There are also some works addressing phrase-table size reduction. With
very limited loss in translation quality (if any), it has been shown that
the phrase-table can be pruned by up to 97%. See for instance:
http://www.mt-archive.info/EAMT-2011-Sanchis-Trilles.pdf
http://aclweb.org/anthology-new/N/N07/N07-2006.pdf
http://aclweb.org/anthology-new/D/D07/D07-1103.pdf
Cheers,
Germán
Phrase table shrinking is done :) See Compact Phrase Table in the
advanced section.
W dniu 27.11.2012 10:54, Miles Osborne pisze:
For a long time now I've wanted to see Moses on a small device. Apart from
all of the extra functionality that isn't needed, one would also need to
work on shrinking the phrase table and perhaps also the search graph.
KenLM / RandLM already deal with making the language model smaller.
An interesting research question would be as follows: can we frame decoding on
a
small device in terms of a budget and optimise that budget? We normally don't
bother thinking this way and instead focus entirely on quality. But it might be
possible to instead have a better connection with the amount of space / search
done and quality than we have already. I'm not sure if this is just a matter of
fiddling with the beam size etc. Evince seems to suggest that this doesn't
always give the expected behaviour (ie the relationship between BLEU and beam
size isn't linear).
Miles
--
The University of Edinburgh is a charitable body, registered in Scotland, with
registration number SC005336.
_______________________________________________
Moses-support mailing list
Moses-support@mit.edu
http://mailman.mit.edu/mailman/listinfo/moses-support
_______________________________________________
Moses-support mailing list
Moses-support@mit.edu
http://mailman.mit.edu/mailman/listinfo/moses-support
