future research in this area, and practical implementations of wide-coverage controllable generators.
Research Opportunities This project has funding for a PhD studentship to start around October 2003. The student will study questions on the border between formal semantics and computational semantics, in particular surrounding the possible ambiguity of generated texts. For example, how might a generator `reflect' on its own output, and thereby manage to avoid unwanted ambiguities? What type of semantic representations are most suitable for controlled generation of text? This studentship would be suitable for people interested in carrying out research into areas such as
  • underspecified semantic representations (e.g., MRS)
  • statistical NLG
  • connections between NLG and formal semantics

For details about studying at ITRI and the application process, see our Postgraduate Study page.

See also The Sussex COGENT project page.

Maintained by Roger Evans
Last Modified: March 27 2003

© Information Technology Research Institute at the University of Brighton