Natural Language Generation

Abstract

Communication via a natural language requires two fundamental skills: producing ‘text’ (written or spoken) and understanding it. This chapter introduces newcomers to computational approaches to the former—natural language generation (henceforth NLG)—showing some of the theoretical and practical problems that linguists, computer scientists, and psychologists encounter when trying to explain how language production works in machines or in our minds. The chapter first defines and illustrates the abstract components of the NLG task and their distinctive roles in accounting for the coherence and appropriateness of natural texts and then sets out the principal methods that have been developed in the field for building working computational systems. Current problems, new proposals for solutions and potential applications are also briefly characterized.