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: low Accuracy (Alexandra Birch)
2. Re: exception in running moses using binary, models (Tom Hoar)
3. Re: exception in running moses using binary, models
(Jeroen Vermeulen)
4. Server for Installing System (Vishal Goyal (????? ????))
5. segmentation fault with square brackets inside xml markup
(Hala Maghout)
----------------------------------------------------------------------
Message: 1
Date: Thu, 2 Jul 2015 09:45:58 +0100
From: Alexandra Birch <lexi.birch@gmail.com>
Subject: Re: [Moses-support] low Accuracy
To: fatma elzahraa Eltaher <fatmaeltaher@gmail.com>
Cc: "moses-support@mit.edu" <moses-support@mit.edu>
Message-ID:
<CA+h82t40NpZRf4UMG_9ujUn+YjtB3OPLcgM23KLgh720UxQSZQ@mail.gmail.com>
Content-Type: text/plain; charset="utf-8"
Hi Fatma,
Models are routinely trained with millions of parallel sentence pairs. You
need more data. Please read the Moses software documentation, and Philipp
Koehn's book for more background.
Lexi
On Thu, Jul 2, 2015 at 9:42 AM, fatma elzahraa Eltaher <
fatmaeltaher@gmail.com> wrote:
> Dear All,
>
> I trained my model with 4633 words ,tested it with 342 word and only 99
> word was right . How can I increase the accuracy of my model?
>
> note: I use 1000 word for tuning.
>
>
> thank you,
>
>
>
> Fatma El-Zahraa El -Taher
>
> Teaching Assistant at Computer & System department
>
> Faculty of Engineering, Azhar University
>
> Email : fatmaeltaher@gmail.com
> mobile: +201141600434
>
>
> _______________________________________________
> Moses-support mailing list
> Moses-support@mit.edu
> http://mailman.mit.edu/mailman/listinfo/moses-support
>
>
--
------------------------------------------------------------------------------------------
School of Informatics
University of Edinburgh
Phone +44 (0)131 650-8286
--
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/20150702/6682e225/attachment-0001.htm
------------------------------
Message: 2
Date: Thu, 2 Jul 2015 17:09:09 +0700
From: Tom Hoar <tahoar@precisiontranslationtools.com>
Subject: Re: [Moses-support] exception in running moses using binary,
models
To: moses-support@mit.edu
Message-ID: <55950DC5.8050803@precisiontranslationtools.com>
Content-Type: text/plain; charset=utf-8; format=flowed
It looks like you compiled with the --with-cmph=... flag because your
moses.ini is configured for PhraseDictionaryCompact and the log output
shows it loaded. If this is true and you still get the "Exception:
vector::_M_range_check" error, try removing the suffix (file extension)
.minlexr from the reordering-table path name.
path=/..../binarised-model/reordering-table.minlexr ==>
path=/..../binarised-model/reordering-table
On another note, is it normal to have different "num-features" for
phrase and lexical tables?
PhraseDictionaryCompact num-features=4
LexicalReordering num-features=6
Tom
On 7/2/2015 3:42 PM, moses-support-request@mit.edu wrote:
> Date: Thu, 2 Jul 2015 11:34:55 +0400
> From: Hieu Hoang<hieuhoang@gmail.com>
> Subject: Re: [Moses-support] exception in running moses using binary
> models
> To: Barun Halder<barun.halder@citrix.com>, "moses-support@mit.edu"
> <moses-support@mit.edu>
> Message-ID:<5594E99F.1080600@gmail.com>
> Content-Type: text/plain; charset="windows-1252"
>
> you should binarize the reordering-table file with
> processLexicalTable
> DON'T give it the suffix .minlexr. Then delete your existing file
> reordering-table.minlexr
>
> Alternatively, recompile moses with --with-cmph=... flag and use the
> compact phrase-table and compact reordering model.
>
> If you are new to moses, please work through the tutorial
> http://www.statmt.org/moses/?n=Moses.Baseline
>
------------------------------
Message: 3
Date: Thu, 02 Jul 2015 18:09:00 +0700
From: Jeroen Vermeulen <jtv@precisiontranslationtools.com>
Subject: Re: [Moses-support] exception in running moses using binary,
models
To: moses-support@mit.edu
Message-ID: <55951BCC.5070005@precisiontranslationtools.com>
Content-Type: text/plain; charset=windows-1252
On 02/07/15 17:09, Tom Hoar wrote:
> It looks like you compiled with the --with-cmph=... flag because your
> moses.ini is configured for PhraseDictionaryCompact and the log output
> shows it loaded. If this is true and you still get the "Exception:
> vector::_M_range_check" error, try removing the suffix (file extension)
> .minlexr from the reordering-table path name.
In this case though, looking at the code, I can only see that message
"Loading table into memory" coming from LexicalReorderingTableMemory.
Unless there is a code path that I haven't spotted, that would mean that
either cmph is not compiled in, or no .minlexr file exists. Looks like
a line in the file doesn't contain as many fields as LoadFromFile is
expecting.
Assuming any of this makes sense, I could make things very slightly
better by adding some code to check for this situation and throw a more
helpful error.
Jeroen
------------------------------
Message: 4
Date: Thu, 2 Jul 2015 17:30:20 +0530
From: Vishal Goyal(????? ????) <vishal.pup@gmail.com>
Subject: [Moses-support] Server for Installing System
To: moses-support <moses-support@mit.edu>
Message-ID:
<CADAAq5zjAHmAxsYecttKT_gromRmHAvLL5HE=WQKiHE5nuULwQ@mail.gmail.com>
Content-Type: text/plain; charset="utf-8"
Hello All,
Do u know anyone providing free service of server where MOSES is pre
installed and we can install our MT system there.
Else It is very costly to bear the cost from own pocket.
It approx. costs about 6k INR rupees every month for hosting MT
systemdeveloped using MOSES.
--
*Regards,*
Vishal Goyal,
Ph.D., M.Tech., MCA, M.C.S.D.
Assistant Professor(Stage III),
Department of Computer Science,
Punjabi University Patiala-147002.
*NLP International Conference on 18-19 Sept, 2015: regICON2015*
http://regICON2015.learnpunjabi.org
*Machine Translation Systems:*
[*Online Hindi to Punjabi Machine Translation Tool -*
http://h2p.learnpunjabi.org ]
[*Statistical Approach Based Hindi to Punjabi Machine Translation System *
- http://statmt.org/~vishal/hp/index.cgi
- http://tdil-dc.in/hi2pu/index.cgi
]
*Online Journal: [Research Cell: An International Journal of Engineering
Sciences, http://ijoes.vidyapublications.com
<http://ijoes.vidyapublications.com>]*
*Book: A Simplified Approach to Data Structures, Shroff Publications and
Distributors*
-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://mailman.mit.edu/mailman/private/moses-support/attachments/20150702/7f2b5dd9/attachment-0001.htm
------------------------------
Message: 5
Date: Thu, 2 Jul 2015 17:02:55 +0100
From: Hala Maghout <hala.maghout@gmail.com>
Subject: [Moses-support] segmentation fault with square brackets
inside xml markup
To: moses-support <moses-support@mit.edu>
Message-ID:
<CAE9fu9UOMTUJjHLTrp5QzvjaafqGoWBxPZTSRi-FFa=fax7qTg@mail.gmail.com>
Content-Type: text/plain; charset="utf-8"
Hi,
It appears that there's a problem with square brackets handling with xml
markup in moses. For example, when translation the following segment with
xml markup in moses:
<tm translation="[src]">tgt</tm>
using the following command:
./bin/moses -f moses.ini -xml-input constraint
A segmentation fault happens.
When adding a space between one of the brackets and the text it works.
Best,
Hala
-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://mailman.mit.edu/mailman/private/moses-support/attachments/20150702/9bd36145/attachment.htm
------------------------------
_______________________________________________
Moses-support mailing list
Moses-support@mit.edu
http://mailman.mit.edu/mailman/listinfo/moses-support
End of Moses-support Digest, Vol 105, Issue 4
*********************************************
Subscribe to:
Post Comments (Atom)
0 Response to "Moses-support Digest, Vol 105, Issue 4"
Post a Comment