COGENT COntrolled GENeration of Text (August 2003 - April 2007)
Project Partners University of Brighton, University of Sussex
Project team
Brighton
 Sussex
Funding EPSRC grants GR/S24480/01 (Brighton) and GR/S24497/01 (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.
Publications

A. Belz and R. Dale. 2006. Introduction to the INLG'06 special session on sharing data and comparative evaluation. In Proceedings of International Conference on Natural Language Generation.

A. Belz and A. Kilgarriff. 2006. Shared-task evaluations in HLT: Lessons for NLG. In Proceedings of International Conference on Natural Language Generation.

A. Belz and E. Reiter. 2006. Comparing automatic and human evaluation of NLG systems. In Proceedings of the European Chapter of the Association of Computational Linguistics, pages 313-320.

A. Belz and S. Varges. 2005. Workshop on using corpora for natural language generation. In Proceedings of Corpus Linguistics Conference.

A. Belz. 2004a. Context-free representational underspecification for NLG. Technical Report ITRI-04-08, Information Technology Research Institute, University of Brighton.

A. Belz. 2004b. Towards a general framework for underspecification in NLG and an underspecification language for MRS. Technical Report ITRI-04-17, Information Technology Research Institute, University of Brighton.

A. Belz. 2004c. Underspecification for NLG. In Extended Abstracts of Posters, Third International Conference on Natural Language Generation, pages 9-13.

A. Belz. 2005a. Corpus-driven generation of weather forecasts. In Proceedings of Corpus Linguistics Conference.

A. Belz. 2005b. Statistical generation: Three methods compared and evaluated. In Proceedings of European Natural Language Generation Workshop.

A. Belz. 2006a. High-quality probabilistic generation of language. Technical Report NLTG-06-02, Natural Language Technology Group, CMIS, University of Brighton.

A. Belz. 2006b. Probabilistic generation using representational underspecification. Technical Report NLTG-06-01, Natural Language Technology Group, CMIS, University of Brighton.

A. Belz. 2007. Probabilistic generation of weather forecast texts. In Proceedings of the North American Chapter of the Association of Computational Linguistics.

J. Carroll and S. Oepen. 2005. High efficiency realization for a wide-coverage unification grammar. In Proceedings of the Second International Joint Conference on Natural Language Processing, pages 165-176.

R. Evans, K. van Deemter, A. Belz, J. Teeple, D. Weir, J. Carroll, D. Paiva, and E. Ferrer. 2004. Controlling wide-coverage generation: The cogent project. In Extended Abstracts of Posters, International Conference on Natural Language Generation, pages 16-19.

R. Evans, D. Weir, J. Carroll, D. Paiva, and A. Belz. 2007. Modelling control in generation. In Proceedings of the European Natural Language Generation Workshop.

D. Paiva and R. Evans. 2005. Empirically-based control of natural language generation. In Proceedings of the Association of Computational Linguistics, pages 58-65.

E. Reiter and A. Belz. 2006. GENEVAL: A proposal for shared-task evaluation in NLG. In Proceedings of the International Conference on Natural Language Generation.

K. van Deemter. 2004. Towards a probablistic version of bidirectional OT syntax and semantics. Journal of Semantics, 21(3):251-281.

Maintained by Roger Evans
Last Modified: April 30 2007

© Natural Language Technology Group at the University of Brighton