Natural Language Generation (NLG) is concerned with getting computer programs to produce readable text in an ordinary language such as English.
Usually, the program will start from information which is not expressed in language, such as tables of numerical data or a collection of entries in a database; sometimes, the generation process starts from information stated in language and the aim is to re-phrase the text, for example to make it more readable.
Our group has explored a wide range of practical uses of NLG, such as writing brief weather forecasts or summarising medical data, and we are also interested in more theoretical issues, such as the best way to describe an object so that someone can identify it, or how to control a text-generating program in a flexible way.
Recurring themes in our work are:
- the study of real applications with actual human users
- looking at various uses of text, not just the stating of factual information
- considering the kinds of effects that text can have on readers
- investigating theoretical as well as practical issues
The Aberdeen group is probably the largest concentration of NLG researchers in the world, and is very active in the wider international research community.