Hi im building an smt web translation system using your given guidelines on
moses home.
The translations are good , but even after doing the steps of memory
management for speeding up the translation given in the step by step guide
, I am still facing delay in translation output due to disk
I would only put in evidence that irstlm is not responsible for the very large
loading time .
In fact, it starts and ends in less than 1 second (start at 49 seconds and end
at the same time)
So probably as Barry mention, you have to use binarized version of the phrase
and reordering tables
In
It's using lazy mmap as evidenced by the .mm at the end. So loading
time will be fast but this may still explain the slow speed.
Regardless of using IRSTLM or KenLM, cat the binary file /dev/null
first, though not being lazy (remove .mm for IRSTLM or use 8 for KenLM)
should accomplish the
Hi,
I am working on a more compact phrase table representation. I should be
done with it in about one or two months. It is around five times smaller
than the currently used binary phrase table implementation, so it has
much better performance on systems with low RAM. It is already working