Re: I need a critique: using crm114 to train on (very) limited word set - or are there better ways?

On Wed, Sep 10, 2008 at 09:30:55PM +0200, Ger Hobbelt wrote:

> Now for the fun stuff. The number of parameters (a.k.a. 'words') in
> all possible messages is known (requires a bit of work though) AND
> severely limited. To talk numbers: I'm pretty sure I've got a
> 'vocabulary' of more than 100 words, but I am also pretty sure I'll
> never surpass the 5000 words upper limit. In email analogy terms, that
> would mean I know the lower and upper limits of the number of
> *different* words (no l33t spellings and other tricks for this guy!)
> PLUS I know that each message will:
> a) only contain each word ONCE, and
> b) only contain a limited SUBSET of all the possible words, and
> c) all words will appear in a predetermined, FIXED ORDER in each
> message. (Did I hear a <unique> there? well, maybe not.)
...
> very strong feeling it won't ever get near 95% - contrary to email
> claims / SPAMTREC benchmarks - as there's just way too much noise in
> the inputs obscuring signal.

perhaps a Viterbi decoder is more apt to the task here.

... just a quick 0.02 EUR note - will read up better later/tonight while 
going through my backlog.

-- 
paolo

-------------------------------------------------------------------------
This SF.Net email is sponsored by the Moblin Your Move Developer's challenge
Build the coolest Linux based applications with Moblin SDK & win great prizes
Grand prize is a trip for two to an Open Source event anywhere in the world
http://moblin-contest.org/redirect.php?banner_id=100&url=/