We present a multi-agent framework for generating natural languages, motivated by
grammar systems from formal language theory. The model gives a unified approach to …

Developing artificial learning systems that can understand and generate natural language
has been one of the long-standing goals of artificial intelligence. Recent decades have …

In natural language generation, different generation tasks often interact with each other in a
complex way. We think that how to resolve the complex interactions inside and between …

In this paper we present a means of compensating for the semantic deficits of linguistically
naive underlying application programs without compromising principled grammatical …

Although there can only be a single author of a thesis, it is never truly the work of a single
person. For one, ideas don't belong to one person, they are born and shaped in discussion …

In natural language generation the grammatical component has to be systematically
interfaced to the other components of the system, for example, the planning component …

Traditionally, semantic information in computational lexicons is limited to notions such as
selectional restrictions or domain-specific constraints, encoded in a “static” representation …

We present the RAGS (Reference Architecture for Generation Systems) framework: a
specification of an abstract Natural Language Generation (NLG) system architecture to …

We report here on a significant new set of capabilities that we have incorporated into our
language generation system MUMBLE. Their impact will be to greatly simplify the work of …

Natural language generation (NLG) is a subfield of natural language processing (NLP) that
is often characterized as the study of automatically converting non-linguistic representations …