Paper: User-Controlled, Robust Natural Language Generation from an Evolving Knowledge Base

ACL ID W13-2103
Title User-Controlled, Robust Natural Language Generation from an Evolving Knowledge Base
Venue European Workshop on Natural Language Generation
Session
Year 2013
Authors

In this paper we describe a natural lan- guage generation system which produces complex sentences from a biology knowl- edge base. The NLG system allows do- main 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 cus- tomise its lexical resources and to set pa- rameters which influence syntactic con- structions in generated sentences. The system is capable of dealing with certain types of incomplete inputs arising from a knowledge base which is constantly edited and includes a referring expression gen- eration module which keeps track of dis- course history. Our referring expression module is available for download as the open source Antfarm tool1.