"As for why I tell a lot of stories, there's a joke about that. There was once a man who had a computer, and he asked it, 'Do you compute that you will ever be able to think like a human being?' And after assorted grindings and beepings, a slip of paper came out of the computer that said, 'That reminds me of a story . . . "
– from ANGELS FEAR: TOWARDS AN EPISTEMOLOGY OF THE SACRED. Gregory Bateson & Mary Catherine Bateson. (Part III 'Metalogue').
This paper surveys the current state of the art in Natural Language Generation (NLG), defined as the task of generating text or speech from non-linguistic input. A survey of NLG is timely in view of the changes that the field has undergone over the past two decades, especially in relation to new (usually data-driven) methods, as well as new applications of NLG technology.
Using revision to produce extended natural language text through a series of drafts provides three significant advantages over a traditional natural language generation system. First, it reduces complexity through task decomposition. Second, it promotes text polishing techniques that benefit from the ability to examine generated text in the context of the underlying knowledge from which it was generated. Third, it provides a mechanism for the interaction of conceptual and stylistic decisions. Kalos is a natural language generation system that produces advanced draft quality text for a microprocessor users' guide from a knowledge base describing the microprocessor. It uses revision iteratively to polish its initial generation.
The problem of programming computers to produce natural language explanations and other texts on demand is an active research area in artificial intelligence. In the past, research systems designed for this purpose have been limited by the weakness of their linguistic bases, especially their grammars, and their techniques often cannot be transferred to new knowledge domains. A new text generation system, Penman, is designed to overcome these problems and produce fluent multiparagraph text in English in response to a goal presented to the system. Penman consists of four major modules: a knowledae acauisition module which can perform domain-specific searches for knowledge relevant to a given communication goal; a text planninq module which can organize the relevant information, decide what portion to present.