Re: [NTLK] Newton Spanish text recognition.

From: Larry Yaeger (lsynewtal_at_beanblossom.in.us)
Date: Tue Sep 21 2004 - 15:55:48 PDT


At 12:33 AM +0200 9/22/04, Roman Pixell wrote:
>larry, is 70k really a good choice considered the small amount of heap?

That may be a reasonable concern, since the new dictionary obviously
is not in the ROMs. I was assuming the word list would be compressed
into the standard dictionary format, which would reduce its
footprint, but heap space might still be an issue. And I'm now
wondering how/if the word list actually gets converted to the
standard dictionary format; I don't remember that tool being built
into the system (though that doesn't mean it wasn't).

>doesnt the english word-list suck heap simultaniously?

Not as such, since it is in the ROMs. The English and alternate
language hypotheses will compete for space in the recognizer's search
engine, so that could conceivably affect accuracy, but the maximum
amount of memory used for that purpose is fixed, so it probably will
not affect heap usage.

>what would the optimal size be?

Sorry, I really don't know. More words -> greater coverage ->
greater overall accuracy. But if you're running out of heap space,
you clearly want to limit what you add to the system.

- larryy

-- 
This is the NewtonTalk list - http://www.newtontalk.net/ for all inquiries
Official Newton FAQ: http://www.chuma.org/newton/faq/
WikiWikiNewt for all kinds of articles: http://tools.unna.org/wikiwikinewt/


This archive was generated by hypermail 2.1.5 : Wed Sep 22 2004 - 09:00:01 PDT