VMs: Backward scanning EVA algorithm

["Jeff" <jeff@xxxxxxxxxxxxxxxxxxxxxx>]

I am finding that I either get whole words that appear in the sample texts
or word pairs that are joined together. So far I always seem to be able to
find the last word in the sample, which I expected. The constructed word
that appears as the first of the pair I usually find as an individual word
either in the sample or by a quick google search. It is as if the first word
can be constructed from the information I have built from the sample text. I
will keep scanning until I have either found a word that does not exist in
the vms or the algorithm exhausts itself.

jeff

BTW this seems to indicate that my algorithm has found a rolling pattern to
word formation. Although this was not exactly what I expected. As if word
boundaries are non existent and words are interlinked by rules somehow.


______________________________________________________________________
To unsubscribe, send mail to majordomo@xxxxxxxxxxx with a body saying:
unsubscribe vms-list