Daniel S. Paiva

A Reference Architecture for Natural Language Generation Systems

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 from that seen in similar initiatives in information extraction and multimedia interfaces. We introduce the framework itself, in particular the two-level data model that allows us to support the complex data requirements of NLG systems in a flexible and coherent fashion, and describe our efforts to validate the framework through a range of implementations.

Empirically-based Control of Natural Language Generation

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 architecture adopted by most previous empirically-based generation approaches, offering a more efficient, generic and holistic method of generator control. We illustrate the approach by describing a system in which stylistic variation (in the sense of Biber (1988)) can be effectively controlled during the generation of short medical information texts.

A Reference Architecture for Generation Systems

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 from that seen in similar initiatives in information extraction and multimedia interfaces. We introduce the framework itself, in particular the two-level data model that allows us to support the complex data requirements of NLG systems in a flexible and coherent fashion, and describe our efforts to validate the framework through a range of implementations.

From RAGS to RICHES: Exploiting the Potential of a Flexible Generation Architecture

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 system -- a generation system built from simple linguistically-motivated modules.

A Framework for Stylistically Controlled Generation

In this paper we describe a framework for stylistic control of the generation process. The approach correlates stylistic dimensions obtained from a corpus-based factor analysis with internal generator decisions, and uses the correlation to direct the generator towards particular style settings. We illustrate this approach with a prototype generator of medical information. We compare our framework with previous approaches according to how they define, characterise and specify style and how effective they are at controlling it, arguing that our framework offers a generic, practical, evaluable approach to the problem of stylistic control.

A Representation for Complex and Evolving Data Dependencies in Generation

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 representation scheme capable of handling these cases. In addition, we make a proposal for organising intermodule communication in an NLG system by having a central server for this information. We have validated the approach by a reanalysis of an existing NLG system and through a full implementation of a runnable specification.

Reinterpretation of an Existing NLG System in a Generic Generation Architecture

The RAGS project aims to define a reference architecture for Natural Language Generation (NLG) systems. Currently the major part of this architecture consists of a set of datatype definitions for specifying the input and output formats for modules within NLG systems. In this paper we describe our efforts to reinterpret an existing NLG system in terms of these definitions. The system chosen was the Caption Generation System.

Investigating NLG architectures: taking style into consideration

In this paper we propose a methodology for investigating the relationship between architectures of natural language generation (NLG) systems and stylistic properties of texts. Bibers (1988) methodology is used to obtain both the characterisation of style of our corpus and the division of the corpus into sets of linguistically similar texts. These sets will be used for studying the architectural aspects.