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. using sparse features (Prashant Mathur)
2. BLEU result (Ihab Ramadan)
3. Re: BLEU result (Tom Hoar)
----------------------------------------------------------------------
Message: 1
Date: Wed, 12 Nov 2014 21:27:00 +0100
From: Prashant Mathur <prashant@fbk.eu>
Subject: [Moses-support] using sparse features
To: "moses-support@mit.edu" <moses-support@mit.edu>
Message-ID:
<CAK3pNhLSnkrYmPzVmrZwKdGNaJ9yUGyH8D4JYoyyWL-wtwRNyA@mail.gmail.com>
Content-Type: text/plain; charset="utf-8"
Hi All,
I have a question about implementing sparse feature function.
I went through the details on its implementation, still somethings are not
clear.
FYI, I am using an old version of moses which dates back to Release 0.91 I
guess. So, I am sorry if my questions don't relate to the latest
implementation.
1. I was looking at the TargetNgramFeature where MakePrefixNgrams adds
features in Evaluate function. From the code it seems MakePrefixNgrams is
adding sparse features on the fly. Is it correct?
what is the weight assigned to this newly added feature? 1 or 0?
2. What is the difference between these two functions?
*void PlusEquals(const ScoreProducer*sp, const std::string& name, float
score)*
*void SparsePlusEquals(const std::string& full_name, float score)*
It seems like both of them are used for updating sparse feature values..
correct?
Or, do the first one points to sparse features of a particular FF and
second one to generic sparse features?
3. How is the structure like if I use one StatelessFeatureFunction with
unlimited scores? Is it different from having unlimited sparse features?
I assume if there is one FF then there is one weight assigned to it but in
the case of sparse features I have one weight for each feature.
4. In general when should I compute the sparse features?
Thanks for the patience,
--Prashant
PS: I am still trying to figure out stuff, so questions might seem stupid.
-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://mailman.mit.edu/mailman/private/moses-support/attachments/20141112/22e479f8/attachment-0001.htm
------------------------------
Message: 2
Date: Thu, 13 Nov 2014 11:06:25 +0200
From: "Ihab Ramadan" <i.ramadan@saudisoft.com>
Subject: [Moses-support] BLEU result
To: <moses-support@mit.edu>
Message-ID: <003301cfff21$1bd4d390$537e7ab0$@saudisoft.com>
Content-Type: text/plain; charset="us-ascii"
Dears,
I have a BLEU result with 77.67
I used files with 5000 lines to test with, could this result be a fake one?
as the quality does not fit this result as I think
Best Regards
Ihab Ramadan| Senior Developer| <http://www.saudisoft.com/> Saudisoft -
Egypt | Tel +2 02 330 320 37 Ext- 0 | Mob+201007570826 | Fax+20233032036 |
Follow us on
<http://www.linkedin.com/company/77017?trk=vsrp_companies_res_name&trkInfo=V
SRPsearchId%3A1489659901402995947155%2CVSRPtargetId%3A77017%2CVSRPcmpt%3Apri
mary> linked |
<https://www.facebook.com/pages/Saudisoft-Co-Ltd/289968997768973?ref_type=bo
okmark> ZA102637861 | <https://twitter.com/Saudisoft> ZA102637858
-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://mailman.mit.edu/mailman/private/moses-support/attachments/20141113/af505245/attachment-0001.htm
-------------- next part --------------
A non-text attachment was scrubbed...
Name: not available
Type: image/gif
Size: 1314 bytes
Desc: not available
Url : http://mailman.mit.edu/mailman/private/moses-support/attachments/20141113/af505245/attachment-0003.gif
-------------- next part --------------
A non-text attachment was scrubbed...
Name: not available
Type: image/gif
Size: 1317 bytes
Desc: not available
Url : http://mailman.mit.edu/mailman/private/moses-support/attachments/20141113/af505245/attachment-0004.gif
-------------- next part --------------
A non-text attachment was scrubbed...
Name: not available
Type: image/gif
Size: 1351 bytes
Desc: not available
Url : http://mailman.mit.edu/mailman/private/moses-support/attachments/20141113/af505245/attachment-0005.gif
------------------------------
Message: 3
Date: Thu, 13 Nov 2014 10:32:08 +0100
From: Tom Hoar <tahoar@precisiontranslationtools.com>
Subject: Re: [Moses-support] BLEU result
To: moses-support@mit.edu
Message-ID: <54647A98.1060908@precisiontranslationtools.com>
Content-Type: text/plain; charset="windows-1252"
5,000 lines is way too many. You probably only need 2000-3000.
Here are my questions:
1. How many duplicate segments (source & target sentence pairs) are
replicated/repeated in your training corpus?
2. Are your test segments similar to/same/different from your tuning set?
3. How did you select your 5,000 segments? Were they hand-slected? Are
they a random sample representing the entire corpus? etc?
4. Is it possible your test segments are duplicate segments of segments
in your training corpus?
First, how did you select the
On 11/13/2014 10:06 AM, Ihab Ramadan wrote:
>
> Dears,
>
> I have a BLEU result with 77.67
>
> I used files with 5000 lines to test with, could this result be a fake
> one?
>
> as the quality does not fit this result as I think
>
> Best Regards
>
> /Ihab Ramadan/| Senior Developer|Saudisoft <http://www.saudisoft.com/>
> - Egypt| *Tel * +2 02 330 320 37 Ext- 0| Mob+201007570826 |
> Fax+20233032036 | *Follow us on *linked
> <http://www.linkedin.com/company/77017?trk=vsrp_companies_res_name&trkInfo=VSRPsearchId%3A1489659901402995947155%2CVSRPtargetId%3A77017%2CVSRPcmpt%3Aprimary>* |
> **ZA102637861*
> <https://www.facebook.com/pages/Saudisoft-Co-Ltd/289968997768973?ref_type=bookmark>* |
> **ZA102637858* <https://twitter.com/Saudisoft>
>
>
>
> _______________________________________________
> 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/20141113/7ad2045b/attachment.htm
-------------- next part --------------
A non-text attachment was scrubbed...
Name: not available
Type: image/gif
Size: 1314 bytes
Desc: not available
Url : http://mailman.mit.edu/mailman/private/moses-support/attachments/20141113/7ad2045b/attachment.gif
-------------- next part --------------
A non-text attachment was scrubbed...
Name: not available
Type: image/gif
Size: 1317 bytes
Desc: not available
Url : http://mailman.mit.edu/mailman/private/moses-support/attachments/20141113/7ad2045b/attachment-0001.gif
-------------- next part --------------
A non-text attachment was scrubbed...
Name: not available
Type: image/gif
Size: 1351 bytes
Desc: not available
Url : http://mailman.mit.edu/mailman/private/moses-support/attachments/20141113/7ad2045b/attachment-0002.gif
------------------------------
_______________________________________________
Moses-support mailing list
Moses-support@mit.edu
http://mailman.mit.edu/mailman/listinfo/moses-support
End of Moses-support Digest, Vol 97, Issue 16
*********************************************
Subscribe to:
Post Comments (Atom)
0 Response to "Moses-support Digest, Vol 97, Issue 16"
Post a Comment