Current research in natural language generation is situated in a computational linguistics
tradition that was founded several decades ago. We critically analyse some of the …

While differences in starting points, grammatical formalisms, and control structures make it
intrinsically difficult to compare alternative designs for natural language generation systems …

In natural language generation, a meaning representation of some kind is successively
transformed into a sentence or a text. Naturally, a central subtask of this problem is the …

Research into natural language generation has often divided the processing into separate
text planning and linguistic realization components. Despite this division's intuitive …

This book aims to inform researchers with an interest in natural language generation about
advances in the field. It is organised around four topics–system architectures, content …

The chapters of this book are edited versions of all 29 papers presented at the Third
International Workshop on Natural Language Generation, which took place in Nijmegen …

Natural language generation (NLG) systems generate texts in English and other human
languages. Although they are based on many of the same linguistic and algorithmic insights …

There are two sides to natural language processing. On the one hand, work in natural
language understanding is concerned with the mapping from some surface representation …

Systems that generate text from non-linguistic knowledge representations make use of a
wide range of theories and representations, borrowed from a variety of disciplines. And …

Almost all current natural language generation (NLG) systems, as contrasted with current NL
understanding (NLU) systems, have one somewhat surprising property in common: Most …