On Mon, 23 Jul 2018, Nick Bright wrote:
On 7/23/2018 8:10 PM, Reindl Harald wrote:
what exactly is the problem right-click on the attachments, save
them to files and drag&drop them to the imap training folder?
What on earth is even right about it? I'm not going to do that for hundreds
or even thousands of submissions sent in by users, that would be insane!
Sorry, responding as I read through the thread.
frankly i trained 100000 mails by save them with right-click and upload
them via sftp and user-submitted mails have to be taken with caution
anyways
Then you don't value your own time I suppose. I find such a solution is
completely unacceptable.
The problem with training unreviewed is: the quality of your corpus is
only as good as your *least responsible* (and least malicious) user.
Having a quality bayes requires a certain level of commitment and effort.
--
John Hardin KA7OHZ http://www.impsec.org/~jhardin/
jhar...@impsec.org FALaholic #11174 pgpk -a jhar...@impsec.org
key: 0xB8732E79 -- 2D8C 34F4 6411 F507 136C AF76 D822 E6E6 B873 2E79
-----------------------------------------------------------------------
Sheep have only two speeds: graze and stampede. -- LTC Grossman
-----------------------------------------------------------------------
481 days since the first commercial re-flight of an orbital booster (SpaceX)
