Hi Tim,
Thanks for a most informative response. I will retrieve these references and study
them carefully. In the mean time, I wonder if it makes any difference whether a "term"
is a single concept or a group of concepts? Please see below.
On Fri, 13 Apr 2001 10:04:33 Tim Benson wrote:
...
>So one solution is to generate many such schemes.
...
>This is not simply a term-to-term translator, because the
>algorithms may need to take account of other factors.
This means scheme A + scheme B --> scheme C,
where scheme A would include "these factors" and scheme B would be "other factors".
It appears to me that the translator's function (-->) is really no different no matter
how many schemes are in the left side of the transform?
In other words, the translator mechanism (==>) where scheme D ==> scheme E is no
different from (-->) where scheme A + scheme B --> scheme C.
Furthermore, it matters not whether each scheme contains only a single concept or
multiple concepts. For example, apple --> fruit can be handled in the same way as
apple, pear, orange ==> fruit.
So, once we build one term-to-term translator, we have a universal translating
mechanism (of course, missing the "rules" for each translation). Is that right?
...
>and those where
>the grouping is done as a subsequent computation. The latter approach is
>advocated in Slee, Slee and Schmidt "The Endangered Medical Record" (2000).
>It looks promising.
Great! This is exactly the approach that we are using in the OIO project. Do you know
the weaknesses of this approach?
Thanks,
Andrew
---
Andrew P. Ho, M.D.
OIO: Open Infrastructure for Outcomes
www.TxOutcome.Org
Assistant Clinical Professor
Department of Psychiatry, Harbor-UCLA Medical Center
University of California, Los Angeles
Join 18 million Eudora users by signing up for a free Eudora Web-Mail account at
http://www.eudoramail.com
