arXiv subjects

Ehud Reiter

Publications and source records attributed to Ehud Reiter.

44 records · Page 3Linked to original sources

arXiv1997

Tailored Patient Information: Some Issues and Questions

Tailored patient information (TPI) systems are computer programs which produce personalised heath-information material for patients. TPI systems are of growing interest to the natural-language generation (NLG) community; many TPI systems have also been developed in the medical community, usually with mail-merge technology. No matter what technology is used, experience shows that it is not easy to field a TPI system, even if it is shown to be effective in clinical trials. In this paper we discuss some of the difficulties in fielding TPI systems. This is based on our experiences with 2 TPI systems, one for generating asthma-information booklets and one for generating smoking-cessation letters.

cmp-lg↗

arXiv1997

Knowledge Acquisition for Content Selection

An important part of building a natural-language generation (NLG) system is knowledge acquisition, that is deciding on the specific schemas, plans, grammar rules, and so forth that should be used in the NLG system. We discuss some experiments we have performed with KA for content-selection rules, in the context of building an NLG system which generates health-related material. These experiments suggest that it is useful to supplement corpus analysis with KA techniques developed for building expert systems, such as structured group discussions and think-aloud protocols. They also raise the point that KA issues may influence architectural design issues, in particular the decision on whether a planning approach is used for content selection. We suspect that in some cases, KA may be easier if other constructive expert-system techniques (such as production rules, or case-based reasoning) are used to determine the content of a generated text.

cmp-lg↗

arXiv1996

Building Natural-Language Generation Systems

This is a very short paper that briefly discusses some of the tasks that NLG systems perform. It is of no research interest, but I have occasionally found it useful as a way of introducing NLG to potential project collaborators who know nothing about the field.

cmp-lg↗

arXiv1996

The Role of the Gricean Maxims in the Generation of Referring Expressions

Grice's maxims of conversation [Grice 1975] are framed as directives to be followed by a speaker of the language. This paper argues that, when considered from the point of view of natural language generation, such a characterisation is rather misleading, and that the desired behaviour falls out quite naturally if we view language generation as a goal-oriented process. We argue this position with particular regard to the generation of referring expressions.

cmp-lg↗

arXiv1995

Computational Interpretations of the Gricean Maxims in the Generation of Referring Expressions

We examine the problem of generating definite noun phrases that are appropriate referring expressions; i.e, noun phrases that (1) successfully identify the intended referent to the hearer whilst (2) not conveying to her any false conversational implicatures (Grice, 1975). We review several possible computational interpretations of the conversational implicature maxims, with different computational costs, and argue that the simplest may be the best, because it seems to be closest to what human speakers do. We describe our recommended algorithm in detail, along with a specification of the resources a host system must provide in order to make use of the algorithm, and an implementation used in the natural language generation component of the IDAS system. This paper will appear in the the April--June 1995 issue of Cognitive Science, and is made available on cmp-lg with the permission of Ablex, the publishers of that journal.

cmp-lg↗

arXiv1995

NLG vs. Templates

One of the most important questions in applied NLG is what benefits (or `value-added', in business-speak) NLG technology offers over template-based approaches. Despite the importance of this question to the applied NLG community, however, it has not been discussed much in the research NLG community, which I think is a pity. In this paper, I try to summarize the issues involved and recap current thinking on this topic. My goal is not to answer this question (I don't think we know enough to be able to do so), but rather to increase the visibility of this issue in the research community, in the hope of getting some input and ideas on this very important question. I conclude with a list of specific research areas I would like to see more work in, because I think they would increase the `value-added' of NLG over templates.

cmp-lg↗

arXiv1994

Automatic Generation of Technical Documentation

Natural-language generation (NLG) techniques can be used to automatically produce technical documentation from a domain knowledge base and linguistic and contextual models. We discuss this application of NLG technology from both a technical and a usefulness (costs and benefits) perspective. This discussion is based largely on our experiences with the IDAS documentation-generation project, and the reactions various interested people from industry have had to IDAS. We hope that this summary of our experiences with IDAS and the lessons we have learned from it will be beneficial for other researchers who wish to build technical-documentation generation systems.

cmp-lg↗

arXiv1994

Has a Consensus NL Generation Architecture Appeared, and is it Psycholinguistically Plausible?

I survey some recent applications-oriented NL generation systems, and claim that despite very different theoretical backgrounds, these systems have a remarkably similar architecture in terms of the modules they divide the generation process into, the computations these modules perform, and the way the modules interact with each other. I also compare this `consensus architecture' among applied NLG systems with psycholinguistic knowledge about how humans speak, and argue that at least some aspects of the consensus architecture seem to be in agreement with what is known about human language production, despite the fact that psycholinguistic plausibility was not in general a goal of the developers of the surveyed systems.

cmp-lg↗