. Health-education documents can be much more effective in achieving patient compliance if they are customized for individual readers. For this purpose, a medical record can be thought of as an extremely detailed user model of a reader of such a document. The HealthDoc project is developing methods for producing health-information and patienteducation documents that are tailored to the individual personal and medical characteristics of the patients who receive them. Information from an on-line medical record or from a clinician will be used as the primary basis for deciding how best to fit the document to the patient. In this paper, we describe our research on three aspects of the project: the kinds of tailoring that are appropriate for health-education documents; the nature of a tailorable master document, and how it can be created; and the linguistic problems that arise when a tailored instance of the document is to be generated. 1 The Value of Tailored Health-Education Documents He...

We present a new, data-driven approach to text planning, which can be used not only to map full knowledge pools into natural language texts, but also to generate texts that satisfy multiple, high-level communicative goals. The approach explains how global coherence can be achieved by exploiting the local coherence constraints of rhetorical relations. The local constraints were derived from a corpus analysis. Motivation 1 All current flexible approaches to text planning that assume that the abstract structure of text is a tree-like structure are, esentially, top-down approaches. Some of them define plan operators and exploit hierarchical planning techniques (Hovy 1993; Moore and Paris 1993; Moore and Swartout 1991; Cawsey 1991; Maybury 1992) and partial-order planning techniques (Young and Moore 1994). Others assume that plans are hierarchically organized sets of frames that can be derived through a top-down expansion process (Nirenburg et al. 1989; Meteer 1992). And the recursive app...

... document structure can be seen as an extension of Nunberg's `text-grammar'; it is also closely related to `logical' mark-up in languages like HTML and LATEX. We show that by using this intermediate representation, several subtasks in language generation and language understanding can be defined more cleanly.

This report presents a summary of the architectural characteristics of some of the Natural Language Generation (NLG) systems that serve as the main building blocks of the RAGS

Abstract not found

In the pharmaceutical industry, products have to be described by a range of document types with overlapping content. Moreover, much of this documentation has to be produced in many languages. This situation is commonplace in many commercial domains, and leads to well-known problems in maintaining a set of related documents and their translations. We describe a potential solution explored in the PILLS project. All relevant knowledge about a product is entered only once, through a natural-language interface to a knowledge base. From this `master model', specialised models for a range of document types are derived automatically; from each specialised model, documents are generated automatically in all supported languages. As an illustration of this approach, the PILLS demonstrator generates three medical document types in English, German and French.

This paper discusses some issues relating to the task of lexicalisation within applied NLG systems. We restrict ourselves here to the systems covered in "A Survey of Applied Natural Language Systems" [Pai98], that are fully implemented, complete

Aggregation is gaining attention as an important phenomenon in automated natural language generation. The small quantity of previous work which deals with this subject suffers from some conceptual difficulties, including inadequate definition (i.e., as a process which eliminates redundancy), vagueness as to its locus in the generation process, and unclear relation to other phenomena. It is concluded here that aggregation is best seen as an emergent phenomenon which results from careful sentence planning. This view draws attention to the processes of semantic grouping, sentence structuring, and sentence delimitation which together underlie aggregation effects. Within the framework of the HealthDoc project, an attempt to develop systems for automatic patient text customization, the application of the above perspective is considered. 1 Introduction Aggregation is an issue that has recently begun to attract attention in the field of natural language generation (NLG). It is usually describ...

The Patient Education and Activation System (PEAS) project aims to prepare people to take a more active role in their health care decisions. In this paper, we describe our work on the Layman Education and Activation Form (LEAF). LEAF is designed to be an interactive, Internet-based system for collecting a patient's medical history. It is unique in that it gives patients access to educational information when it is most pertinent, while they are attempting to complete a form. It avoids overwhelming the patient, by only providing the information when it is likely to be relevant. The system avoids asking irrelevant questions or providing irrelevant facts by tailoring the content of the form based on the patient's interaction with the system. The system also uses the patient's answers to suggest questions that the patient might ask her doctor and provides online resources that the patient can browse. Keywords: health education, Internet, medical history form 3 3 I. Introduction The PE...

A great part of the product knowledge in manufacturing enterprises is only available in the form of natural language documents. The know-how recorded in these documents is an essential resource for successful competition in the market. From the viewpoint of knowledge management, however, documents have a severe limitation: They do not capture the wealth of knowledge contained in these documents, since the entire knowledge is not spelled out on the linguistic surface. In order to overcome this limitation, the notion of a document as a particular kind of realization of (or view on) the underlying knowledge is introduced. The paper discusses the major steps in realizing this approach to documents: Knowledge acquisition, knowledge representation, and techniques to automatically generate multilingual documents from knowledge bases. Further, the paper describes how the required product knowledge can be represented in a sharable and reusable way.