In this paper we describe a natural language generation system which produces complex sentences from a biology knowledge base. The NLG system allows domain experts to discover errors in the knowledge base and generates certain parts of answers in response to users' questions in an e-textbook application. The system allows domain experts to customise its lexical resources and to set parameters which influence syntactic constructions in generated sentences. The system is capable of dealing with

more »

... rtain types of incomplete inputs arising from a knowledge base which is constantly edited and includes a referring expression generation module which keeps track of discourse history. Our referring expression module is available for download as the open source Antfarm tool 1 .