Send Moses-support mailing list submissions to
moses-support@mit.edu
To subscribe or unsubscribe via the World Wide Web, visit
http://mailman.mit.edu/mailman/listinfo/moses-support
or, via email, send a message with subject or body 'help' to
moses-support-request@mit.edu
You can reach the person managing the list at
moses-support-owner@mit.edu
When replying, please edit your Subject line so it is more specific
than "Re: Contents of Moses-support digest..."
Today's Topics:
1. Re: Decoding Speed perfomance - suggestion and question
(Philipp Koehn)
2. Re: Decoding Speed perfomance - suggestion and question
(Vincent Nguyen)
3. Re: Decoding Speed perfomance - suggestion and question
(Vincent Nguyen)
----------------------------------------------------------------------
Message: 1
Date: Mon, 31 Aug 2015 10:44:32 -0400
From: Philipp Koehn <phi@jhu.edu>
Subject: Re: [Moses-support] Decoding Speed perfomance - suggestion
and question
To: Vincent Nguyen <vnguyen@neuf.fr>
Cc: moses-support <moses-support@mit.edu>
Message-ID:
<CAAFADDBbEz2ZTVVJSG7+JShxu8coipgqEvuL3bEK-TEFLHFLrA@mail.gmail.com>
Content-Type: text/plain; charset="utf-8"
hI,
0.0001 should have no impact on translation quality,
0.001 will have some impact
0.01 is probably a bit too drastic.
But that's the range you should explore.
-phi
On Mon, Aug 31, 2015 at 10:33 AM, Vincent Nguyen <vnguyen@neuf.fr> wrote:
> is there any benchmark on what value / what impact ?
> what should I start with as a test 0.001 ?
>
> the standard value 0.0001 seems really really low to me ....
> maybe I am not getting what this probability exactly refers to.
>
>
>
> where FIELDn is the position of the score (typically 2 for the direct
> phrase probability p(e|f), or 0 for the indirect phrase probability p(f|e))
> and THRESHOLD the maximum probability allowed. A good setting is 2:0.0001,
> which removes all rules, where the direct phrase translation probability is
> below 0.0001.
>
>
>
> Le 31/08/2015 16:14, Philipp Koehn a ?crit :
>
> Hi,
>
> I would suspect that with beam sizes <500 the bulk of the time is
> spent on translation option collection, not decoding. You could speed
> that up with tighter threshold pruning of the phrase table.
>
> See the script scripts/training/threshold-filter.perl or the setting
> score-settings = "--MinScore 2:0.0001"
> in EMS.
>
> -phi
>
> On Mon, Aug 31, 2015 at 3:03 AM, Vincent Nguyen <vnguyen@neuf.fr> wrote:
>
>> Hi,
>>
>> Here are some results with several values with cube pruning pop limit :
>>
>> (pop limit / decoding time for 3000 sentences / BLEU score)
>>
>> 5000 - 15m45 - 29.59
>> 1000 - 4m27 - 29.59
>> 500 - 3m35 - 29.59
>> 200 - 3m15 - 29.51
>> 100 - 3m00 - 29.40
>>
>> Therefore I took 400 - 3m19 - 29.58
>>
>> If I am not mistaken the default value for Moses is 1000 [read in the
>> doc] but in the EMS
>> it is 5000 right now .... which makes the experience so long .....
>> I suggest to change the EMS default value.
>>
>> Is there a way to also use a cube pruning limit in the decoder at Tuning
>> time ?
>>
>> Now with this optimized setting I get a ration of 15 segments per second
>> in average.
>> What is the reason for online tools like Google / Bing to be much much
>> faster.
>> it's not a machine issue, is it ?
>>
>>
>> Cheers
>> Vincent
>>
>> _______________________________________________
>> Moses-support mailing list
>> Moses-support@mit.edu
>> http://mailman.mit.edu/mailman/listinfo/moses-support
>>
>
>
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://mailman.mit.edu/mailman/private/moses-support/attachments/20150831/167c11a3/attachment-0001.html
------------------------------
Message: 2
Date: Mon, 31 Aug 2015 16:33:43 +0200
From: Vincent Nguyen <vnguyen@neuf.fr>
Subject: Re: [Moses-support] Decoding Speed perfomance - suggestion
and question
To: Philipp Koehn <phi@jhu.edu>
Cc: moses-support <moses-support@mit.edu>
Message-ID: <55E465C7.3060706@neuf.fr>
Content-Type: text/plain; charset="utf-8"
is there any benchmark on what value / what impact ?
what should I start with as a test 0.001 ?
the standard value 0.0001 seems really really low to me ....
maybe I am not getting what this probability exactly refers to.
where |FIELDn| is the position of the score (typically 2 for the direct
phrase probability p(e|f), or 0 for the indirect phrase probability
p(f|e)) and |THRESHOLD| the maximum probability allowed. A good setting
is |2:0.0001|, which removes all rules, where the direct phrase
translation probability is below 0.0001.
Le 31/08/2015 16:14, Philipp Koehn a ?crit :
> Hi,
>
> I would suspect that with beam sizes <500 the bulk of the time is
> spent on translation option collection, not decoding. You could speed
> that up with tighter threshold pruning of the phrase table.
>
> See the script scripts/training/threshold-filter.perl or the setting
> score-settings = "--MinScore 2:0.0001"
> in EMS.
>
> -phi
>
> On Mon, Aug 31, 2015 at 3:03 AM, Vincent Nguyen <vnguyen@neuf.fr
> <mailto:vnguyen@neuf.fr>> wrote:
>
> Hi,
>
> Here are some results with several values with cube pruning pop
> limit :
>
> (pop limit / decoding time for 3000 sentences / BLEU score)
>
> 5000 - 15m45 - 29.59
> 1000 - 4m27 - 29.59
> 500 - 3m35 - 29.59
> 200 - 3m15 - 29.51
> 100 - 3m00 - 29.40
>
> Therefore I took 400 - 3m19 - 29.58
>
> If I am not mistaken the default value for Moses is 1000 [read in the
> doc] but in the EMS
> it is 5000 right now .... which makes the experience so long .....
> I suggest to change the EMS default value.
>
> Is there a way to also use a cube pruning limit in the decoder at
> Tuning
> time ?
>
> Now with this optimized setting I get a ration of 15 segments per
> second
> in average.
> What is the reason for online tools like Google / Bing to be much much
> faster.
> it's not a machine issue, is it ?
>
>
> Cheers
> Vincent
>
> _______________________________________________
> Moses-support mailing list
> Moses-support@mit.edu <mailto:Moses-support@mit.edu>
> http://mailman.mit.edu/mailman/listinfo/moses-support
>
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://mailman.mit.edu/mailman/private/moses-support/attachments/20150831/76aafb56/attachment-0001.html
------------------------------
Message: 3
Date: Mon, 31 Aug 2015 16:50:17 +0200
From: Vincent Nguyen <vnguyen@neuf.fr>
Subject: Re: [Moses-support] Decoding Speed perfomance - suggestion
and question
To: Philipp Koehn <phi@jhu.edu>
Cc: moses-support <moses-support@mit.edu>
Message-ID: <55E469A9.4060504@neuf.fr>
Content-Type: text/plain; charset="utf-8"
thanks, will try and post results.
just to be clear:
I can re-use the previous extract file
I have to rebuild the phrase-table with new min score (ie no way to just
filter the previous one ?)
do I have to rebuild the reordering table too ?
Vincent
Le 31/08/2015 16:44, Philipp Koehn a ?crit :
> hI,
>
> 0.0001 should have no impact on translation quality,
> 0.001 will have some impact
> 0.01 is probably a bit too drastic.
>
> But that's the range you should explore.
>
> -phi
>
> On Mon, Aug 31, 2015 at 10:33 AM, Vincent Nguyen <vnguyen@neuf.fr
> <mailto:vnguyen@neuf.fr>> wrote:
>
> is there any benchmark on what value / what impact ?
> what should I start with as a test 0.001 ?
>
> the standard value 0.0001 seems really really low to me ....
> maybe I am not getting what this probability exactly refers to.
>
>
>
> where |FIELDn| is the position of the score (typically 2 for the
> direct phrase probability p(e|f), or 0 for the indirect phrase
> probability p(f|e)) and |THRESHOLD| the maximum probability
> allowed. A good setting is |2:0.0001|, which removes all rules,
> where the direct phrase translation probability is below 0.0001.
>
>
>
> Le 31/08/2015 16:14, Philipp Koehn a ?crit :
>> Hi,
>>
>> I would suspect that with beam sizes <500 the bulk of the time is
>> spent on translation option collection, not decoding. You could speed
>> that up with tighter threshold pruning of the phrase table.
>>
>> See the script scripts/training/threshold-filter.perl or the setting
>> score-settings = "--MinScore 2:0.0001"
>> in EMS.
>>
>> -phi
>>
>> On Mon, Aug 31, 2015 at 3:03 AM, Vincent Nguyen <vnguyen@neuf.fr
>> <mailto:vnguyen@neuf.fr>> wrote:
>>
>> Hi,
>>
>> Here are some results with several values with cube pruning
>> pop limit :
>>
>> (pop limit / decoding time for 3000 sentences / BLEU score)
>>
>> 5000 - 15m45 - 29.59
>> 1000 - 4m27 - 29.59
>> 500 - 3m35 - 29.59
>> 200 - 3m15 - 29.51
>> 100 - 3m00 - 29.40
>>
>> Therefore I took 400 - 3m19 - 29.58
>>
>> If I am not mistaken the default value for Moses is 1000
>> [read in the
>> doc] but in the EMS
>> it is 5000 right now .... which makes the experience so long
>> .....
>> I suggest to change the EMS default value.
>>
>> Is there a way to also use a cube pruning limit in the
>> decoder at Tuning
>> time ?
>>
>> Now with this optimized setting I get a ration of 15 segments
>> per second
>> in average.
>> What is the reason for online tools like Google / Bing to be
>> much much
>> faster.
>> it's not a machine issue, is it ?
>>
>>
>> Cheers
>> Vincent
>>
>> _______________________________________________
>> Moses-support mailing list
>> Moses-support@mit.edu <mailto:Moses-support@mit.edu>
>> http://mailman.mit.edu/mailman/listinfo/moses-support
>>
>>
>
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://mailman.mit.edu/mailman/private/moses-support/attachments/20150831/9ab7133d/attachment.html
------------------------------
_______________________________________________
Moses-support mailing list
Moses-support@mit.edu
http://mailman.mit.edu/mailman/listinfo/moses-support
End of Moses-support Digest, Vol 106, Issue 57
**********************************************
Subscribe to:
Post Comments (Atom)
0 Response to "Moses-support Digest, Vol 106, Issue 57"
Post a Comment