Refining instructional text generation after evaluation

Abstract

In this paper, we describe how user-adapted explanations about drug prescriptions can be generated from already existing data sources. We start by illustrating the two-step approach employed in the first version of the natural language generator and the limitations of generated texts, that we discovered through analytical and empirical evaluations. We claim that, although style refinement would be needed in these texts, particular care should be devoted to implementing some of the persuasion techniques that doctors employ in their explanations. This would require either thoroughly revising the text planning techniques employed or converting to a multistep generation architecture. We justify why we selected this second alternative and propose some heuristics to repair problems found in the first version of the generator. Some final considerations about the advantages of this approach and the possibility of generalizing it to other domains conclude the paper.

Playing with RST: Two Algorithms for the Automated Manipulation of Discourse Trees

“…This paper described two of these text modification problems, and introduced two algorithms to solve them. The algorithms' results have been evaluated, and they were applied to two typical cases: re-structuring of one-shot documents [1] and generation of dynamic hypermedia. The two applications showed that these algorithms can be successfully used in practical contexts.…”

Untitled

“…* The observation that conveying appropriate information to patients reduces the overall cost of health care has created a demand for health documents tailored to patients' needs and abilities. Several researchers developed systems that generate medical advice (Carenini et al, 1994;Binsted et al, 1995;Hirst et al, 1997;de Rosis et al, 1999). ** Carenini et al (1994) developed a system that advised patients about migraines and their treatment.…”

“…Two systems that generate health advice also consulted multi-dimensional user models (Hirst et al, 1997;de Rosis et al, 1999). Hirst et al (1997) developed an authoring tool for use by technical writers, which produced a £uent rendering of the information selected by these writers.…”

“…de Rosis et al's system, which generated explanations about drug prescriptions, maintained two user models, direct and indirect (de Rosis et al, 1999). The direct user model represented doctors, who interacted with the system and had the`¢nal word' regarding which information was presented.…”

From Greta's mind to her face: modelling the dynamics of affective states in a conversational embodied agent

“…Finally, the 'affective' aspects of communication are expressed in more or less overt form (Hovy, 1988;Walker et al, 1997;de Rosis et al, 1999;de Rosis and Grasso, 2000). We include in affective aspects of communication not only 'basic' emotions and mood, but also those aspects of the mind that are often considered as 'extrarational' in the artificial intelligence community: for instance, 'doubt' 'cognitive overload' and 'deception' (Carberry and Schroeder, 2001;Berthold and Jameson, 1999) .…”