i prefer to use SALM's fixed number of rules 'cos I don't have to think
about the low score threshold or risk have too many rules for a
particular source phrase, which can slow don't decoding.
However, it would be good to know which gives better quality/speed tradeoff.
On 28/06/2016 13:33,
Hi!
I have one question about pruning translation table during EMS training.
What method is better SALM or based on low scores (described here:
http://www.statmt.org/moses/?n=Advanced.RuleTables#ntoc5) ?
SALM filtering takes relatively more time than pruning while LM creation.
But I'm not