Empirically-based control of natural language generation

Paiva, D.S. and Evans, R. (2005) Empirically-based control of natural language generation In: Proceedings of the 43rd Annual Meeting of the ACL, June 2005, Ann Arbor, USA.

Restricted to Registered users only


Official URL: http://acl.ldc.upenn.edu/P/P05/P05-1008.pdf


In this paper we present a new approach to controlling the behaviour of a natural language generation system by correlating internal decisions taken during free generation of a wide range of texts with the surface stylistic characteristics of the resulting outputs, and using the correlation to control the generator. This contrasts with the generate-and-test architecture adopted by most previous empirically-based generation approaches, offering a more efficient, generic and holistic method of generator control. We illustrate the approach by describing a system in which stylistic variation (in the sense of Biber (1988)) can be effectively controlled during the generation of short medical information texts.

Item Type:Contribution to conference proceedings in the public domain ( Full Paper)
Additional Information:Deposit=postprint
Uncontrolled Keywords:Natural language generation
Subjects:G000 Computing and Mathematical Sciences
Faculties:Faculty of Science and Engineering > School of Computing, Engineering and Mathematics > Natural Language Technology
ID Code:2831
Deposited By:Helen Webb
Deposited On:13 Nov 2007
Last Modified:15 Jun 2012 13:16

Repository Staff Only: item control page