Showing papers by "Chris Mellish published in 1993"
Proceedings Article•
01 Jun 1993
TL;DR: GAs provide a way of addressing hard search and optimisation problems in very hilly spaces and are particularly good at nding global optima in veryHilly spaces; for these reasons, the use of GAs on the mesp is investigated.
49 citations
Proceedings Article•
01 Jan 1993
39 citations
28 Apr 1993
TL;DR: In this paper, the authors make an initial assessment of the prospects of commercial applications of NLG in the area of technical documentation, based on experiences in the IDAS natural language generation project and discussions with project partners and other interested parties.
Abstract: This paper makes an initial assessment of the prospects of commercial applications of Natural Language Generation (NLG) in the area of technical documentation. This is very much our own personal view, though based on experiences in the IDAS natural language generation project and discussions with our project partners and other interested parties. We start to address the following kinds of questions:
1.
What has NLG to offer?
2.
Why are there so few real applications at present?
3.
What extra constraints do real applications impose?
4.
How can we compensate for current limitations in NLG?
5.
Where is new NLG work needed?
4 citations
Proceedings Article•
28 Aug 1993TL;DR: This work discusses IDAS'S classification system and how it differs from other such systems (perhaps most notably in the presence of template' constructs that enable recursion to be encoded); gives examples of program fragments encoded in the classification system; and compares the classification approach to other AI programming paradigms.
Abstract: Our experience in the IDAS natural language generation project has shown us that IDAS'S KLONE-like classifier, originally built solely to hold a domain knowledge base, could also be used to perform many of the computations required by a natural-language generation system; in fact it seems possible to use the classifier to encode and execute arbitrary programs. We discuss IDAS'S classification system and how it differs from other such systems (perhaps most notably in the presence of template' constructs that enable recursion to be encoded); give examples of program fragments encoded in the classification system; and compare the classification approach to other AI programming paradigms (e.g., logic programming).
1 citations
Proceedings Article•
28 Apr 1993
TL;DR: This paper makes an initial assessment of the prospects of commercial applications of Natural Language Generation in the area of technical documentation based on experiences in the IDAS natural language generation project and discussions with project partners and other interested parties.
Abstract: This paper makes an initial assessment of the prospects of commercial applications of Natural Language Generation (NLG) in the area of technical documentation. This is very much our own personal view, though based on experiences in the IDAS natural language generation project and discussions with our project partners and other interested parties. We start to address the following kinds of questions:
1.
What has NLG to offer?
2.
Why are there so few real applications at present?
3.
What extra constraints do real applications impose?
4.
How can we compensate for current limitations in NLG?
5.
Where is new NLG work needed?
1 citations