[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

VMs: Re: RE: Re: RE: Re: Information lost!

Mark wrote: 

(1) Create a function which measures the similarity of neighbouring words.
(2) Apply the function to the whole VMs text and note the overall 'score'.
(3) randomise the word order and rescore.

(4) repeat (3) and see how many randomisations it takes before you
   get a similar score (or higher) than the original.


To make sure not to spread (thin out) a local effect, first of all I think the procedure should be applied only to the parts (language, subject) of the manuscript where these pairs occur (more or less consistently) at high freuqency, that is if not through all of the VMs. And ofcourse if you didn't do that already.

In this case do you have a figure of the numbers of such pairs you get on average in such simulations, as opposed to the number actually found?

Ger





---
Outgoing mail is certified Virus Free.
Checked by AVG anti-virus system (http://www.grisoft.com).
Version: 6.0.784 / Virus Database: 530 - Release Date: 28-10-2004 

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