This paper addresses the question of whether Reiter's `Consensus NL Generation Architecture' Rei94] really exists, and if so whether it is a suitable candidate for a `reference architecture' for NLG systems. Our answer to the rst question is a tentative yes, but we are less comfortable to accept the second. In pursuit of a better understanding, we develop… (More)
In this paper we present a new approach to controlling the behaviour of a natural language generation system by correlating internal decisions taken during free generation of a wide range of texts with the surface stylistic characteristics of the resulting outputs, and using the correlation to control the generator. This contrasts with the generate-and-test… (More)
We present the rags (Reference Architecture for Generation Systems) framework: a specification of an abstract Natural Language Generation (NLG) system architecture to support sharing, re-use, comparison and evaluation of NLG technologies. We argue that the evidence from a survey of actual NLG systems calls for a different emphasis in a reference proposal… (More)
The RAGS proposals for generic specification of NLG systems includes a detailed account of data representation, but only an outline view of processing aspects. In this paper we introduce a modular processing architecture with a concrete implementation which aims to meet the RAGS goals of transparency and reusability. We illustrate the model with the RICHES… (More)
We present the rags (Reference Architecture for Generation Systems) framework, a specification of an abstract Natural Language Generation (NLG) system architecture to support sharing, re-use, comparison and evaluation of NLG technologies. We argue that the evidence from a survey of actual NLG systems calls for a different emphasis in a reference proposal… (More)
The RAGS project aims to develop a reference architecture for natural language generation, to facilitate modular development of NLG systams as well as evaluation of components, systems and algorithms. This paper gives an overview of the proposed framework, describing an abstract data model with five levels of representation: Conceptual, Semantic,… (More)
This paper introduces an approach to representing the kinds of information that components in a natural language generation (NLG) system will need to communicate to one another. This information may be partial, may involve more than one level of analysis and may need to include information about the history of a derivation. We present a general… (More)
In this paper we present an analysis of stylistic variation that uses a factor analytic technique to group the variables responsible for the bulk of the linguistic variation found in a corpus of pharmaceutical leaflets. Two main factors of variation were found and analysed in more detail; they also were compared with other two analyses.