Re: [Moses-support] Eliminating load times for MOSES phrase table, language model and reordering model

[Mathias Müller]

Hi Roko

Apart from compact phrase tables, which you should try:

You could start several Moses servers on different ports, with different 
decoding parameters. Would that not be feasible for you?


Regards

Mathias


On 05.04.17 13:33, RR wrote:

Hi,

I am currently working on a system to explore MOSES decoding parameter 
space - running MOSES in decoding mode with one parameter set, getting 
a BLEU score and rerunning with different parameters.


More than 50% of my time is being spent repeatedly "loading" the 
phrase table, language model and reordering model. For example,


$ ./example.fr  | .../moses -f ./run11.moses.ini 
-threads 31   > ./trans_baseline


gives: "Start loading text phrase table. Moses format : [37.296] 
seconds."


37 seconds just to load a 590MB phrase table, even if it is on 
RAMDISK. htop indicates that for those 37 seconds, a single core is 
100% utilized.


My understanding is that some kind of optimized data structure (a hash 
table of some kind?) is being created in those 37 seconds, which is 
then lost and recreated when I re-run MOSES with a different value of 
a decoding parameter.


If I want to eliminate this loading time, what is the best way 
forward? Is there a phrase table format that avoids a significant 
loading time (i.e. a 500MB phrase table loads in < 1 sec)? Should I 
try to find a way to run a single MOSES server but with different 
decoding parameters? I have a system with 130GB RAM and I am using a 
small phrase table that has been filtered for my decoding set.


Thanks in advance,

Roko


___
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

Re: [Moses-support] Eliminating load times for MOSES phrase table, language model and reordering model

[Dingyuan Wang]

Try Compact Table? http://www.statmt.org/moses/?n=Advanced.RuleTables#ntoc3

2017年4月5日 下午7:33，"RR" 寫道：

> Hi,
>
> I am currently working on a system to explore MOSES decoding parameter
> space - running MOSES in decoding mode with one parameter set, getting a
> BLEU score and rerunning with different parameters.
>
> More than 50% of my time is being spent repeatedly "loading" the phrase
> table, language model and reordering model. For example,
>
> $ ./example.fr | .../moses -f ./run11.moses.ini -threads 31   >
> ./trans_baseline
>
> gives: "Start loading text phrase table. Moses format : [37.296] seconds."
>
> 37 seconds just to load a 590MB phrase table, even if it is on RAMDISK.
> htop indicates that for those 37 seconds, a single core is 100% utilized.
>
> My understanding is that some kind of optimized data structure (a hash
> table of some kind?) is being created in those 37 seconds, which is then
> lost and recreated when I re-run MOSES with a different value of a decoding
> parameter.
>
> If I want to eliminate this loading time, what is the best way forward? Is
> there a phrase table format that avoids a significant loading time (i.e. a
> 500MB phrase table loads in < 1 sec)? Should I try to find a way to run a
> single MOSES server but with different decoding parameters? I have a system
> with 130GB RAM and I am using a small phrase table that has been filtered
> for my decoding set.
>
> Thanks in advance,
>
> Roko
>
> ___
> 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