Natural language

RE01 Rice Brian T. EM2
Tue, 29 Dec 1998 13:13:38 +0300

> Natural language can be of a great value sometimes, when you have a
> rather complex problem that you want to solve, because of its
> fuzzyness. However, this fuzzyness can be a problem for common actions
> : it can lead to disastruous quiproquos. How shoul the system
> understand a statement like "delete all"? What context should be taken
> into account? What is "all"? 
well, with reflection, the system can hypothesize about what the user means
by "all", for instance, in a formal way.  this would basically involve
dealing with the "algebra of assumptions".  in that way the actions it takes
in response are just as programmable and debuggable as the average "hello
world" program.

> So my conlusion is : yes it would be great, but I do not place it with
> a very high priority in the todo list. However, once we have a core
> system running, some linguists should be able to experiment with our
> system in a seemless fashion, without the need to "hack" every where.
it would be a nice "killer app", though.