The area of study called natural language generation (NLG) investigates how computer programs can be made to produce high-quality natural language text or speech from computer-internal representations of information. Motivations for this study range from highly theoretical attempts to understand how people produce text and speech (linguistic, psycholinguistic) to entirely practical efforts to produce natural language output for a wide range of applications, including automatic explanation from advisory systems, automatic summarisation from single or multiple documents, machine translation, dialogue systems, tutorial systems, and many more.
This course will provide:
This course assumes that students have taken Introduction to Computational Linguistics and have prior progrramming experience.
Ehud Reiter and Robert Dale (2000) Building Natural Language Generation Systems, Cambridge University Press, 2000.
This course will consist of lectures, student presentations and discussions.
Students will be assessed on performance on:
Note: After introductory lectures by the lecturer, there will be student presentations and student-led discussions. The papers listed here are suggestions for each category, and which we read will depend on student interest. We will read many, but not all of the papers listed here.The problem of natural language generation is typically viewed as a three-stage process:
The following web pages may prove useful during the course.
Informatics Forum, 10 Crichton Street, Edinburgh, EH8 9AB, Scotland, UK
Tel: +44 131 651 5661, Fax: +44 131 651 1426, E-mail: email@example.com
Please contact our webadmin with any comments or corrections. Logging and Cookies
Unless explicitly stated otherwise, all material is copyright © The University of Edinburgh