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: about the scores in run*.best100.out (Arefeh Kazemi)
2. Re: about the scores in run*.best100.out (arefeh_kazemi@yahoo.com)
3. Re: about the scores in run*.best100.out (Matthias Huck)
----------------------------------------------------------------------
Message: 1
Date: Fri, 23 Jan 2015 12:03:29 +0000 (UTC)
From: Arefeh Kazemi <arefeh_kazemi@yahoo.com>
Subject: Re: [Moses-support] about the scores in run*.best100.out
To: Moses-support <moses-support@mit.edu>
Message-ID:
<247320709.71469.1422014609410.JavaMail.yahoo@mail.yahoo.com>
Content-Type: text/plain; charset="utf-8"
Thanks Matthias
>>Can you try to run the setup from the cluster on your local desktop
system? With the same input, a Moses binary compiled from the same
sources, and the same command to produce the n-best lists? Normally it
should give you the same output.
you mean I run the binary file which is produced on the cluster, on my local pc, without compiling moses again?
>>Why would the feature never produce an overall score larger than 60?
my feature calculate multiply of some probabilities for dependency structures of a sentence. a sentence with limited max size has limited number of such dependencies, so I can estimate the maximum value of my feature.
>>Also note that you should not use Assign() in your feature functions any
more (since two weeks ago).
I've already seen your post. I just use PlusEquals in my code, as I understand its not affected by your change, right?
Regards
? On Friday, January 23, 2015 12:11 AM, Matthias Huck <mhuck@inf.ed.ac.uk> wrote:
Hi Arefeh,
Can you try to run the setup from the cluster on your local desktop
system? With the same input, a Moses binary compiled from the same
sources, and the same command to produce the n-best lists? Normally it
should give you the same output.
Why would the feature never produce an overall score larger than 60?
Also note that you should not use Assign() in your feature functions any
more (since two weeks ago).
http://comments.gmane.org/gmane.comp.nlp.moses.user/12146
If you use Assign rather than PlusEquals and you merged with the recent
master from GitHub on the cluster but not on your desktop machine, then
something like what you described can have happened.
Cheers,
Matthias
On Thu, 2015-01-22 at 21:00 +0000, Arefeh Kazemi wrote:
> Hi
>
>
> I've implemented a feature with 4 scores in moses-chart. when I debug
> the code on my system, every thing is OK and the scores are calculated
> right, but when I run mert to tune the weights (on a cluster), I get
> wrong scores for my feature in run*.best.100 files. for example my
> feature could have the maximum value of 60 but for some instances I
> get values more than 300.
>
> does anyone know why this happens?
>
>
> Regards
>
>
> _______________________________________________
> Moses-support mailing list
> Moses-support@mit.edu
> http://mailman.mit.edu/mailman/listinfo/moses-support
--
The University of Edinburgh is a charitable body, registered in
Scotland, with registration number SC005336.
-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://mailman.mit.edu/mailman/private/moses-support/attachments/20150123/4340a149/attachment-0001.htm
------------------------------
Message: 2
Date: Fri, 23 Jan 2015 00:37:10 +0000
From: arefeh_kazemi@yahoo.com
Subject: Re: [Moses-support] about the scores in run*.best100.out
To: Matthias Huck <mhuck@inf.ed.ac.uk>, moses-support@mit.edu
Message-ID: <0ec045a5-965b-4cb5-8452-9051da29bdc6.maildroid@localhost>
Content-Type: text/plain; charset="utf-8"
Thanks Matthias,
You mean I run the binary which has been produced on the cluster on my local desktop, without compiling moses again?
My feature score for a sentence or a part of it, is the multiply of probabilities for its dependency structures. Each sentence with limited max size has a maximum number of such dependencies. So I can estimate the maximum value of my feature.
Yep, I've seen your previous email about changing the code. I just use plusEquals in my feature to add scores, as I understand, the new code does not affect it. Right?
Sent from my android device.
-----Original Message-----
From: Matthias Huck <mhuck@inf.ed.ac.uk>
To: Arefeh Kazemi <arefeh_kazemi@yahoo.com>
Cc: Moses-support <moses-support@mit.edu>
Sent: Fri, 23 Jan 2015 0:11
Subject: Re: [Moses-support] about the scores in run*.best100.out
Hi Arefeh,
Can you try to run the setup from the cluster on your local desktop
system? With the same input, a Moses binary compiled from the same
sources, and the same command to produce the n-best lists? Normally it
should give you the same output.
Why would the feature never produce an overall score larger than 60?
Also note that you should not use Assign() in your feature functions any
more (since two weeks ago).
http://comments.gmane.org/gmane.comp.nlp.moses.user/12146
If you use Assign rather than PlusEquals and you merged with the recent
master from GitHub on the cluster but not on your desktop machine, then
something like what you described can have happened.
Cheers,
Matthias
On Thu, 2015-01-22 at 21:00 +0000, Arefeh Kazemi wrote:
> Hi
>
>
> I've implemented a feature with 4 scores in moses-chart. when I debug
> the code on my system, every thing is OK and the scores are calculated
> right, but when I run mert to tune the weights (on a cluster), I get
> wrong scores for my feature in run*.best.100 files. for example my
> feature could have the maximum value of 60 but for some instances I
> get values more than 300.
>
> does anyone know why this happens?
>
>
> Regards
>
>
> _______________________________________________
> Moses-support mailing list
> Moses-support@mit.edu
> http://mailman.mit.edu/mailman/listinfo/moses-support
--
The University of Edinburgh is a charitable body, registered in
Scotland, with registration number SC005336.
-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://mailman.mit.edu/mailman/private/moses-support/attachments/20150123/4abd04e7/attachment-0001.htm
------------------------------
Message: 3
Date: Fri, 23 Jan 2015 15:48:24 +0000
From: Matthias Huck <mhuck@inf.ed.ac.uk>
Subject: Re: [Moses-support] about the scores in run*.best100.out
To: Arefeh Kazemi <arefeh_kazemi@yahoo.com>
Cc: Moses-support <moses-support@mit.edu>
Message-ID: <1422028104.2192.211.camel@portedgar>
Content-Type: text/plain; charset="UTF-8"
Hi Arefeh,
On Fri, 2015-01-23 at 12:03 +0000, Arefeh Kazemi wrote:
>
> >>Can you try to run the setup from the cluster on your local desktop
> system? With the same input, a Moses binary compiled from the same
> sources, and the same command to produce the n-best lists? Normally it
> should give you the same output.
>
>
> you mean I run the binary file which is produced on the cluster, on my
> local pc, without compiling moses again?
If you can use the binary from the cluster, yes, copy it to your desktop
system and run that.
Your previous mail seemed to indicate that you observe the issue on the
cluster only, not on your local machine. Make sure you did not use a
different Moses code base first. See if the output is the same on some
toy setup. Then try to reproduce the setup from the cluster on your
desktop (if the memory requirements allow for that).
>
>
> >>Why would the feature never produce an overall score larger than
> 60?
>
>
>
> my feature calculate multiply of some probabilities for dependency
> structures of a sentence. a sentence with limited max size has limited
> number of such dependencies, so I can estimate the maximum value of my
> feature.
Okay, that makes sense.
>
>
>
> >>Also note that you should not use Assign() in your feature functions
> any
> more (since two weeks ago).
>
>
> I've already seen your post. I just use PlusEquals in my code, as I
> understand its not affected by your change, right?
No, if you used Assign() before, you've been setting the overall score
for the complete derivation so far. With PlusEquals() you're adding
deltas. They get accumulated. You need to rewrite your code to compute a
delta score just for the current hypothesis expansion. (Typical feature
functions compute that kind of score anyway, but maybe yours didn't.)
If you used PlusEquals() before already, then you don't have to modify
anything.
Cheers,
Matthias
>
>
> Regards
>
>
> On Friday, January 23, 2015 12:11 AM, Matthias Huck
> <mhuck@inf.ed.ac.uk> wrote:
>
>
>
> Hi Arefeh,
>
> Can you try to run the setup from the cluster on your local desktop
> system? With the same input, a Moses binary compiled from the same
> sources, and the same command to produce the n-best lists? Normally it
> should give you the same output.
>
> Why would the feature never produce an overall score larger than 60?
>
> Also note that you should not use Assign() in your feature functions
> any
> more (since two weeks ago).
> http://comments.gmane.org/gmane.comp.nlp.moses.user/12146
> If you use Assign rather than PlusEquals and you merged with the
> recent
> master from GitHub on the cluster but not on your desktop machine,
> then
> something like what you described can have happened.
>
> Cheers,
> Matthias
>
>
>
> On Thu, 2015-01-22 at 21:00 +0000, Arefeh Kazemi wrote:
> > Hi
> >
> >
> > I've implemented a feature with 4 scores in moses-chart. when I
> debug
> > the code on my system, every thing is OK and the scores are
> calculated
> > right, but when I run mert to tune the weights (on a cluster), I get
> > wrong scores for my feature in run*.best.100 files. for example my
> > feature could have the maximum value of 60 but for some instances I
> > get values more than 300.
> >
> > does anyone know why this happens?
> >
> >
> > Regards
>
> >
> >
> > _______________________________________________
> > Moses-support mailing list
> > Moses-support@mit.edu
> > http://mailman.mit.edu/mailman/listinfo/moses-support
>
>
>
> --
> 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
>
--
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
End of Moses-support Digest, Vol 99, Issue 54
*********************************************
Subscribe to:
Post Comments (Atom)
0 Response to "Moses-support Digest, Vol 99, Issue 54"
Post a Comment